Liora - AI 紅隊工程師 AI Skill
$29.00
特價
$29.00
原價
$43.99
跳至產品資訊
Start All-Access
Liora - AI 紅隊工程師 AI Skill
$29.00
this skill
vs
$43.99
hiring a senior QA/AI engineer
Complete skill package instant downloadliora-agent-qa-red-team-engineer.skill
Choose how to get it
Start All-Access, from $8.25/mo$99 a year, or $19 a month. 14-day refund on the first charge.
// all-access
You do not download skills. Your AI fetches them.
The KissMySkills connector is a small server your AI chat talks to. Add it once to Claude, ChatGPT, Claude Code or Cursor. From then on, any of our 1,000+ skills is one sentence away.
- 01Add the connector. Settings, Connectors, paste one link. A minute.
- 02Sign in once. The email from your subscription. Nothing installs.
- 03Ask for a skill. "Load Liora." It arrives in the conversation and your AI answers as that specialist.
$99/yr $8.25 a month
$19/mo month to month
Every skill, prompt pack and agent, new releases included. Single files can still be bought and kept. Cancel any time from your account. Compare plans
Secure checkout by Shopify
⚡ 立即下載
∞ 永遠保留
✎ 由我們撰寫
Add it once. Your AI works like a specialist.
將其加入 Claude、ChatGPT 或 Gemini - 您的 AI 會在此領域中擔任專家。
立即下載 · 30 天退款保證。 一次付費，永久使用 - 無需訂閱。由我們撰寫並測試，絕非從 GitHub 抓取。 退款政策
Ask Liora something hard.
Agent passed 200 happy-path tests, then a user typo made it call the refund tool with a 10x amount. How do I test the unpredictable?
CLAUDE · AS LIORA, AI 紅隊工程師
Happy-path suites test the demo, not the agent - you need three layers: property assertions on every trajectory (refund amount <= order total, enforced in test and in the tool schema), perturbation testing - every eval case re-run with typos, truncation and odd encodings, which is exactly how your 10x case surfaces before prod - and a defensive red-team pass over the tool surface asking what's the worst each tool does with malformed arguments. That refund bug is also an argument-validation gap: bounds live in the runtime, never in the model's judgment. Send the tool schemas and I'll flag the unguarded blast radius.
Trademarks of their respective owners. KissMySkills is not affiliated with or endorsed by them.
你不需要閱讀。由你的 AI 代勞。
只需將技能檔案新增至 Claude、ChatGPT 或 Gemini 一次。從那之後，它就會以這個領域的專家身分運作，並從下一則訊息開始以 Liora 的身分回答。
購買一次，檔案便永久歸您所有。或者訂閱 All-Access，讓 KissMySkills 連接器在您提出要求時，將該檔案及其他所有技能載入您的聊天中。
// what's inside
這項技能包含什麼
- Behavioral tests: tool calls, schema, task completion, refusals
- Trajectory testing and flakiness handling (pass@k)
- Defensive red-team: injection/jailbreak resistance, PII-leak checks
- Regression testing and CI gates before release
Teams shipping agents who need repeatable QA and a defensive robustness pass before release.
A senior QA/AI engineer bills $120+/hr, the complete skill is yours forever.
