{"title":"AI Agents \u0026 LLM Ops Skills","description":"\u003cp\u003eProduction-grade AI Skills for the people who build and run LLM agents: RAG and retrieval, context engineering, agent orchestration, evaluation, guardrails, LLMOps and inference, fine-tuning, voice and realtime, cost and latency, memory and knowledge graphs, and agent QA. Each Skill turns Claude, ChatGPT and other models into a senior AI engineer that ships real, reviewable artifacts.\u003c\/p\u003e","products":[{"product_id":"kai-rag-retrieval-architect","title":"Kai - RAG Engineer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Kai into Claude and get a senior RAG architect who builds retrieval that returns the right context, measured with an eval harness before you tune.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eKai treats retrieval as an information-retrieval problem first: corpus prep and chunking strategy, embedding selection, vector index tuning (HNSW\/IVF), hybrid search (BM25 + dense) with RRF fusion, cross-encoder reranking, query transformation (multi-query, HyDE, decomposition), retrieval and end-to-end evaluation (recall@k, MRR, nDCG, faithfulness), grounding and citation, freshness, and the cost and latency of every hop. Measure before you tune. Always evaluate on a held-out labeled set in dev\/staging before serving in production.\u003c\/p\u003e\n  \u003cdiv style=\"background: #ECEDFC; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #4A5BEE; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eChunking strategy and metadata design\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eHybrid search (BM25 + dense) with RRF and cross-encoder reranking\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eQuery transformation: multi-query, HyDE, decomposition\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eRetrieval eval: recall@k, MRR, nDCG, faithfulness, with before\/after\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 kai-rag-retrieval-architect.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #4A5BEE; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#4A5BEE; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Kai builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58312988721416,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/kai-rag-retrieval-architect-book.jpg?v=1787150383"},{"product_id":"selin-context-engineer","title":"Selin - Context Engineer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Selin into Claude and get a senior context engineer who treats the context window as a scarce, ordered token budget and makes every token earn its place.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eSelin engineers the context window: token accounting across system prompt, tools, retrieved snippets, memory and history; context assembly and templating; positional placement (lost-in-the-middle, primacy and recency); compression and summarization before truncation; retrieved-context selection and dedup; tool-result trimming; memory injection; multi-turn history windowing and eviction; structured context; and prompt caching. Measure whether the model actually uses the context. Always evaluate on a held-out set in dev\/staging before production.\u003c\/p\u003e\n  \u003cdiv style=\"background: #ECEDFC; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #4A5BEE; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eToken accounting and per-region context budgets\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003ePlacement for lost-in-the-middle, primacy and recency\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eCompression, dedup and tool-result trimming before truncation\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eHistory windowing, memory injection and prompt caching\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 selin-context-engineer.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #4A5BEE; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#4A5BEE; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Selin builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58312991899912,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/selin-context-engineer-book.jpg?v=1787150384"},{"product_id":"enzo-ai-agent-orchestrator","title":"Enzo - AI Agent Orchestrator AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Enzo into Claude and get a senior agent orchestrator who builds the agent loop: typed state, validated tool calls, retries, loop guards and traces.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eEnzo builds agent runtimes: the perceive-plan-act-observe loop, tool and function calling with JSON schemas, argument validation, timeout\/retry and idempotency, planning patterns (ReAct, plan-and-execute, reflection), multi-agent topologies (supervisor\/worker, hierarchical, sequential) and when each earns its cost, typed state and checkpoints, human-in-the-loop, loop-guarding and budgets, observability and tracing, and the cost and latency of multi-step runs. Framework-aware (LangGraph, CrewAI, AutoGen, OpenAI Agents SDK, Anthropic tool use), not married to one. Always test in staging with guardrails, budgets and traces before production.\u003c\/p\u003e\n  \u003cdiv style=\"background: #ECEDFC; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #4A5BEE; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eThe agent loop with schema-validated tool calls\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eRetries, timeouts, idempotency and loop guards\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003ePlanning patterns and multi-agent topologies (with cost\/benefit)\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eTyped state, human-in-the-loop, tracing and cost\/latency\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 enzo-ai-agent-orchestrator.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #4A5BEE; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#4A5BEE; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Enzo builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58312997404936,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/enzo-ai-agent-orchestrator-book.jpg?v=1787150385"},{"product_id":"ingrid-llm-evaluation-engineer","title":"Ingrid - LLM Evaluation Engineer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Ingrid into Claude and get a senior LLM evaluation engineer whose rule is simple: no ship without an eval gate.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eIngrid evaluates LLM apps and agents: building golden datasets (coverage, edge cases, no leakage, versioning), metric selection, LLM-as-judge (rubric design, pairwise vs pointwise, bias and position effects with mitigations, calibration against human labels), RAG metrics (faithfulness, context and answer relevance), agent trajectory eval (tool-call correctness, task completion), offline harnesses and CI regression gates, online eval (A\/B, guardrail metrics, human review sampling), and statistical rigor (confidence intervals, significance). Tools like Ragas, promptfoo, DeepEval, LangSmith and Braintrust, without lock-in. Always evaluate on a held-out set before shipping.\u003c\/p\u003e\n  \u003cdiv style=\"background: #ECEDFC; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #4A5BEE; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eGolden datasets: coverage, edge cases, no leakage\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eLLM-as-judge: rubric, bias mitigation, human calibration\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eRAG and agent metrics (faithfulness, tool-call accuracy)\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eCI regression gates with confidence intervals and significance\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 ingrid-llm-evaluation-engineer.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #4A5BEE; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#4A5BEE; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Ingrid builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58313000845576,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/ingrid-llm-evaluation-engineer-book.jpg?v=1787150385"},{"product_id":"rania-ai-guardrails-engineer","title":"Rania - AI Safety Engineer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Rania into Claude and get a senior guardrails engineer who hardens your own agent against prompt injection and data leakage, defense only.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eRania builds defensive guardrails for your LLM app: input guardrails (prompt-injection and jailbreak detection and mitigation, instruction-hierarchy enforcement, delimiting untrusted content), output guardrails (schema and format validation, PII detection and redaction, moderation, faithfulness and leakage checks), tool-use guardrails (least privilege, argument validation, confirmation gates for high-impact actions), rate and abuse limiting, and layered defense measured with your own red-team suite. Tools like Llama Guard, NeMo Guardrails, Guardrails AI and Presidio, without lock-in. Strictly defensive: no working jailbreaks, exploits or malware. Test on a held-out set in staging before production.\u003c\/p\u003e\n  \u003cdiv style=\"background: #ECEDFC; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #4A5BEE; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003ePrompt-injection and jailbreak detection and mitigation (defensive)\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eOutput guardrails: schema validation, PII redaction, moderation\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eTool guardrails: least privilege, arg validation, confirmation gates\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eLayered defense measured with your own red-team suite\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 rania-ai-guardrails-engineer.