← ClaudeAtlas

diagnosing-bugslisted

Diagnose hard, flaky, intermittent, environment-specific, or performance regressions, especially when a prior fix failed. Use a tight reproduction and falsifiable hypotheses; do not invoke for a straightforward bug with an obvious local cause and cheap test.
3metaJun/mstack · ★ 0 · AI & Automation · score 75
Install: claude install-skill 3metaJun/mstack
# Diagnosing bugs A discipline for hard bugs. Skip phases only when explicitly justified. For a diagnosis-only request, report the verified cause and evidence. Enter the fix phases when the user has authorized implementation. When exploring the codebase, read `CONTEXT.md` (if it exists) to get a clear mental model of the relevant modules, and check ADRs in the area you're touching. ## Redact This skill has you show commands, outputs and captured artifacts. **Redact every secret first**: write `<REDACTED>` in its place. Build loops against env vars, so the credential stays in the environment rather than in what you show. Captured artifacts carry auth headers: quote only the lines that carry the signal. If the redacted output is not enough to diagnose the bug, say so and ask the user. ## Phase 1: Build a feedback loop **This is the skill.** Everything else is mechanical. If you have a **tight** pass/fail signal for the bug (one that goes red on _this_ bug), you will find the cause; bisection, hypothesis-testing, and instrumentation all just consume it. If you don't 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, 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 snapsh