agentleFS
Crypto69Crypto69/claude-skills/fix-bug/SKILL.md

fix-bug

Skill0 starsChanged 5 months agoMITView on GitHub

Fix bugs from docs/bugs.md. Lists unfixed bugs in priority order for selection, or accepts a bug number directly. Investigates, implements, tests, and updates the bug status.

44 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 10 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

Show its rules and text

We split this skill into the rules it gives an agent

23 rules. 0 are common, 19 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 44 edited versions we read keep these.

  • 19

    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. Distinctive:

    Read the bug description, steps to reproduce, and expected vs actual behaviour

    line 38
  2. Distinctive:

    Search for the root cause using Grep, Read, and Glob

    line 40
  3. Distinctive:

    Follow all coding conventions from CLAUDE.md

    line 50
  4. Distinctive:

    Don't introduce unnecessary changes or refactors beyond the bug fix

    line 51
  5. Distinctive:

    If the fix spans multiple areas, handle each area

    line 52
  6. Distinctive:

    Add comments only if the fix is non-obvious

    line 53
  7. Distinctive:

    Add one mapping per area in your project

    line 58
  8. Distinctive:

    If the bug involves UI behaviour, validate it visually (e.g.

    line 59
  9. Distinctive:

    If tests fail, diagnose and fix before proceeding

    line 60
  10. Distinctive:

    Add a Fix details section below the existing fields:

    line 64
  11. Distinctive:

    If the user selects multiple bugs or says "all":

    line 80
  12. Distinctive:

    Update each bug's status as you go

    line 82
  13. Distinctive:

    If one fix is blocked or too complex, skip it, note why, and move to the next

    line 83
  14. Very specific:

    If docs/bugs.md has no open bugs, say "No open bugs to fix.

    line 88
  15. Very specific:

    If the requested bug number doesn't exist, say "BUG-{NNN} not found in docs/bugs.md"

    line 89
  16. Distinctive:

    If the bug is already Fixed, say "BUG-{NNN} is already marked as Fixed"

    line 90
  17. Very specific:

    If the bug is Won't Fix, say "BUG-{NNN} is marked as Won't Fix — reopen it first with /add-bug or edit docs/bugs.md"

    line 91
  18. Distinctive:

    If you cannot determine the root cause after investigation, update the status to Confirmed (if it was Reported), describe your findings, …

    line 92
  19. Distinctive:

    If the fix requires changes to infrastructure, environment variables, or third-party services (e.g.

    line 93
  20. Very specific:

    Use the <TIMEZONE> timezone for timestamps

    line 107
  21. Distinctive:

    Always read the relevant code before attempting a fix — never guess

    line 108
  22. Distinctive:

    Prefer the smallest correct fix over a large refactor

    line 109
  23. Distinctive:

    If the fix is risky or touches payment/auth code, flag it to the user before applying

    line 110

“Common” is measured: kept by at least 6 in 10 of the 44 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 Bug

Investigate and fix bugs tracked in docs/bugs.md.

Process

  1. Read docs/bugs.md — Parse all bug entries.
  2. Determine which bug to fix:

    • If the user provided a bug number (e.g. /fix-bug 1, /fix-bug BUG-003): Find that specific bug. If it's already Fixed or Won't Fix, inform the user and stop.
    • If no bug number provided: Collect all open bugs (statuses: Reported, Confirmed, In Progress) and present them in priority order. Use AskUserQuestion to let the user pick which bug(s) to fix.
  3. Priority ordering — When listing bugs for selection, sort by:

    1. Severity: Critical > High > Medium > Low
    2. Status: In Progress > Confirmed > Reported (prefer bugs already being worked on)
    3. Age: Older bugs first (earlier reported date)

    Display as a numbered list:

    Open bugs (prioritised):
    