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #4A5BEE; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#4A5BEE; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Rania builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58313004581128,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/rania-ai-guardrails-engineer-book.jpg?v=1787150385"},{"product_id":"dario-llmops-inference-engineer","title":"Dario - LLMOps Engineer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Dario into Claude and get a senior LLMOps engineer who runs your model like an SRE-owned service: SLOs, a gateway, dashboards and one-step rollback.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eDario serves and operates LLMs in production: inference engines (vLLM, TGI, TensorRT-LLM), throughput vs latency (continuous batching, KV-cache, paged attention, speculative decoding, quantization tradeoffs), an LLM gateway (routing, fallbacks, retries, timeouts, rate and quota limits, key management), autoscaling and GPU capacity planning, caching (prefix and semantic), reliability (circuit breakers, multi-provider failover), observability (p50\/p95\/p99, TTFT, tokens\/sec, cost per request, alerts), and canary\/shadow rollout with SLOs and error budgets. Tools like vLLM, LiteLLM, KServe, Prometheus, Grafana and Langfuse, without lock-in. Roll out via canary in staging first.\u003c\/p\u003e\n  \u003cdiv style=\"background: #ECEDFC; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #4A5BEE; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eInference tuning: continuous batching, KV-cache, quantization\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eAn LLM gateway: routing, fallbacks, retries, rate limits\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eCapacity math, autoscaling and prefix\/semantic caching\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eObservability (TTFT, p95, cost\/req), SLOs and canary rollout\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 dario-llmops-inference-engineer.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #4A5BEE; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#4A5BEE; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Dario builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58313009463560,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/dario-llmops-inference-engineer-book.jpg?v=1787150385"},{"product_id":"mei-llm-finetuning-engineer","title":"Mei - LLM Fine-tuning Engineer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Mei into Claude and get a senior fine-tuning engineer whose first question is: have you exhausted prompting and RAG? You earn the fine-tune and prove it with eval.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eMei adapts LLMs the disciplined way: when not to fine-tune (prompt\/RAG first) and when it genuinely wins (format and schema adherence, tool-call reliability, latency and cost via smaller models, domain tone), dataset curation (quality over quantity, dedup, decontamination against the eval set, chat templating), methods (full SFT vs PEFT: LoRA\/QLoRA rank\/alpha\/target modules, learning rate, epochs, packing), preference tuning (DPO\/ORPO\/KTO), GPU-memory math, overfitting and catastrophic forgetting detection, evaluation vs the base model, and serving the adapter. Tools like Hugging Face TRL\/PEFT, Axolotl, Unsloth and bitsandbytes, without lock-in. Always evaluate on a held-out set before serving.\u003c\/p\u003e\n  \u003cdiv style=\"background: #ECEDFC; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #4A5BEE; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eWhen NOT to fine-tune vs when it genuinely wins\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eDataset curation: dedup, decontamination, chat templating\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eQLoRA\/LoRA and preference tuning (DPO\/ORPO\/KTO) with defaults\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eGPU-memory math, forgetting checks and base-vs-tuned eval\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 mei-llm-finetuning-engineer.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #4A5BEE; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#4A5BEE; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Mei builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58313013002504,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/mei-llm-finetuning-engineer-book.jpg?v=1787150386"},{"product_id":"aksel-voice-realtime-agent-engineer","title":"Aksel - Voice Agent Engineer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Aksel into Claude and get a senior voice AI engineer who builds low-latency realtime agents where latency is the product.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eAksel builds voice and realtime agents: the STT to LLM to TTS pipeline (and speech-to-speech realtime APIs), the latency budget (sub-800ms target broken down across VAD, endpointing, STT, LLM TTFT, TTS first-audio and network), streaming everything, turn-taking (voice activity detection, endpointing, barge-in and interruption), telephony vs web (SIP, WebRTC, codecs), mid-conversation tool calls, error recovery, and evaluation (latency percentiles, word error rate, task success). Tools like Deepgram, Whisper, ElevenLabs, Cartesia, LiveKit, Pipecat and the OpenAI Realtime API, without lock-in. Test in staging under real network conditions before production.\u003c\/p\u003e\n  \u003cdiv style=\"background: #ECEDFC; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #4A5BEE; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eThe realtime STT-LLM-TTS pipeline and a per-stage latency budget\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eTurn-taking: VAD, endpointing and barge-in handling\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eTelephony vs web (SIP, WebRTC) and mid-call tool calls\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eEvaluation: latency percentiles, word error rate, task success\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 aksel-voice-realtime-agent-engineer.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #4A5BEE; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#4A5BEE; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Aksel builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58313018474760,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/aksel-voice-realtime-agent-engineer-book.jpg?v=1787150385"},{"product_id":"devika-llm-cost-latency-optimizer","title":"Devika - LLM Cost \u0026 Latency Optimizer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Devika into Claude and get a senior cost and latency optimizer who cuts spend and tail latency while measuring quality on every change.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eDevika cuts the cost and latency of LLM features without wrecking quality: token accounting and cost modeling, model routing and cascades (cheap model first, escalate on low confidence), prompt slimming (shorter prompts, fewer and better few-shots, output-length control, structured output), caching (exact, prefix and semantic with thresholds), batching, retrieval trimming, streaming for perceived latency, and quantization tradeoffs, always with a quality gate so you never trade cost for silent quality loss. Tools like LiteLLM, Helicone, Langfuse and tiktoken, without lock-in. Measure quality on a held-out set for every cost cut.\u003c\/p\u003e\n  \u003cdiv style=\"background: #ECEDFC; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #4A5BEE; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eToken accounting and a cost model that finds the big line items\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eModel routing\/cascades and prompt slimming\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eExact, prefix and semantic caching with thresholds\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eA quality gate on every cost cut, with before\/after numbers\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 devika-llm-cost-latency-optimizer.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #4A5BEE; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#4A5BEE; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Devika builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58313022636296,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/devika-llm-cost-latency-optimizer-book.jpg?v=1787150387"},{"product_id":"soren-agent-memory-knowledge-graph","title":"Soren - AI Agent Memory Engineer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Soren into Claude and get a senior memory engineer who gives your agent durable, useful memory, with the write path done right before retrieval.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eSoren builds agent memory: the memory types (working, episodic, semantic, procedural), the write path (fact and entity extraction, dedup, conflict resolution and supersede, decay and forgetting), the read path (retrieval by relevance and recency), storage backends (vector for semantic recall, a knowledge graph for entities and relations, key-value for profile), knowledge-graph construction and GraphRAG, personalization and multi-session continuity, privacy and deletion, and evaluating whether memory improves task success. Tools like Mem0, Zep, Letta\/MemGPT, Neo4j and pgvector, without lock-in. Bound memory growth and evaluate on a held-out set before production.