Testing & Debugging Skills

Investigate a specific Claude Code session by session ID — correlate the local transcript (~/.claude/projects/...jsonl) with the router's production logs to understand what the client rendered vs. what the upstream served. Use when given a session ID and asked "why did X render?" for a Claude Code conversation routed through the router.

Fetches feedback from a GitHub PR — review-thread comments, ad-hoc PR comments (including those posted as a review's body without a thread), and bot/advisory review submissions — and fixes all of them as they appear (comments before CI). Bot comment-length nits apply verbatim; comments requiring a genuine human decision are NOT auto-fixed and are escalated to the user with options grounded in existing patterns and best practices. After each fix batch, runs pre-commit validation and submits, then waits for CI only when no actionable feedback remains. Loops until all feedback is resolved AND all CI checks have completed. Use when asked to fix PR comments, address review feedback, address PR-level bot reviews (e.g. workweave-bot advisory nits), babysit a PR to merge-ready, or handle review comments.

Run the Weave router locally in docker compose and drive it with claude -p to reproduce and verify routing/translation behavior for a specific upstream model (e.g. GLM-5.1, DeepSeek, Qwen). Use when verifying a router fix end-to-end, reproducing a prod routing bug, confirming a model's streaming behavior (nudges, tool-call suppression, loop/no-progress breaks), or testing a /force-model route — without touching the user's global Claude Code config.