agentleFS
Sign inStart free
3metaJun3metaJun/mstack/skills/principle-fix-root-causes/SKILL.md

principle-fix-root-causes

Skill0 starsChanged 27 days agoMITView on GitHub

Debug by reproducing the symptom, tracing the causal chain, and fixing the earliest incorrect assumption or state transition. Use for crashes, flaky behavior, restart failures, and recurring workarounds.

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 45 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:

    Do not silence a symptom while leaving the cause intact.

    line 9
  2. Distinctive:

    Ask why each preceding condition became possible until reaching the first incorrect assumption, invalid state, or broken boundary.

    line 12

“Common” is measured: kept by at least 6 in 10 of the 45 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

Fix root causes

Do not silence a symptom while leaving the cause intact.

  1. Reproduce the failure with the smallest observable case.
  2. Ask why each preceding condition became possible until reaching the first incorrect assumption, invalid state, or broken boundary.
  3. Instrument uncertain transitions and read actual values. Do not guess.
  4. Fix the cause at its owner, then search for the same pattern elsewhere.
  5. Re-run the reproduction and the nearest meaningful validation.

Resist guards that merely suppress a crash. If a workaround needs a long comment to remain believable, revisit the model or boundary.

For failures that appear after restart, inspect durable state before blaming unchanged code: configuration, caches, locks, checkpoints, serialized objects, and version skew. If clearing state restores behavior, add validation, migration, or reconciliation rather than institutionalizing manual cleanup.

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