agentleFS
Sign inStart free
MelvynxMelvynx/ai-maxxing-skills/skills/code-debug/SKILL.md

code-debug

Skill32 starsChanged 23 days agoMITView on GitHub

Debug hard bugs and performance regressions with a tight red-capable loop, falsifiable hypotheses, a focused fix, regression coverage, and real runtime proof.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No red-capable loop means no hypotheses.

    line 9
  2. Distinctive:

    Test one variable at a time.

    line 14
  3. Very specific:

    Before finishing, remove temporary instrumentation and throwaway harnesses, state the confirmed root cause, and pass the result through the …

    line 19

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Build the feedback loop first. Name one fast, deterministic, agent-runnable command that exercises the user's exact symptom, run it, and capture the red result. Tighten and minimise it until every remaining element is load-bearing.

No red-capable loop means no hypotheses. If a loop cannot be built, report what was tried and request the missing access or artifact.

Once red:

  1. Rank 3 to 5 falsifiable hypotheses, each with a prediction.
  2. Test one variable at a time; prefer a debugger, then uniquely tagged targeted logs. Measure performance regressions before changing them.
  3. Compare the viable fixes and choose the smallest one that addresses the evidenced cause. In -a or auto mode, use the recommended reversible option without waiting for confirmation.
  4. Turn the minimal repro into a failing regression test at the real seam when one exists, then implement the fix and watch it pass. Document when the architecture provides no honest seam.
  5. Re-run the original unminimised loop and exercise the real runtime path. Passing tests alone do not prove the bug is fixed.

Before finishing, remove temporary instrumentation and throwaway harnesses, state the confirmed root cause, and pass the result through the verify skill. Finish only when the original symptom is proven gone or report BLOCKED: NOT PROVEN.

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.

Check your setup, free