Quirin — LLM Gateway & Model Routing Engineer AI Skill
Instant download · 30-day money-back guarantee. Pay once, keep forever — no subscription. Refund policy
Build the LLM gateway: route by measured quality and cost, cache and fall back safely, and pin versions so nothing shifts underneath you.
- Gateway architecture, credential isolation and PII redaction
- Routing by task and quality tier with measured rules
- Fallback chains, caching with invalidation, backpressure
- Quotas, spend controls and model version pinning
Platform teams whose LLM spend is unattributable and whose product changed behaviour after a provider update.An LLM platform engineer commands $140+/hr, this is one file, yours forever.
Drop Quirin into Claude and get a gateway engineer who pins model versions so a provider update cannot silently change your product overnight.
Quirin 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.
What you get
- →Gateway architecture, credential isolation and PII redaction
- →Routing by task and quality tier with measured rules
- →Fallback chains, caching with invalidation, backpressure
- →Quotas, spend controls and model version pinning
How to install
Download 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.
# Quirin - LLM Gateway & Model Routing Engineer You are Quirin, an LLM gateway and routing engineer. Nothing calls a provider directly, and no model version floats. ## How you work 1. Put every call through the gateway; isolate credentials there 2. Derive routing rules from measured quality and cost per task 3. Build fallback, caching and backpressure with stated failure modes 4. Pin prompt and model versions; attribute every dollar to a team Never route on projected savings alone, and never let a provider version change reach production without a pinned rollback.
Excerpt from the actual file you'll download.
Four steps. Any AI chat.
- 01Download the file
After checkout, the download link lands in your inbox. Save the file anywhere on your device.
- 02Open your AI chat
Claude, ChatGPT, Gemini, Grok, or Copilot — whichever one you already use.
- 03Paste the file contents
Drop it into the system prompt, Project instructions, or custom instructions field.
- 04Start working
Your AI is now configured as a specialist. Ask it anything inside its domain.
No technical knowledge required. No subscription. Pay once, keep forever.
Works with every major AI chat.
Drop the file into your AI's system prompt, Project instructions, or custom instructions. No setup. No code. No vendor lock-in.
- Claude
- ChatGPT
- Gemini
- Grok
- Copilot
Works with any AI chat that accepts a system prompt or custom instructions.
Ready to specialise your AI?
One drop-in file. Pay once, keep forever — works with Claude & ChatGPT.