\u003c\/p\u003e\n  \u003cdiv style=\"background: #ECEDFC; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #4A5BEE; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eMemory types and the write path (extract, dedup, supersede, decay)\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eRead path: retrieval by relevance and recency\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eHybrid backends: vector + knowledge graph + profile\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eGraphRAG, personalization, privacy\/deletion and memory eval\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 soren-agent-memory-knowledge-graph.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #4A5BEE; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#4A5BEE; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Soren builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58313026044168,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/soren-agent-memory-knowledge-graph-book.jpg?v=1787150386"},{"product_id":"liora-agent-qa-red-team-engineer","title":"Liora - AI Red Team Engineer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Liora into Claude and get a senior agent QA engineer who tests and hardens your own agent with behavioral suites and a defensive red-team pass.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eLiora quality-assures non-deterministic agents: behavioral test suites (assertions on tool calls, output schema, task completion and refusal behavior), an eval\/test dataset (happy path, edge cases, robustness), trajectory testing (tool selection, argument correctness, loop and termination, recovery), defensive robustness and red-team testing of your own agent (prompt-injection and jailbreak resistance, PII-leak checks, off-policy refusals), regression testing across prompt and model changes, flakiness handling (seeds, pass@k), grounding checks, and CI gates. Tools like promptfoo, DeepEval, LangSmith and pytest, without lock-in. Strictly defensive: your own agent only, no attack tooling. Gate in CI in staging before release.\u003c\/p\u003e\n  \u003cdiv style=\"background: #ECEDFC; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #4A5BEE; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eBehavioral tests: tool calls, schema, task completion, refusals\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eTrajectory testing and flakiness handling (pass@k)\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eDefensive red-team: injection\/jailbreak resistance, PII-leak checks\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eRegression testing and CI gates before release\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 liora-agent-qa-red-team-engineer.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #4A5BEE; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#4A5BEE; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Liora builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58313031516424,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/liora-agent-qa-red-team-engineer-book.jpg?v=1787150387"},{"product_id":"cyrus-ai-agent-architect","title":"Cyrus - AI Agent Architect AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Cyrus into Claude and get a senior agent architect whose signature move is talking you down the ladder to the simplest thing that works, and writing the tradeoffs into an ADR.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eCyrus designs whole agentic systems and makes the hard calls: when to use a single prompt vs RAG vs a fixed workflow vs an agent vs multi-agent (agents earn their cost only with genuine open-ended decisioning), reference architectures (retrieval, tools, memory, orchestration, guardrails, evals, observability), build-vs-framework, reliability for non-deterministic systems (idempotency, retries, human-in-the-loop, fallbacks, budgets, loop guards), cost and latency architecture, security and data boundaries (least-privilege tools, untrusted-input isolation, PII), evaluation and observability as first-class, failure-mode analysis, rollout, and capturing decisions as ADRs with tradeoffs. Framework-agnostic (LangGraph, CrewAI, OpenAI Agents SDK, Anthropic tool use). Nothing ships without evals, guardrails and observability.\u003c\/p\u003e\n  \u003cdiv style=\"background: #ECEDFC; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #4A5BEE; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eThe decision ladder: prompt vs RAG vs workflow vs agent vs multi-agent\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eReference architecture: retrieval, tools, memory, guardrails, evals\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(74,91,238,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eReliability, cost, latency and security tradeoffs\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#4A5BEE; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eADRs, failure-mode analysis and a phased rollout\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 cyrus-ai-agent-architect.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #4A5BEE; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#4A5BEE; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Cyrus builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58313034858760,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/cyrus-ai-agent-architect-book.jpg?v=1787150386"},{"product_id":"tarquin-prompt-ops-lifecycle-manager","title":"Tarquin - Prompt Operations Manager AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Tarquin into Claude and get a prompt ops lead who treats every prompt as a versioned production artifact with a regression suite behind it.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eTarquin owns the prompt lifecycle end to end: a prompt registry with real version control and immutable release tags, staged rollout and instant rollback, regression suites that run automatically on every prompt change, A\/B and shadow testing of prompt variants with enough traffic to be conclusive, templating and variable-injection safety, drift detection when a model version changes underneath a prompt you never touched, and per-template token budgeting. He refuses to let a prompt reach production on a copy-paste from someone's chat window.\u003c\/p\u003e\n  \u003cdiv style=\"background: #EEECFD; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #5B4BE8; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003ePrompt registry, versioning and immutable release tags\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eRegression suites that gate every prompt change\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eStaged rollout, shadow tests and instant rollback\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eDrift detection when the model changes under a stable prompt\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 tarquin-prompt-ops-lifecycle-manager.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #5B4BE8; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#5B4BE8; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package, open Claude, paste SKILL.md into your Project Instructions or system prompt, describe your requirement, and Tarquin builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58371215884552,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/tarquin-prompt-ops-lifecycle-manager-book.jpg?v=1787150439"},{"product_id":"xanthe-mcp-tool-integration-engineer","title":"Xanthe - MCP Developer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Xanthe into Claude and get a tool-layer engineer who designs tool schemas the model can actually call correctly, and secures what those tools can reach.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eXanthe owns the layer between an agent and the systems it acts on: Model Context Protocol server design, tool and function schema authoring that models call correctly on the first attempt, argument validation and coercion, idempotency and retry semantics for side-effecting tools, error surfaces the model can recover from, auth and token scoping so a tool cannot exceed its mandate, tool-count and description budgeting when selection accuracy starts degrading, and pagination and result shaping so a tool response does not blow the context window.\u003c\/p\u003e\n  \u003cdiv style=\"background: #EEECFD; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #5B4BE8; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eMCP server design and tool schema authoring\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eArgument validation, idempotency and retry semantics\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eAuth scoping and token passthrough hazards\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eTool-count budgeting and result shaping for context\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 xanthe-mcp-tool-integration-engineer.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #5B4BE8; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#5B4BE8; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package, open Claude, paste SKILL.md into your Project Instructions or system prompt, describe your requirement, and Xanthe builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58371219751176,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/xanthe-mcp-tool-integration-engineer-book.jpg?v=1787150439"},{"product_id":"rurik-ai-product-manager","title":"Rurik - AI\/ML Product Manager AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Rurik into Claude and get an AI product manager who will tell you which of your AI features should not be built at all.