agentleFS
Sign inStart free
roronoazoroshao369roronoazoroshao369/vibe-coding-os/skills/core/disciplined-diagnosis/SKILL.md

disciplined-diagnosis

Skill1 starsChanged 5 months agoMITView on GitHub

Debug by reproducing, isolating, hypothesizing, testing, and documenting evidence before patching. Use for bugs, flaky tests, regressions, performance surprises, or any symptom without a proven cause. Symptom, expected behavior, reproduction steps, logs, recent changes, affected files, and available checks. Diagnosis notes, root cause or best-supported hypothesis, patch plan, regression test, and verification results. Shotgun fixes, changing multiple variables at once, ignoring failed hypotheses, or claiming a cause without evidence. A reproduction exists or limitation is stated; hypotheses are tracked; fix…

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    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:

    Use for bugs, flaky tests, regressions, performance surprises, or any symptom without a proven cause.

    line 20
  2. Distinctive:

    Test the cheapest hypothesis first.

    line 31
  3. Distinctive:

    Add or update a regression check when feasible.

    line 33

≈ “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

Skill: Disciplined Diagnosis

Purpose

Debug by reproducing, isolating, hypothesizing, testing, and documenting evidence before patching.

When to use

Use for bugs, flaky tests, regressions, performance surprises, or any symptom without a proven cause.

Inputs

Symptom, expected behavior, reproduction steps, logs, recent changes, affected files, and available checks.

Workflow

  1. Reproduce or define why reproduction is blocked.
  2. Capture observed vs expected behavior.
  3. Generate ranked hypotheses.
  4. Test the cheapest hypothesis first.
  5. Patch only after evidence points to a cause.
  6. Add or update a regression check when feasible.

Outputs

Diagnosis notes, root cause or best-supported hypothesis, patch plan, regression test, and verification results.

Failure modes

Shotgun fixes, changing multiple variables at once, ignoring failed hypotheses, or claiming a cause without evidence.

Verification checklist

A reproduction exists or limitation is stated; hypotheses are tracked; fix is minimal; regression check proves the bug.

Ghi chú tiếng Việt

Đây là vòng debug có kỷ luật: tái hiện lỗi, lập giả thuyết, kiểm chứng, rồi mới sửa. Liên kết với commands/vibe-diagnose.md và templates/diagnosis-template.md. Khi upstream thay đổi phần diagnose, cập nhật checklist chứ không chép nội dung.

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