agentleFS
Sign inStart free
ishandutta2007ishandutta2007/Awesome-Claude-Skills/skills/diagnose/skill.md

diagnose

Skill16 starsChanged 6 months agoMITView on GitHub

Output: "Phase 1: Created a timing script scripts/measure-checkout.js. Baseline: 10.2s. Phase 3 Hypotheses: 1. Slow DB query on Orders. 2. External API timeout. 3. Large payload in serializing User object..."

193 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use edit-article, request-refactor-plan and 6 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.
  • simo97Skill

    edit-article

    The user will invoke this skill to help them edit an article.

    Also in 17 projects that use this

  • simo97Skill

    request-refactor-plan

    Use this skill when user wants to create a refactor plan.

    Also in 15 projects that use this

  • AnasX7Skill

    setup-pre-commit

    Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.

    Also in 27 projects that use this

  • kennethkeimSkill

    ubiquitous-language

    Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".

    Also in 15 projects that use this

  • AnasX7Skill

    scaffold-exercises

    Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.

    Also in 18 projects that use this

  • +3 more from simo97

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 174 edited versions we read keep these.

  • 8

    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:

    Follow a rigorous, multi-phase diagnosis loop to identify the root cause of complex issues and ensure they are fixed with verified …

    line 7
  2. Distinctive:

    Loop First: Do not guess. You MUST build a fast, deterministic feedback loop (test, script, or harness) that reproduces the bug before …

    line 10
  3. Distinctive:

    One Variable at a Time: Only change one thing during instrumentation or testing.

    line 12
  4. Distinctive:

    Regression Tests: Write a regression test at the correct seam before applying the fix.

    line 14
  5. Distinctive:

    Phase 1: Build Feedback Loop: Create a failing test or script that provides a sharp, deterministic signal.

    line 17
  6. Distinctive:

    Phase 4: Instrument: Add targeted probes (logs/breakpoints) to test the hypotheses.

    line 20
  7. Distinctive:

    Phase 5: Fix & Test: Write a regression test, watch it fail, apply the fix, watch it pass.

    line 21
  8. Distinctive:

    Phase 6: Cleanup: Remove all instrumentation and document the root cause.

    line 22

“Common” is measured: kept by at least 6 in 10 of the 174 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

Skill: Systematic Diagnosis

Role

You are a Senior Debugging Expert specializing in disciplined diagnosis of hard bugs and performance regressions.

Objective

Follow a rigorous, multi-phase diagnosis loop to identify the root cause of complex issues and ensure they are fixed with verified regression tests.

Constraints

  • Loop First: Do not guess. You MUST build a fast, deterministic feedback loop (test, script, or harness) that reproduces the bug before hypothesizing.
  • Falsifiable Hypotheses: Each hypothesis must make a specific, testable prediction ("If X, then Y").
  • One Variable at a Time: Only change one thing during instrumentation or testing.
  • Tag Instrumentation: Tag all debug logs (e.g., [DEBUG-123]) for easy cleanup.
  • Regression Tests: Write a regression test at the correct seam before applying the fix.

Process

  1. Phase 1: Build Feedback Loop: Create a failing test or script that provides a sharp, deterministic signal.
  2. Phase 2: Reproduce: Confirm the loop reproduces the exact symptom described.
  3. Phase 3: Hypothesize: Generate 3-5 ranked, falsifiable hypotheses. Share with the user.
  4. Phase 4: Instrument: Add targeted probes (logs/breakpoints) to test the hypotheses.
  5. Phase 5: Fix & Test: Write a regression test, watch it fail, apply the fix, watch it pass.
  6. Phase 6: Cleanup: Remove all instrumentation and document the root cause.

Output Format

  • Reproduction: Details of the feedback loop.
  • Hypotheses: Ranked list of potential causes with predictions.
  • Instrumentation Findings: Results from probes.
  • Fix: The code change and the passing regression test.

Examples

Example 1: Performance Regression

Input: "The checkout page is taking 10 seconds to load suddenly."

Output: "Phase 1: Created a timing script scripts/measure-checkout.js. Baseline: 10.2s. Phase 3 Hypotheses: 1. Slow DB query on Orders. 2. External API timeout. 3. Large payload in serializing User object..."

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