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eRurik owns the product side of shipping LLM features: deciding whether a problem deserves an AI feature or a deterministic one, writing requirements against probabilistic rather than deterministic behavior, defining acceptance criteria as measurable eval scores instead of vibes, unit economics and pricing for token-metered features, staged launch with human-in-the-loop fallbacks, expectation-setting and trust design in the UI, and killing features that do not beat a boring deterministic baseline. He treats an unmeasurable quality bar as a missing requirement, not a soft one.\u003c\/p\u003e\n  \u003cdiv style=\"background: #EEECFD; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #5B4BE8; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eDecide what should not be an AI feature at all\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eRequirements and acceptance criteria as eval scores\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eToken unit economics and pricing per feature\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eStaged launch, fallbacks and trust design in the UI\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 rurik-ai-product-manager.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #5B4BE8; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#5B4BE8; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package, open Claude, paste SKILL.md into your Project Instructions or system prompt, describe your requirement, and Rurik builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58371224273160,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/rurik-ai-product-manager-book.jpg?v=1787150441"},{"product_id":"almeric-vector-database-index-operations-engineer","title":"Almeric - Vector Database Engineer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Almeric into Claude and get a vector infrastructure engineer who tunes recall against latency with measured curves, not defaults copied from a quickstart.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eAlmeric runs the vector store as production infrastructure: index type and parameter selection across HNSW, IVF and ScaNN with real M, efConstruction, efSearch, nlist and nprobe reasoning, measured recall-versus-latency curves rather than vendor claims, sharding and replication topology, memory and disk sizing per billion vectors, quantization tradeoffs across scalar, product and binary, zero-downtime reindexing and migration, metadata-filtering performance cliffs, and platform selection across pgvector, Qdrant, Pinecone, Weaviate and Milvus.\u003c\/p\u003e\n  \u003cdiv style=\"background: #EEECFD; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #5B4BE8; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eHNSW\/IVF\/ScaNN parameter selection with real tradeoffs\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eMeasured recall-versus-latency curves, not vendor claims\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eMemory and disk sizing, sharding and replication\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eQuantization tradeoffs and zero-downtime reindexing\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 almeric-vector-database-index-operations-engineer.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #5B4BE8; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#5B4BE8; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package, open Claude, paste SKILL.md into your Project Instructions or system prompt, describe your requirement, and Almeric builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58371230531848,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/almeric-vector-database-index-operations-book.jpg?v=1787150440"},{"product_id":"thibaut-eval-dataset-synthetic-data-engineer","title":"Thibaut - Synthetic Data Engineer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Thibaut into Claude and get a data engineer who builds the eval set your scores are only as trustworthy as.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eThibaut builds and curates the datasets underneath every eval and every fine-tune: sampling a held-out set that actually represents production traffic, stratifying by the failure modes you care about, annotation guidelines and inter-annotator agreement, synthetic data generation with diversity and label-noise gates, contamination and leakage checks between train and eval, dataset versioning and provenance, golden-set maintenance as the product changes, and knowing when a synthetic batch should be thrown away rather than shipped.\u003c\/p\u003e\n  \u003cdiv style=\"background: #EEECFD; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #5B4BE8; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eRepresentative held-out sampling and failure-mode stratification\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eAnnotation guidelines and inter-annotator agreement\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eSynthetic generation with diversity and label-noise gates\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eContamination checks, versioning and golden-set upkeep\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 thibaut-eval-dataset-synthetic-data-engineer.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #5B4BE8; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#5B4BE8; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package, open Claude, paste SKILL.md into your Project Instructions or system prompt, describe your requirement, and Thibaut builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58371234726152,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/thibaut-eval-dataset-synthetic-data-engineer-book.jpg?v=1787150440"},{"product_id":"veska-structured-output-constrained-decoding-engineer","title":"Veska - LLM Structured Output Engineer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Veska into Claude and get an engineer who makes model output parse every single time, without pretending a retry loop is a design.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eVeska owns getting reliable structured output out of a language model: JSON Schema and grammar design that the model can satisfy, constrained decoding and grammar-guided generation, tool-call and function-response schema shaping, validation and repair layers, the accuracy cost of huge enums and deeply nested schemas, streaming partial structures safely, schema versioning against downstream consumers, and knowing when a schema is fighting the model rather than guiding it.\u003c\/p\u003e\n  \u003cdiv style=\"background: #EEECFD; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #5B4BE8; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eJSON Schema and grammar design the model can satisfy\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eConstrained and grammar-guided decoding\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eValidation, repair layers and safe streaming partials\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eWhere large enums and deep nesting destroy accuracy\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 veska-structured-output-constrained-decoding-engineer.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #5B4BE8; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#5B4BE8; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package, open Claude, paste SKILL.md into your Project Instructions or system prompt, describe your requirement, and Veska builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58371239248136,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/veska-structured-output-constrained-decoding-book.jpg?v=1787150439"},{"product_id":"solvej-llm-observability-tracing-engineer","title":"Solvej - LLM Observability Engineer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Solvej into Claude and get an observability engineer who can tell you exactly which span in a 40-step agent run went wrong, and why.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eSolvej instruments LLM and agent systems so production failures are diagnosable: OpenTelemetry span design for multi-step agent runs, trace and session correlation across tools, retries and sub-agents, capturing prompt and completion payloads without leaking secrets, online quality signals and user-feedback capture, alerting on quality regressions rather than only errors, sampling strategy that keeps cost sane at volume, and replaying a failed production run against a candidate fix.\u003c\/p\u003e\n  \u003cdiv style=\"background: #EEECFD; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #5B4BE8; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eOpenTelemetry span design for multi-step agent runs\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eTrace correlation across tools, retries and sub-agents\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eQuality-regression alerting, not just error alerting\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eSampling that stays affordable, plus failed-run replay\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 solvej-llm-observability-tracing-engineer.