Debug
Diagnose difficult or recurring failures with an evidence-driven hypothesis loop. Use when the cause is unclear, normal troubleshooting failed, or retries would otherwise be speculative.From its SKILL.md
npx -y skills add kevinb361/agent-skills --skill debugAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.1 KB, 172 tokens by cl100k_base, as published. Nobody here has run it
Evidence-driven debugging
Do not change code until the failure is characterized.
- State the observed symptom precisely, including scope and timing.
- Reproduce it with the smallest safe command, or collect bounded logs and state if reproduction is unsafe.
- Separate facts from assumptions.
- Form a short ranked list of falsifiable hypotheses.
- Test one discriminating hypothesis at a time.
- Update the ranking from evidence; do not repeat a failed action unchanged.
- Fix the root cause with the smallest coherent change.
- Re-run the original reproduction and relevant regression checks.
Preserve useful diagnostics. Do not silence exceptions, weaken tests, add arbitrary retries, or widen timeouts unless evidence shows that behavior is correct.
When reporting, include the root cause, evidence that ruled alternatives in or out, the fix, and fresh verification.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.