Quality

Document control system management for medical device QMS. Covers document numbering, version control, change management, and 21 CFR Part 11 compliance.

Traces reproduced software symptoms to their root cause in source code, identifying the specific file and line. Use after reproducing a bug to pinpoint the code responsible and propose a fix.

Implements a diagnosed bug fix in the EmDash CMS codebase, following project conventions, adding regression tests, running lint/typecheck, and staging the change for human review.

Reproduce an EmDash admin UI bug by booting a demo, driving the admin with agent-browser, and capturing screenshots and a replayable transcript.

Reproduce EmDash bugs in REST handlers, CLI, MCP, migrations, or build tooling. Creates a failing vitest test or repro script to isolate backend issues without a browser.

Reproduce a bug in the public-facing part of a web app by booting a demo, driving public routes with a browser agent, and capturing screenshots plus a written transcript.

Cross-references code, docs, and tests to decide if a diagnosed issue is an actual bug or deliberately intended behavior. Acts as a gating step to prevent unnecessary code changes.

Review a pull request for real bugs, regressions, and convention violations. The skill enumerates candidate issues across the diff, verifies each against the code, and returns structured line-anchored findings and a verdict.

An adversarial code review skill that assumes bugs exist and hunts for them. Use it to stress-test pull requests, audit code for correctness, and find every possible bug.

A systematic debugging approach that replicates bugs by writing external scripts interacting only with public interfaces. Ideal for isolating difficult issues without modifying internals.

Handle code review feedback with technical rigor: fetch, verify, implement, and test changes before pushing updates. Use when receiving PR comments to avoid performative agreement and ensure each suggestion is sound.

Systematically traces bugs backward through the call stack to identify the original trigger, using instrumentation and stack trace analysis to fix root causes rather than symptoms.