← ClaudeAtlas

diagnoselisted

Disciplined diagnosis and re-validation loop for hard bugs and performance regressions. Reproduce, minimise, hypothesise, instrument, fix, and regression-test. Use when the user says diagnose this / debug this, reports a bug, says something is broken/throwing/failing, or describes a performance regression. User-facing questions and findings must be in Portuguese (pt-BR). Part of the afonsoft/skills collection.
afonsoft/skills · ★ 2 · AI & Automation · score 78
Install: claude install-skill afonsoft/skills
# Diagnose A discipline for hard bugs and regressions. Skip phases only when explicitly justified. All questions and findings reported to the user must be in **Portuguese (pt-BR)**. When exploring the codebase, use the project's domain glossary from `.claude/CONTEXT.md` to get a clear mental model of the relevant modules, and check `docs/architecture/` for decisions in the area you are touching. **Re-validation loop**: after every hypothesis, fix, or change, re-run the reproduction and the regression checks before declaring the bug resolved. ## When to Use - User asks or mentions this skill in English (e.g., "use /diagnose", "run diagnose"). - O usuário pede ou menciona esta skill em português (ex.: "use /diagnose", "execute diagnose"). ## Phase 1 — Build a feedback loop **This is the skill.** Everything else is mechanical. If you have a fast, deterministic, agent-runnable pass/fail signal for the bug, you will find the cause — bisection, hypothesis-testing, and instrumentation all just consume that signal. If you do not have one, no amount of staring at code will save you. Spend disproportionate effort here. **Be aggressive. Be creative. Refuse to give up.** ### Ways to construct one — try them in roughly this order 1. **Failing test** at whatever seam reaches the bug — unit, integration, e2e. 2. **Curl / HTTP script** against a running dev server. 3. **CLI invocation** with a fixture input, diffing stdout against a known-good snapshot. 4. **Headless browser script