DE

debug-investigator

A strict, evidence-based debugging workflow that prioritizes reproduction over guessing.

Install

mkdir -p .claude/skills/debug-investigator && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/9763" && unzip -o skill.zip -d .claude/skills/debug-investigator && rm skill.zip

Installs to .claude/skills/debug-investigator

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Apply a systematic reproduce, isolate, hypothesize, test, and verify loop to debug failures and preserve root-cause knowledge.
126 chars · catalog descriptionno explicit “when” trigger
Intermediate

Key capabilities

  • Reproduce deterministic failures
  • Isolate problem space and code paths
  • Formulate explicit debugging hypotheses

How it works

The skill enforces a disciplined five-step loop of reproduction, isolation, hypothesis, testing, and verification to ensure root-cause resolution.

Inputs & outputs

You give it
Bug report or failure description
You get back
Verified root cause and regression test

When to use debug-investigator

  • Debugging persistent production issues
  • Isolating complex state bugs
  • Root cause analysis

About this skill

Debug Investigator — systematic, not vibes-based

Follow this loop every time. Jumping straight to "fix" without reproducing is how false fixes ship.

The loop

  1. Reproduce. Get a deterministic failure. If you can't reproduce, you can't fix.
  2. Isolate. Bisect the problem space: narrow inputs, narrow code paths, narrow time windows.
  3. Hypothesize. Form one explicit hypothesis. Write it in memory/working/WORKSPACE.md under "Active hypotheses".
  4. Test the hypothesis. A single change that proves or disproves it — no shotgun fixes.
  5. Verify. After the fix, re-run the repro. If the bug is gone, the repro is your new regression test.

What to log

  • Each hypothesis that was wrong (high importance; these compound into domain knowledge).
  • The actual root cause and why it wasn't obvious.

Anti-patterns

  • "It works now, not sure why" — keep investigating.
  • Adding try/except to silence an error without understanding it.
  • Changing five things at once and claiming one of them fixed it.

Self-rewrite hook

If the same class of bug appears 3+ times (timezone bugs, race conditions, off-by-one), promote a lesson to LESSONS.md and update this skill with a domain-specific sub-procedure.

When not to use it

  • When jumping to fixes without reproduction
  • When changing multiple variables simultaneously

Limitations

  • Requires a deterministic reproduction case
  • Prohibits shotgun fixes

How it compares

It mandates a systematic, evidence-based debugging loop instead of trial-and-error fixes.

Compared to similar skills

debug-investigator side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
debug-investigator (this skill)04moNo flagsIntermediate
python-testing-patterns772moReviewIntermediate
error-handling-patterns352moNo flagsIntermediate
codex-claude-loop139moReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

Search skills

Search the agent skills registry