round3ai/three-dev
Integrate three.dev into a codebase and work with recorded LLM traffic: route calls through the proxy, define use cases and quality metrics, investigate failure modes, and test prompt or model changes with offline experiments, using the three.dev MCP server.
Investigates production quality problems in an LLM feature that three.dev already records. Takes the worst failure mode, classifies the requests with its issues, reads the conversations to find the root cause, and proposes a prompt, model, tool or code fix. Use when the user asks why an LLM feature is failing, how to fix or improve its worst failure mode, what its top failure modes or quality problems are, whether a problem is growing or started after a deploy, or wants to see bad conversations or count or segment requests. Also when the user arrives with a three.dev conversation id, to continue an investigation started in the three.dev chat. Needs the three.dev MCP server. Not for setting up three.dev or routing calls through the proxy; that is the three-dev-setup skill.
Adds three.dev to a codebase so its LLM calls are recorded. Connects the app to the user's three.dev organization with one approval in the browser, finds every LLM call site, groups the calls into use cases, and routes them through the three.dev proxy (gate.three.dev) with the app's own provider key plus use case, session, and environment headers. Use when the user mentions three.dev, gate.three.dev, or X-Three headers, asks to record or monitor their LLM calls, or wants to set up, connect, or extend a three.dev integration. Covers OpenAI, Anthropic, Gemini, Azure OpenAI, OpenRouter, Concentrate, Portkey, Bedrock, LiteLLM, Vercel AI SDK, and LangChain and LangGraph clients. Not for investigating failure modes or reading recorded conversations; that is the three-dev-failure-modes skill.