// what's inside
What you're actually buying
將 Liora 放入 Claude，即可獲得一位資深 agent QA 工程師，透過行為測試套件與防禦性紅隊測試來測試並強化您自己的 agent。
Liora 為非確定性 agent 進行品質保證：行為測試套件（針對工具呼叫、輸出結構描述、任務完成與拒絕行為的斷言）、評估／測試資料集（正常路徑、邊界情況、穩健性）、軌跡測試（工具選擇、引數正確性、迴圈與終止、復原）、針對您自己的 agent 進行防禦性穩健性與紅隊測試（prompt 注入與越獄抵抗力、PII 洩漏檢查、偏離策略的拒絕）、跨 prompt 與模型變更的回歸測試、不穩定性處理（種子、pass@k）、基礎依據檢查，以及 CI 閘門。可使用 promptfoo、DeepEval、LangSmith 與 pytest 等工具，不受單一工具綁定。嚴格限於防禦用途：僅測試您自己的 agent，不提供攻擊工具。在發布前於 staging 的 CI 中設置閘門。
您將獲得的內容
- →行為測試：工具呼叫、結構描述、任務完成、拒絕行為
- →軌跡測試與不穩定性處理（pass@k）
- →防禦性紅隊測試：注入／越獄抵抗力、PII 洩漏檢查
- →發布前的回歸測試與 CI 閘門
📄 liora-agent-qa-red-team-engineer.skill
安裝時間不到 2 分鐘
適用於 Claude、ChatGPT 與任何 AI 聊天工具
如何安裝
下載 .skill 套件 → 開啟 Claude → 將 SKILL.md 貼到您的專案指示或 system prompt 中 → 描述您的需求 → 由 Liora 建立答案。包含完整的操作範例，讓您確切了解會得到什麼。
# Liora - Agent QA & Red-Team Engineer You are Liora, a senior Agent QA & Red-Team Engineer. You test and harden the team's own agent. Defensive only. ## How you work 1. Build a labeled test set (happy path, edge, robustness) 2. Assert on tool calls, schema, task completion and refusals 3. Run a defensive red-team pass on your own agent; handle flakiness (pass@k) 4. Gate CI on regressions before release Defensive only: your own agent, no attack tooling or targeting systems you do not own. Gate in staging before release.
您將下載的實際檔案範例。
// how to install
不到 2 分鐘
四個步驟。任何 AI 聊天。
- 01下載檔案
結帳後，下載連結會寄到您的收件匣。將檔案儲存至裝置上的任意位置。
- 02開啟你的 AI 聊天功能
Claude、ChatGPT、Gemini、Grok 或 Copilot - 無論你目前使用哪一個。
- 03貼上檔案內容
將其放入系統 prompt、專案指示或自訂指示欄位中。
- 04開始工作
您的 AI 現已設定為專業助手。您可以詢問它任何與其專業領域相關的問題。
不需要技術知識。不需訂閱。一次付費，永久使用。
// compatible with
支援所有主要的 AI 聊天服務。
將檔案放入您的 AI system prompt、專案指示或自訂指示中。無需設定。無需程式碼。不受供應商綁定。
// faq
關於此產品的問題
What does the Liora skill do?+
QA your agent: behavioral tests, trajectory checks, a defensive red-team pass and CI gates, with pass@k. Load it once into Claude Projects and you get a configured Agent QA & Red-Team Engineer without re-explaining context at the start of every session. Build and evaluate against a held-out test set in a development or staging environment, add guardrails, cost and rate limits, and human review, and roll out behind evals and monitoring before serving agents or LLM features in production.
How do I install this skill file?+
Download the .skill package (it contains SKILL.md), paste the contents into Claude Projects Instructions or your AI's system prompt, add your own context and start your first session. Works with Claude, ChatGPT, or any AI chat that accepts system prompts.
Which AI tools does this skill work with?+
Works with Claude (recommended), ChatGPT, Gemini, Perplexity and Copilot, and any AI chat that accepts system prompts. Claude Projects gives the best results.
What is included in this download?+
One .skill package delivered instantly after purchase: the full SKILL.md role configuration plus a worked-example file with a real scenario so you see the quality before you rely on it. No subscription, yours permanently.
How is this different from using Claude without the Liora skill?+
Without a skill file your AI starts every session as a general assistant. With Liora loaded it applies Agent QA & Red-Team Engineer methodology from the first message, with consistent quality every time. Build and evaluate against a held-out test set in a development or staging environment, add guardrails, cost and rate limits, and human review, and roll out behind evals and monitoring before serving agents or LLM features in production.
Do I have to read it myself?+
No. The file is written for your AI to read, not for you. Upload it or paste it in once and the AI takes on the role. After that you just ask it questions the way you normally would. You're welcome to open it and read it, but nothing here depends on you doing that.
Is this a physical book?+
No, it's digital. You download it the moment the order goes through and it's yours permanently. The cover is styled like a book because each edition is written and edited as one self-contained piece of work. The reading part is your AI's job, not yours.
準備好讓您的 AI 專精了嗎？
一個即插即用的檔案。一次付費，永久保留 - 適用於 Claude 和 ChatGPT。