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #5B4BE8; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#5B4BE8; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package, open Claude, paste SKILL.md into your Project Instructions or system prompt, describe your requirement, and Solvej builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58371243770120,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/solvej-llm-observability-tracing-engineer-book.jpg?v=1787150440"},{"product_id":"isaure-computer-use-browser-agent-engineer","title":"Isaure - Browser Automation Engineer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Isaure into Claude and get a computer-use engineer who will start by telling you which of your target systems should not have an agent driving them.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eIsaure builds agents that operate real interfaces: browser and desktop automation with vision-and-DOM hybrid grounding, selector strategy that survives UI changes, action confirmation before consequential clicks, session and auth handling without storing credentials in prompts, recovery from unexpected modals and layout shifts, rate limiting and anti-abuse compliance, sandboxing and blast-radius control, and an honest assessment of when an API exists and the agent should use it instead.\u003c\/p\u003e\n  \u003cdiv style=\"background: #EEECFD; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #5B4BE8; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eVision plus DOM hybrid grounding and durable selectors\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eConfirmation gates before consequential actions\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eSession\/auth handling without credentials in prompts\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eSandboxing, rate limits and recovery from UI surprises\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 isaure-computer-use-browser-agent-engineer.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #5B4BE8; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#5B4BE8; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package, open Claude, paste SKILL.md into your Project Instructions or system prompt, describe your requirement, and Isaure builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58371247833352,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/isaure-computer-use-browser-agent-engineer-book.jpg?v=1787150441"},{"product_id":"anouska-conversational-ai-experience-designer","title":"Anouska - Chatbot Designer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Anouska into Claude and get a conversation designer who designs the failure paths first, because that is where users actually decide whether to trust the thing.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eAnouska designs the conversation itself: turn and flow design, persona and tone specification that survives contact with real users, error and misunderstanding recovery, graceful degradation and the moment to hand off to a human, confirmation patterns before consequential actions, onboarding and capability disclosure so users learn what the assistant can and cannot do, multi-turn context repair, and writing the actual assistant copy rather than leaving it to whoever ships last.\u003c\/p\u003e\n  \u003cdiv style=\"background: #EEECFD; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #5B4BE8; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eTurn and flow design with failure paths designed first\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003ePersona and tone specification, with real copy\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eRecovery, context repair and human handoff moments\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eCapability disclosure and confirmation before consequential acts\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 anouska-conversational-ai-experience-designer.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #5B4BE8; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#5B4BE8; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package, open Claude, paste SKILL.md into your Project Instructions or system prompt, describe your requirement, and Anouska builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58371253371144,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/anouska-conversational-ai-experience-designer-book.jpg?v=1787150441"},{"product_id":"orsolya-ai-governance-regulatory-compliance-specialist","title":"Orsolya - AI Governance Specialist AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Orsolya into Claude and get an AI governance specialist who will not let you argue your way out of a high-risk classification.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eOrsolya owns the regulatory and documentation layer around AI systems: EU AI Act risk classification and the obligations that attach at each tier, NIST AI RMF, ISO\/IEC 42001 management systems, model and system cards, an AI inventory with use-case registration, conformity assessment and technical documentation packs, transparency and disclosure duties, incident reporting obligations, third-party model vendor due diligence, and an internal AI policy that survives an actual audit rather than a slide review.\u003c\/p\u003e\n  \u003cdiv style=\"background: #EEECFD; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #5B4BE8; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eEU AI Act risk tiers and the obligations at each\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eNIST AI RMF and ISO\/IEC 42001 alignment\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eModel cards, system cards and technical documentation packs\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eAI inventory, vendor due diligence and incident reporting\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 orsolya-ai-governance-regulatory-compliance-specialist.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #5B4BE8; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#5B4BE8; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package, open Claude, paste SKILL.md into your Project Instructions or system prompt, describe your requirement, and Orsolya builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58371257467144,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/orsolya-ai-governance-regulatory-compliance-book.jpg?v=1787150441"},{"product_id":"ondrej-ai-data-privacy-pii-protection-engineer","title":"Ondrej - Data Privacy Engineer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Ondrej into Claude and get a privacy engineer who traces where personal data actually goes in your LLM pipeline, including the places you forgot it lands.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eOndrej does privacy engineering across LLM pipelines: PII detection and redaction in prompts, completions, traces and logs; data residency and cross-border transfer when a model API sits in another jurisdiction; retention and deletion including vendor-side training opt-out and zero-retention terms; handling erasure requests when data may sit inside embeddings and fine-tuned weights; memorization and membership-inference risk; pseudonymization before a payload reaches a third party; and consent and purpose limitation for using customer data in training.\u003c\/p\u003e\n  \u003cdiv style=\"background: #EEECFD; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #5B4BE8; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003ePII detection and redaction in prompts, traces and logs\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eData residency and cross-border transfer for model APIs\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eErasure when data sits in embeddings and fine-tunes\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eRetention, zero-retention terms and training-consent limits\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 ondrej-ai-data-privacy-pii-protection-engineer.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #5B4BE8; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#5B4BE8; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package, open Claude, paste SKILL.md into your Project Instructions or system prompt, describe your requirement, and Ondrej builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58371261104392,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/ondrej-ai-data-privacy-pii-protection-book.jpg?v=1787150441"},{"product_id":"baldassare-ai-platform-agent-program-director","title":"Baldassare - AI Program Director AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Baldassare into Claude and get the director who owns the whole AI platform: what gets built, what gets killed, who owns each piece, and what it costs.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eBaldassare runs the AI platform and agent program at the coordination layer: portfolio and roadmap across agent initiatives, model and vendor strategy with exit paths, platform standards every team builds against, shared infrastructure decisions versus per-team autonomy, budget and cost accountability across the model spend, risk escalation when an unowned model sits inside a regulated control, capability and hiring plans, and the operating cadence that keeps twelve specialists pointed at the same architecture. He routes every hands-on task to a named specialist rather than doing it himself.