agentleFS
insapption-projectsinsapption-projects/claude-agent-team-starter/.claude/skills/implement-fix/SKILL.md

implement-fix

Skill1 starsChanged 8 months agoMITView on GitHub

Applies the approved fix plan to resolve lint, type, and test errors. Strictly applies only the approved fixes — no additional changes. Step 9 of the dev-workflow.

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

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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:

    Do NOT improve, refactor, or clean up anything else

    line 30
  2. Distinctive:

    If the fix plan includes auto-fixable items:

    line 40
  3. Distinctive:

    After applying each fix, run the SPECIFIC test or lint check that was failing — not the full suite:

    line 79
  4. Distinctive:

    If the spot check still fails:

    line 90
  5. Distinctive:

    Do NOT proceed to the next fix until the current one is confirmed passing.

    line 97

≈ “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: /implement-fix

Usage

/implement-fix

Invoke with no arguments. Executes the approved fix plan from /fix-plan.

Prerequisites

  • /fix-plan must have been approved by the lead in this session
  • The original implementation from Step 4 must be in place

Rules

Same as /implement-plan but stricter scope:

  1. Fix ONLY what the approved fix plan lists
  2. Do NOT improve, refactor, or clean up anything else
  3. Auto-fixable tools should run FIRST so manual fixes build on clean code
  4. Report each fix as it's applied

Execution Process

1. Apply Auto-fixes First

If the fix plan includes auto-fixable items:

Laravel (Pint)

./vendor/bin/pint {file1} {file2} ...

Confirm each file changed:

✅  [1/{N}] pint auto-fixed: {file} — {N} changes applied

React / React Native / Frontend (ESLint)

npx eslint {files} --fix

Confirm:

✅  [1/{N}] eslint auto-fixed: {file} — {N} rules corrected

2. Apply Manual Fixes

For each manually fixed item in the plan:

Before editing: re-read the target file to confirm current state After editing: output a brief diff summary:

✅  [{N}/{total}] FIXED: {file}:{line}
    Error was : {error message}
    Fix applied: {1-line description}

3. Verify Each Fix (spot check)

After applying each fix, run the SPECIFIC test or lint check that was failing — not the full suite:

# Laravel: run single test
php artisan test --filter {TestClassName}

# React/RN: run single test file
pnpm test --run {file_pattern}

If the spot check still fails:

❌  Spot check failed for {test/file}.
    Error: {message}
    This fix is not complete — pausing for lead review.

Do NOT proceed to the next fix until the current one is confirmed passing.


4. Completion Report

──────────────────────────────────────────────────────────────
  FIX IMPLEMENTATION COMPLETE
──────────────────────────────────────────────────────────────
Auto-fixes applied  : {N}
Manual fixes applied: {N}
Spot checks         : {N}/{N} passed

Files modified: {list}

Next step: /git-commit (then /test-lint to confirm full suite)
──────────────────────────────────────────────────────────────

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.