MCP servers expose tools to an LLM client (Claude Desktop, Claude Code, etc.). The LLM is the caller, so the failure modes differ from a normal library: errors must be machine-readable, every input is untrusted, and a green test suite often proves nothing about whether the tools actually work. This

Generate GitHub Actions CI/CD pipeline configurations for automated building and testing of library and package projects. Use when creating or updating CI workflows for npm packages, Python packages, Go modules, Rust crates, or other library projects that need automated build and test pipelines. Includes templates for common package ecosystems with best practices for dependency caching, matrix testing, and artifact publishing.

Edit video and audio with local FFmpeg: cut, join, reframe, speed, captions, overlays, silence removal, sync, loudness, HDR to SDR, platform exports and checks. Use whenever the user mentions a video or audio file (mp4, mov, wav, m4a), footage, captions, a reel or short, YouTube/TikTok delivery, LUFS or ffmpeg, even without saying "edit". Needs FFmpeg 6.1+ and Python 3.10+; stdlib only, no cloud.

Some operations have no undo: an orphan-branch rewrite, a recursive delete of every tracked file, an overwrite of a stored artifact, a `DROP`/`purge` path. The implementation is usually short and usually correct *for the setup its author had in mind*. The bug is never the deletion itself — it is t

A local check is only useful if it runs the same thing the runner runs. Most "green locally, red in CI" failures are not bugs in the code — they are a difference between two commands: different paths, different test markers, different env, a different linter version, or a different interpreter.

A report from outside names one tool and one input. It is almost never the only place the defect lives, and the reporter found it because nobody inside thought to look. #437 named `insert.py` and an odd-sized JPEG; the same odd frame also broke `caption.py` and crashed `stabilize.py` on a video, whi

Most integration bugs are not coding errors. They are a belief about someone else's system — a status code, a parameter name, a response shape, a build backend's scoping rule — that was never checked and turned out to be wrong. The code is written correctly against a contract that does not exist

A report is a claim, and it is read by people who will not re-derive it. The cost of an overstated one is not embarrassment — it is a maintainer spending an afternoon on a premise that does not hold, or a "fix" landing for a failure mode that never occurred. The techniques for *finding* a defect l