diagnosing-bugs — Skills — getagentictools

What it does

Can I make it faster? (Cache setup, skip unrelated init, narrow the test scope.)

Can I make the signal sharper? (Assert on the specific symptom, not "didn't crash".)

Can I make it more deterministic? (Pin time, seed RNG, isolate filesystem, freeze network.)

[ ] Deterministic — same verdict every run (flaky bugs: a pinned, high reproduction rate, per above).

[ ] Fast — seconds, not minutes.

[ ] Agent-runnable — you can run it unattended; a human in the loop only via scripts/hitl-loop.template.sh.

[ ] The loop produces the failure mode the user described — not a different failure that happens to be nearby. Wrong bug = wrong fix.

Source

Repository: https://github.com/mattpocock/skills

diagnosing-bugs FAQ

What does the diagnosing-bugs skill do?

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow. Can I make it faster? (Cache setup, skip unrelated init, narrow the test scope.) Can I make the signal sharper? (Assert on the specific symptom, not "didn't crash".)

How do I install diagnosing-bugs?

Run: npx -y skills add https://github.com/mattpocock/skills --skill diagnosing-bugs --agent claude-code — the source lives at github.com/mattpocock/skills.

Maintain diagnosing-bugs?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

[![diagnosing-bugs on getagentictools](https://getagentictools.com/badge/skills/mattpocock-skills-diagnosing-bugs.svg)](https://getagentictools.com/skills/mattpocock-skills-diagnosing-bugs?ref=badge)

npx agentictools info skills/mattpocock-skills-diagnosing-bugs

The second line is the CLI lookup for this page — handy in READMEs and docs.