\u003c\/p\u003e\n  \u003cdiv style=\"background: #EEECFD; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #5B4BE8; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eAgent portfolio and roadmap, including what to kill\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eModel and vendor strategy with real exit paths\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(91,75,232,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003ePlatform standards, shared infrastructure and cost accountability\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#5B4BE8; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eRisk escalation and routing to named specialists\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 baldassare-ai-platform-agent-program-director.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #5B4BE8; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#5B4BE8; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package, open Claude, paste SKILL.md into your Project Instructions or system prompt, describe your requirement, and Baldassare builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58371264151816,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/baldassare-ai-platform-agent-program-director-book.jpg?v=1787150441"},{"product_id":"jaroslav-coding-agent-engineer","title":"Jaroslav - Coding Agent Engineer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Jaroslav into Claude and get a coding agent engineer who measures cost per resolved issue, because a benchmark score on a public repo tells you nothing about your codebase.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eJaroslav builds agents that write and ship real code: repository context strategy across retrieval, file-tree summarisation and the limits of stuffing a monorepo into a window; sandboxed execution because an agent needs a real shell and a real test run; test-driven agent loops where the suite is the reward signal; patch and diff generation versus whole-file rewrite; multi-file coordinated edits; build and dependency resolution inside the sandbox; agent-authored pull requests and the review contract with humans; CI integration and blast-radius limits on what an agent may merge; why SWE-bench scores do not transfer to a private codebase; and the failure taxonomy for an agent that loops or fakes a fix.\u003c\/p\u003e\n  \u003cdiv style=\"background: #EBEDFA; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #2F46DA; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eRepo context strategy and the real limits of a big window\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eSandboxed execution with a real shell and a real test run\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003ePatch generation, multi-file edits and agent-authored PRs\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eCost per resolved issue, blast-radius limits, loop and fake-fix detection\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 jaroslav-coding-agent-engineer.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #2F46DA; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#2F46DA; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Jaroslav builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58385005117704,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/jaroslav-coding-agent-engineer-book.jpg?v=1787150497"},{"product_id":"ilinca-multimodal-agent-engineer","title":"Ilinca - Multimodal Agent Engineer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Ilinca into Claude and get a multimodal engineer who builds an eval set that tests visual reasoning, not caption matching, and knows where chart reading silently breaks.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eIlinca builds agents that see as well as read: vision-language model selection and their genuine failure modes; image preprocessing, resolution and tiling traded against token cost; chart, diagram and table understanding and exactly where it fails silently; screenshot and UI understanding for visual grounding; bounding boxes and the limits of spatial reasoning; video understanding through frame sampling strategy; combining OCR with a vision model rather than picking one; multimodal retrieval and image embeddings; evaluation sets that test reasoning rather than captioning; hallucination patterns specific to images; accessibility uses such as alt text; and the cost arithmetic when every image is thousands of tokens.\u003c\/p\u003e\n  \u003cdiv style=\"background: #EBEDFA; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #2F46DA; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eVision-language model selection and real failure modes\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eResolution, tiling and token cost arithmetic per image\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eChart, table, screenshot and video understanding limits\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eMultimodal retrieval, image hallucination patterns, honest evals\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 ilinca-multimodal-agent-engineer.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #2F46DA; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#2F46DA; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Ilinca builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58385006428424,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/ilinca-multimodal-agent-engineer-book.jpg?v=1787150497"},{"product_id":"bertil-model-distillation-on-device","title":"Bertil - Edge AI Engineer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Bertil into Claude and get a distillation engineer who measures the quality cost of every quantization step instead of assuming INT4 is free.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eBertil makes a small model good enough and gets it onto the device: knowledge distillation from a large teacher across response, feature and rationale distillation; task-specific small language models; quantization across INT8, INT4, GPTQ, AWQ and GGUF with the quality cost measured rather than assumed; pruning and sparsity; LoRA and adapter merging; on-device runtimes including llama.cpp, MLX, ONNX Runtime, Core ML and TFLite; memory, thermal and battery budgets on real hardware; latency on mobile and edge silicon; the hybrid pattern where a small model handles the common path and escalates the rest; offline capability and update distribution; and honest evaluation against the teacher on the tasks that matter.\u003c\/p\u003e\n  \u003cdiv style=\"background: #EBEDFA; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #2F46DA; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eResponse, feature and rationale distillation from a teacher\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eINT8\/INT4, GPTQ, AWQ and GGUF with measured quality cost\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003ellama.cpp, MLX, Core ML, ONNX and TFLite on real hardware\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eMemory, thermal and battery budgets; hybrid escalation patterns\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 bertil-model-distillation-on-device.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #2F46DA; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#2F46DA; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Bertil builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58385010196744,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/bertil-model-distillation-on-device-book.jpg?v=1787150499"},{"product_id":"piroska-document-ai-idp-engineer","title":"Piroska - Document AI Engineer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Piroska into Claude and get a document AI engineer who optimizes straight-through-processing rate, because field accuracy alone can hide a queue nobody can staff.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003ePiroska turns documents into reliable structured data at volume: document classification and splitting of multi-document scans; OCR engine selection and when a vision-language model beats classic OCR; layout analysis, reading order and table extraction from documents never designed to be parsed; key-value extraction against a schema with validation rules; handwriting and low-quality scans; confidence scoring and the human review threshold; straight-through-processing rate as the metric that decides the business case; field-level accuracy measured against a labelled set; exception queues and correction feedback; document versioning and audit trail for regulated processes; throughput and cost per page; and integration into the system that consumes the data.\u003c\/p\u003e\n  \u003cdiv style=\"background: #EBEDFA; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #2F46DA; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eClassification, splitting, layout analysis and table extraction\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eOCR versus vision-language model, chosen on measured accuracy\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eSchema-based extraction with validation and confidence scoring\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eStraight-through-processing rate, exception queues, cost per page\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 piroska-document-ai-idp-engineer.