    1. [BUG-005] 🔴 Critical — Checkout fails when the payment webhook times out (<area-1>)
    2. [BUG-002] 🟡 High — File upload stalls on slow connections (<area-2>)
    3. [BUG-001] 🔴 Medium — Form changes don't enable the submit button (<area-1>)
    
    Enter bug number(s) to fix (e.g. "1" or "1,3"), or "all" to fix everything:
  4. Investigate the bug — Before writing any code:
    • Read the bug description, steps to reproduce, and expected vs actual behaviour
    • Identify the area (one of your configured project areas — see Configuration) and navigate to the relevant code
    • Search for the root cause using Grep, Read, and Glob
    • Understand the surrounding code and any related functionality
    • Identify the minimal set of files that need to change
  5. Update status to In Progress — Edit docs/bugs.md to change the bug's status:
    | **Status** | 🔵 In Progress |
  6. Implement the fix — Write the minimal, correct fix:
    • Follow all coding conventions from CLAUDE.md
    • Don't introduce unnecessary changes or refactors beyond the bug fix
    • If the fix spans multiple areas, handle each area
    • Add comments only if the fix is non-obvious
  7. Verify the fix — Run the test suite for the affected area to confirm. Map each area to its test command (configure these for your project):
    • For <area-1>: <test command, e.g. cd frontend && npm test>
    • For <area-2>: <test command, e.g. pytest backend/>
    • Add one mapping per area in your project
    • If the bug involves UI behaviour, validate it visually (e.g. with a headed browser / Playwright)
    • If tests fail, diagnose and fix before proceeding
  8. Update status to Fixed — Edit docs/bugs.md to update the bug entry:
    • Change status to 🟢 Fixed
    • Add a Fix details section below the existing fields:
    **Fix details:**
    - **Fixed:** {YYYY-MM-DD <TIMEZONE>}
    - **Root cause:** {Brief explanation of what caused the bug}
    - **Files changed:** {List of files modified}
  9. Report to the user — Summarise:
    • What the root cause was
    • What was changed and where
    • Whether tests pass
    • Any follow-up items (e.g. "this should also be tested manually on a real device")

Fixing multiple bugs

If the user selects multiple bugs or says "all":

  • Fix them one at a time in priority order
  • Update each bug's status as you go
  • If one fix is blocked or too complex, skip it, note why, and move to the next
  • Provide a summary at the end listing which bugs were fixed and which were skipped

Edge cases

  • If docs/bugs.md has no open bugs, say "No open bugs to fix. Nice work!"
  • If the requested bug number doesn't exist, say "BUG-{NNN} not found in docs/bugs.md"
  • If the bug is already Fixed, say "BUG-{NNN} is already marked as Fixed"
  • If the bug is Won't Fix, say "BUG-{NNN} is marked as Won't Fix — reopen it first with /add-bug or edit docs/bugs.md"
  • If you cannot determine the root cause after investigation, update the status to Confirmed (if it was Reported), describe your findings, and ask the user for guidance rather than guessing at a fix
  • If the fix requires changes to infrastructure, environment variables, or third-party services (e.g. payment, storage, or email providers) that can't be done in code, document what needs to be done manually and mark the bug as 🟡 Confirmed with a note

Configuration

Replace these placeholders with your project's values before using the skill:

  • <area-1> / <area-2> / … — the modules / sub-projects in your repo (e.g. frontend, backend, api, mobile). Keep this list identical to the areas defined in add-bug.
  • <test command …> — how to run tests for each area (step 7), e.g. cd frontend && npm test, pytest backend/, flutter test. Add one mapping per area.
  • <TIMEZONE> — the timezone for the Fixed timestamp (e.g. UTC, America/New_York, Europe/London).

See the repository README for the full placeholder reference shared across skills.

Notes

  • Use the <TIMEZONE> timezone for timestamps
  • Always read the relevant code before attempting a fix — never guess
  • Prefer the smallest correct fix over a large refactor
  • If the fix is risky or touches payment/auth code, flag it to the user before applying
  • Each bug fix should be a separate commit

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.