agentleFS
kapadiaskapadias/nonna/.claude/skills/debug/SKILL.md

debug

Skill0 starsChanged 46 days agoMITView on GitHub

Root-cause a failure — reproduce deterministically, isolate by bisection, fix the cause (not the symptom), and leave a regression test behind.

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-discord, add-slack and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    add-discord

    Add Discord bot channel integration via Chat SDK.

    Also in 11 projects that use this

  • MicrosoftSkill

    add-slack

    Add Slack channel integration via Chat SDK.

    Also in 11 projects that use this

  • +10 more from microsoft

The file

Files
SKILL.md

Debug: $ARGUMENTS

Steps (hand to debugger for anything non-obvious)

  1. Reproduce. Get a deterministic repro — ideally a failing test. If none exists, write one now; it becomes the regression test. A bug you cannot reproduce, you cannot claim to have fixed.
  2. Isolate. Form a hypothesis and bisect — recent diffs, inputs, the code path, git history. Read the stack trace and the actual values; trust evidence over intuition. Use explorer to locate suspects without bloating this thread.
  3. Diagnose. State the root cause in one sentence: the bug is X, which causes Y under condition Z.
  4. Fix minimally. Change the cause, not the symptom. Keep the diff small. Do not broaden a catch, loosen a check, or weaken a test to make red go away — that hides the bug (see .claude/rules/safety.md).
  5. Prove it. The regression test passes, the full suite stays green, and nothing was masked.

Output

The root-cause sentence, the minimal fix, and the regression test that now guards it.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.