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #2F46DA; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#2F46DA; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Piroska builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58385011704072,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/piroska-document-ai-idp-engineer-book.jpg?v=1787150498"},{"product_id":"quirin-llm-gateway-routing-engineer","title":"Quirin - LLM Gateway Engineer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Quirin into Claude and get a gateway engineer who pins model versions so a provider update cannot silently change your product overnight.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eQuirin owns the control plane in front of every model call: gateway architecture and why calls should never go direct to a provider; model routing by task, quality tier and cost with rules derived from measurement rather than guesswork; cascading and fallback chains across providers and regions; semantic and exact-match caching with invalidation; rate limit handling, queuing and backpressure; per-team and per-feature quotas and spend controls; API key management and credential isolation; request and response logging with PII redaction at the gateway; streaming pass-through and its complications; prompt and model version pinning; provider outage response and where a multi-provider abstraction leaks; and measuring what routing actually saved rather than what it was projected to save.\u003c\/p\u003e\n  \u003cdiv style=\"background: #EBEDFA; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #2F46DA; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eGateway architecture, credential isolation and PII redaction\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eRouting by task and quality tier with measured rules\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eFallback chains, caching with invalidation, backpressure\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eQuotas, spend controls and model version pinning\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 quirin-llm-gateway-routing-engineer.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #2F46DA; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#2F46DA; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Quirin builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58385013178632,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/quirin-llm-gateway-routing-engineer-book.jpg?v=1787150499"},{"product_id":"csilla-rlhf-human-in-the-loop-data-ops","title":"Csilla - AI Data Annotation Manager AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Csilla into Claude and get a human data operations lead who fixes the guideline before blaming the annotators, because low agreement is almost always an ambiguous rubric.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eCsilla runs the human data layer behind aligned models: annotation program design and what makes a guideline usable; annotator recruitment, qualification and calibration; inter-annotator agreement and what to do when it is low; preference data collection for RLHF and DPO; pairwise comparison design and position bias; rubric-based scoring; red-team data collection; active learning and sampling so annotators see the examples that matter; quality control through gold sets, audits and reviewer-of-reviewers; annotator pay, workload and wellbeing especially on distressing content; vendor management for outsourced labelling; cost per label against value; and the data provenance and consent record a regulator may ask for.\u003c\/p\u003e\n  \u003cdiv style=\"background: #EBEDFA; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #2F46DA; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eGuideline design, annotator qualification and calibration\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eInter-annotator agreement diagnosis and repair\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003ePreference and pairwise collection for RLHF and DPO, bias control\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eGold sets, audits, annotator wellbeing, provenance and consent\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 csilla-rlhf-human-in-the-loop-data-ops.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #2F46DA; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#2F46DA; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Csilla builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58385015701768,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/csilla-rlhf-human-in-the-loop-data-ops-book.jpg?v=1787150498"},{"product_id":"vanja-multilingual-localization-engineer","title":"Vanja - Localization Engineer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Vanja into Claude and get a localization engineer who measures quality per language, because English performance never transfers the way the roadmap assumes.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eVanja makes an LLM product work outside English: measuring per-language quality rather than assuming it transfers; tokenizer efficiency and the cost penalty non-Latin scripts pay; language-specific evaluation sets and native-speaker review loops; machine translation versus native generation and when each is right; translation memory and glossary enforcement inside prompts; locale-aware formatting for dates, numbers, currency, addresses and names; right-to-left and bidirectional text; script and encoding pitfalls; retrieval over multilingual corpora including cross-lingual embeddings; culturally appropriate tone and register; regional compliance differences in what a model may say; latency and model availability by region; and a rollout order argued from real user distribution rather than executive preference.\u003c\/p\u003e\n  \u003cdiv style=\"background: #EBEDFA; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #2F46DA; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003ePer-language evaluation with native-speaker review loops\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eTokenizer efficiency and the cost penalty by script\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eGlossary and termbase enforcement, locale formatting, RTL\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eCross-lingual retrieval, regional compliance, rollout ordering\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 vanja-multilingual-localization-engineer.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #2F46DA; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#2F46DA; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Vanja builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58385018093832,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/vanja-multilingual-localization-engineer-book.jpg?v=1787150498"},{"product_id":"odalric-ai-research-engineer","title":"Odalric - AI Research Engineer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Odalric into Claude and get a research engineer who runs multiple seeds and will tell you the paper's result did not reproduce at your scale.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eOdalric turns papers into production systems: reading a paper critically and identifying what will not reproduce; reimplementation with an ablation plan; experiment design and tracking; statistical significance and why single-seed results mislead; baselines that are genuinely strong rather than strawmen; compute budgeting for research; distributed training basics; hyperparameter search strategy; reporting negative results honestly; benchmark contamination and leakage; the gap between benchmark score and product value; research-to-production handoff criteria; publishing and open-sourcing decisions; and keeping a research agenda tied to a product problem rather than to novelty.\u003c\/p\u003e\n  \u003cdiv style=\"background: #EBEDFA; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #2F46DA; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eCritical paper reading and what will not reproduce at your scale\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eAblations, multiple seeds and honest significance testing\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eStrong baselines, compute budgeting, hyperparameter strategy\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eBenchmark contamination and the score-to-product-value gap\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 odalric-ai-research-engineer.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #2F46DA; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#2F46DA; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Odalric builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58385020125448,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/odalric-ai-research-engineer-book.jpg?v=1787150499"},{"product_id":"fabrizio-ai-forward-deployed-engineer","title":"Fabrizio - Forward Deployed Engineer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Fabrizio into Claude and get a forward-deployed engineer who builds the evaluation from the customer's own data and reports the number that kills the sales deck.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eFabrizio is the engineer who sits with the customer and makes the AI product work in their environment: discovery of the real workflow rather than the demo workflow; data access and integration inside a customer network; security review and deployment models across SaaS, VPC and on-premises; customer-specific evaluation built from their own data; prompt and pipeline tuning against their edge cases; pilot design with success criteria the customer signed; change management with the people whose job the system touches; instrumenting the deployment so value is measurable; escalation back to core engineering with reproducible cases; deciding what to productize versus keep bespoke; and telling a customer honestly when the product is not right for their use case.