agentleFS
Sign inStart free
abigaylehabigayleh/claude-workflow-plugin/skills/fix-bug/SKILL.md

fix-bug

Skill0 starsChanged 46 days agoMITView on GitHub

Fix a specific bug — diagnose the root cause, apply the fix, confirm the bug is actually gone, quality check, push, then hand off a PR. Lighter than ship-feature (no test-writer, no parallel stages, no ui-checker unless the bug is visual).

  • Commits and pushes

40 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use improvement, build-feature 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.
  • kiminmonacoSkill

    improvement

    Guide for making improvements to existing ClaudeBar functionality using TDD. Use this skill when: (1) Enhancing existing features (not adding new ones) (2) Improving UX, performance, or code quality (3) User asks "improve X", "make Y better", or "enhance Z" (4) Small enhancements that don't require full architecture design For NEW features, use implement-feature skill instead.

    Also in 4 projects that use this

  • sirakinbSkill

    build-feature

    Autonomous task loop that picks ready tasks, implements them, updates progress.txt, commits, and repeats. Use when asked to 'build feature', 'run the loop', or 'implement these tasks'.

    Also in 5 projects that use this

  • kiminmonacoSkill

    implement-feature

    Guide for implementing features in ClaudeBar following architecture-first design, TDD, rich domain models, and Swift 6.2 patterns. Use this skill when: (1) Adding new functionality to the app (2) Creating domain models that follow user's mental model (3) Building SwiftUI views that consume domain models directly (4) User asks "how do I implement X" or "add feature Y" (5) Implementing any feature that spans Domain, Infrastructure, and App layers

    Also in 7 projects that use this

  • SentrySkill

    write-tests

    Write tests following project conventions. Use when adding new tests or modifying existing ones.

    Also in 6 projects that use this

  • JetBrainsSkill

    create-plan

    Research the codebase and create an implementation plan with architecture notes, design document, and track decomposition. Use when starting a new feature or large change.

    Also in 4 projects that use this

  • JasonPaffSkill

    implement-plan

    Execute implementation plan with structured tracking and validation using subagent architecture

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 40 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    Follow git-workflow to create a fix/...

    line 17
  2. Very specific:

    Use the commands it reports.

    line 26
  3. Very specific:

    If the bug had a visual symptom, use dev-verify to hand the user a checklist confirming the fix, and wait for their answer.

    line 52
  4. Very specific:

    Commit per commit-message — fix: ..., one line.

    line 69

“Common” is measured: kept by at least 6 in 10 of the 40 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 a bug

You're fixing the specific bug described in this skill's arguments.

Smaller than ship-feature — no parallel stages, no test-writer. Ends at a pull request the user opens; you never merge to the base branch.

Step 0 — worktree

Follow git-workflow to create a fix/... branch in its own worktree off the base branch.

Step 1 — detect the stack

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/detect-stack.py"

Use the commands it reports. If ecosystem is unknown, ask the user.

Step 2 — diagnose

Launch the debugger subagent with the bug description. It reproduces the issue and reports a root cause plus a recommended fix. It does not edit code.

If it says it couldn't reproduce the bug, stop and report that. Don't have code-writer implement a fix for a cause nobody confirmed — you'd be changing working code on a guess and calling the bug fixed.

Step 3 — fix

Launch code-writer with the debugger's root-cause report. It implements the recommended fix, touches nothing unrelated, and must not weaken or delete any test to make it pass.

Step 4 — confirm

Two separate things, and the second is the one that matters:

  1. The project's checks — run whatever Step 1 found (test, lint, typecheck, build). Report exactly what ran; skip and name what's absent.
  2. The actual bug — reproduce it the way the debugger did in Step 2 and confirm it's gone. Lint and build don't know what the bug was.

If the bug had a visual symptom, use dev-verify to hand the user a checklist confirming the fix, and wait for their answer.

Step 5 — quality check

Launch code-quality-reviewer on the diff. If the bug was visual, also launch ui-checker on the same diff — otherwise skip it.

A bug fix deserves one extra question: is this the root cause or the symptom? A fix that adds a null check where the null shouldn't have existed will pass every check here and leave the real bug in place.

Step 6 — decide

Fixed, and no blocking review feedback:

  1. diff-review the working diff.
  2. Commit per commit-message — fix: ..., one line.
  3. Rebase onto the current base per git-workflow, then push the branch.
  4. Report and stop: root cause, what changed, what verification ran, and the gh pr create command. The user opens the PR.

Still wrong: return to Step 2 with the new failure information, up to 2 total attempts. After that, stop and report the current state rather than retrying — this needs a human look. Leave the work on the branch.

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