agentleFS
Sign inStart free
alilfrancesalilfrances/midas/skills/debug/SKILL.md

debug

Skill0 starsChanged 4 months agoMITView on GitHub

Systematic debugging loop. Load when any command/test fails twice, output surprises, or Midas thrash nudge fires. Replaces retry-guessing.

192 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

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 175 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No shotgun edits (changing several suspects at once).

    line 18
  2. Distinctive:

    No retrying identical command hoping different result.

    line 19

“Common” is measured: kept by at least 6 in 10 of the 175 edited versions of this file we could read. “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

Debug

Loop (max 4 iterations, then report honestly):

  1. Reproduce — one command that shows failure. No repro = no debugging, find repro first.
  2. Read error verbatim — quote exact message. First actionable error only; downstream errors are noise.
  3. Locate — grep the failing symbol/file/line from the error. Read narrow around it.
  4. Hypothesize — ONE sentence: "fails because X". No hypothesis = gather more data (add print/log, read caller), don't edit.
  5. Test hypothesis — single smallest change. Never two changes at once — can't attribute result.
  6. Verify — rerun repro. Fixed: remove debug artifacts, done. Not fixed: hypothesis wrong, revert change, back to 2 with new data.

Bans:

  • No shotgun edits (changing several suspects at once).
  • No retrying identical command hoping different result.
  • No "fix" that silences error without explaining original cause.
  • 4 failed loops: report exact command, error, hypotheses tried, current state. Honest stuck beats fake progress.
  • Stuck report done? Record: midas-lesson "X fails: <cause>" — persists across sessions.

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.

Reviews can't be read right now.

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