\u003c\/p\u003e\n  \u003cdiv style=\"background: #EBEDFA; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #2F46DA; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eReal-workflow discovery and customer-network integration\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eSaaS, VPC and on-premises deployment and security review\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eEvaluation built from the customer's own data and edge cases\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eSigned pilot criteria, change management, productize-vs-bespoke\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 fabrizio-ai-forward-deployed-engineer.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #2F46DA; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#2F46DA; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Fabrizio builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58385022353672,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/fabrizio-ai-forward-deployed-engineer-book.jpg?v=1787150500"},{"product_id":"genoveva-ai-adoption-enablement-lead","title":"Genoveva - AI Adoption Manager AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Genoveva into Claude and get an adoption lead who measures whether work actually changed, not how many licences were assigned.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eGenoveva gets an organization to actually use the AI it bought: measuring genuine adoption rather than licence count; identifying high-value use cases per function and killing the low-value ones; role-based training and enablement; internal champion networks; prompt and pattern libraries maintained as a product; an acceptable-use policy people can follow; the shadow-AI problem and how to bring it into the light; measuring productivity honestly including where gains did not materialize; addressing job-security fear directly rather than pretending it does not exist; feedback loops from users back to the platform team; licence allocation and reclaim; executive reporting on adoption and value; and the difference between a rollout that finished and one that changed how work is done.\u003c\/p\u003e\n  \u003cdiv style=\"background: #EBEDFA; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #2F46DA; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eAdoption measured by changed work, not licences assigned\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eUse case discovery per function, and killing the weak ones\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eRole-based enablement, champions and a maintained prompt library\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eShadow AI, acceptable-use policy, licence reclaim, honest value reporting\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 genoveva-ai-adoption-enablement-lead.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #2F46DA; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#2F46DA; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Genoveva builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58385023795464,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/genoveva-ai-adoption-enablement-lead-book.jpg?v=1787150500"},{"product_id":"hektor-ai-trust-safety-engineer","title":"Hektor - Trust \u0026 Safety Specialist AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Hektor into Claude and get a trust and safety engineer who measures over-enforcement as carefully as under-enforcement, because a blunt countermeasure destroys legitimate users.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eHektor runs platform-scale abuse and harmful-content defence for AI products: policy written so a classifier and a human reviewer can both apply it; classifier development and threshold selection against precision and recall on real traffic; human review workflows, queue design and reviewer wellbeing; appeals and reversal processes; measuring both over-enforcement and under-enforcement; adversarial and coordinated abuse patterns; age assurance and minor safety; procedural escalation paths for illegal content; regional legal differences in what must be removed; transparency reporting; incident response for a safety failure; and red-team findings fed back into policy. This is defensive platform integrity work only.\u003c\/p\u003e\n  \u003cdiv style=\"background: #EBEDFA; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #2F46DA; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003ePolicy written so a classifier and a reviewer both apply it\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eThreshold selection on real traffic precision and recall\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eOver-enforcement measured as carefully as under-enforcement\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eReview queues, reviewer wellbeing, appeals and transparency reporting\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 hektor-ai-trust-safety-engineer.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #2F46DA; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#2F46DA; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Hektor builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58385025401096,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/hektor-ai-trust-safety-engineer-book.jpg?v=1787150499"},{"product_id":"anselma-chief-ai-officer","title":"Anselma - Chief AI Officer AI Skill","description":"\u003cdiv style=\"font-family: 'DM Sans', sans-serif; color: #1A1A18; max-width: 680px;\"\u003e\n  \u003cp style=\"font-size: 16px; font-weight: 600; line-height: 1.5; margin: 0 0 8px 0;\"\u003eDrop Anselma into Claude and get an AI executive who restates the claimed benefit honestly, kills the initiatives that will not pay, and routes every workstream to a named specialist.\u003c\/p\u003e\n  \u003cp style=\"font-size: 13px; color: #555550; line-height: 1.7; margin: 0 0 28px 0;\"\u003eAnselma is the coordination layer over an entire AI portfolio. She owns enterprise AI strategy tied to business outcomes, the portfolio and how to kill an initiative, build versus buy versus fine-tune across vendors, model and vendor strategy including concentration risk, AI budget and unit economics at portfolio level, the organization's risk appetite and where AI is not allowed at all, board and regulator communication, the operating model across a central platform and embedded teams, talent strategy, data readiness as the usual real blocker, measuring realized value rather than pilots launched, and the boundary between her role and the CTO's, the CIO's and the Chief Data Officer's. She builds nothing herself: every workstream goes to a named specialist and comes back through a review.\u003c\/p\u003e\n  \u003cdiv style=\"background: #EBEDFA; border-radius: 12px; padding: 24px 28px; margin-bottom: 24px;\"\u003e\n    \u003cp style=\"font-size: 10px; font-weight: 600; color: #2F46DA; letter-spacing: 0.08em; text-transform: uppercase; margin: 0 0 16px 0;\"\u003eWhat you get\u003c\/p\u003e\n    \u003cul style=\"margin: 0; padding: 0; list-style: none;\"\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003ePortfolio strategy and the discipline to kill initiatives\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eBuild vs buy vs fine-tune, vendor and concentration risk\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0; border-bottom: 1px solid rgba(47,70,218,0.14); display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eRisk appetite, board and regulator communication\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli style=\"font-size: 13px; padding: 7px 0;  display: flex; gap: 10px;\"\u003e\n\u003cspan style=\"color:#2F46DA; font-weight:600;\"\u003e→\u003c\/span\u003e\u003cspan\u003eRealized value measurement, data readiness, operating model\u003c\/span\u003e\n\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"display:flex; align-items:center; gap:20px; background:#FFFFFF; border:1px solid #E8E6E0; border-radius:8px; padding:14px 20px; margin-bottom:24px;\"\u003e\n    \u003cspan style=\"font-size:11px; color:#888780; font-family:monospace;\"\u003e📄 anselma-chief-ai-officer.skill\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eUnder 2 min install\u003c\/span\u003e\n    \u003cspan style=\"font-size:11px; color:#888780;\"\u003eWorks with Claude, ChatGPT \u0026amp; any AI chat\u003c\/span\u003e\n  \u003c\/div\u003e\n  \u003cdiv style=\"border-left:3px solid #2F46DA; padding-left:16px;\"\u003e\n    \u003cp style=\"font-size:10px; font-weight:600; color:#2F46DA; letter-spacing:0.08em; text-transform:uppercase; margin:0 0 6px 0;\"\u003eHow to install\u003c\/p\u003e\n    \u003cp style=\"font-size:12px; color:#555550; line-height:1.7; margin:0;\"\u003eDownload the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Anselma builds the answer. Includes a full worked example so you see exactly what you get.\u003c\/p\u003e\n  \u003c\/div\u003e\n\u003c\/div\u003e","brand":"KissMySkills","offers":[{"title":"Default Title","offer_id":58385026842888,"sku":null,"price":29.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/files\/anselma-chief-ai-officer-book.jpg?v=1787150499"}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1036\/1444\/7880\/collections\/ai-agents-llm-ops-skills.jpg?v=1787734700","url":"https:\/\/kissmyskills.com\/collections\/ai-agents-llm-ops-skills.oembed?page=2","provider":"KissMySkills","version":"1.0","type":"link"}