agentleFS
alamenaialamenai/terrae/.claude/skills/fix/SKILL.md

fix

Skill245 starsChanged 9 months agoMITView on GitHub

Systematically fix issues found by /review or reported by the user

90 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use feature, frontend-code-review and 9 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.
  • bradtraversySkill

    feature

    Manage current feature workflow - start, review, explain or complete

    Also in 10 projects that use this

  • chendongqiSkill

    frontend-code-review

    Trigger when the user requests a review of frontend files (e.g., `.tsx`, `.ts`, `.js`). Support both pending-change reviews and focused file reviews while applying the checklist rules.

    Also in 4 projects that use this

  • GoogleSkill

    pr-creator

    Also in 4 projects that use this

  • PJuniszewskiSkill

    cook

    Feature development with guardrails. Plan → Review → Code → Ship.

    Also in 3 projects that use this

  • vbrevikSkill

    work

    Use when the user says 'plan', 'todo', 'copy plan', 'append plan', 'resume plan', 'priorities', or 'what's next'.

    Also in 4 projects that use this

  • MetaSkill

    roadmap

    Build, continue, inspect, or visualize a source-grounded mathematical roadmap and theorem DAG in an existing Autoform Markdown blueprint. Use for source research, repository-wide inventories of existing and planned mathematics, scope, coverage, milestones, and roadmap articles; do not create repository infrastructure or prove Lean declarations.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 83 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If coming from a /review, gather the issues from the review output.

    line 15
  2. Distinctive:

    Read the file to understand the current code

    line 47
  3. Distinctive:

    Verify the fix doesn't break anything nearby

    line 49
  4. Very specific:

    Run npx tsc --noEmit to check for type errors

    line 63
  5. Distinctive:

    Ask if they want to proceed with committing or if adjustments are needed.

    line 87
  6. Distinctive:

    Add the import at the top of the file, grouped with similar imports.

    line 93
  7. Very specific:

    Add a return function that removes event listeners, cancels animation frames, clears timeouts, and removes map layers/sources/markers.

    line 97

“Common” is measured: kept by at least 6 in 10 of the 83 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 Skill

Systematically fix code issues found by /review or reported by the user.

Instructions

Step 1: Identify Issues

If coming from a /review, gather the issues from the review output. Otherwise, ask the user what needs fixing.

Categorize each issue by severity:

  • Critical — Compilation errors, missing imports, runtime crashes
  • High — Memory leaks, missing cleanup, security concerns, DRY violations
  • Medium — Convention violations, inconsistencies, naming issues
  • Low — Style preferences, minor optimizations

Step 2: Plan the Fix Order

Fix issues in severity order (critical first). Group related fixes together when they touch the same file to minimize changes.

Present the plan to the user before starting:

## Fix Plan

### Critical (fix first)
1. [Issue] — [File:line] — [What to do]

### High
2. [Issue] — [File:line] — [What to do]

### Medium
3. [Issue] — [File:line] — [What to do]

Step 3: Apply Fixes

For each fix:

  1. Read the file to understand the current code
  2. Apply the minimal change needed to fix the issue
  3. Verify the fix doesn't break anything nearby
  4. Move to the next issue

Follow these principles:

  • Minimal changes — Fix only what's broken, don't refactor surrounding code
  • One concern at a time — Don't mix fixes for different issues in the same edit
  • Preserve intent — Keep the original behavior while fixing the problem
  • Follow project conventions — Apply fixes using the patterns from .claude/rules/

Step 4: Verify

After all fixes:

  1. Run npx tsc --noEmit to check for type errors
  2. Show the user a summary of what was fixed
## Fix Summary

### Fixed
- [Issue] — [File] — [What was done]

### Skipped (needs discussion)
- [Issue] — [Reason]

### Remaining
- [Issue] — [Why it wasn't fixed]

Step 5: Review Changes

Show the user the diff of all changes:

git diff --stat

Ask if they want to proceed with committing or if adjustments are needed.

Common Fix Patterns

Missing Import

Add the import at the top of the file, grouped with similar imports.

Missing useEffect Cleanup

Add a return function that removes event listeners, cancels animation frames, clears timeouts, and removes map layers/sources/markers.

Untracked setTimeout/setInterval

Store the timer ID in a ref and clear it in the cleanup function.

Untracked requestAnimationFrame

Store the RAF ID and cancel it with cancelAnimationFrame in the cleanup function.

Replacing any with Proper Types

Identify what the value actually is and create a named type for it. Use unknown only as a last resort.

DRY Violations

Extract the duplicated code into a shared utility file. Update all files that used the duplicated code to import from the shared location.

Convention Violations

Reference .claude/rules/ for the correct pattern and apply it consistently.

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.