agentleFS
seancabalseseancabalse/agentic-playbook/skills/fix-bug/SKILL.md

fix-bug

Skill0 starsChanged 15 days agoMITView on GitHub

Fix a defect: reproduce it, write a failing test, find the root cause, fix it and record the lesson. Use for each bug.

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

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 44 edited versions we read keep these.

  • 3

    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:

    Find the root cause, not the symptom: Read the code path end to end.

    line 12
  2. Distinctive:

    Confirm with the smallest counterfactual: before fixing: change one condition that should flip the result if your explanation is right (a …

    line 15
  3. Distinctive:

    Never claim a cause you didn't verify: say "likely" and why.

    line 28

“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 a bug

Bug: $ARGUMENTS

  1. Reproduce first, in a worktree. Get the exact steps, environment and evidence (error text, logs, ids, timestamps). Start from what the user did and saw, not from an internal error or a guess about the code. Create a worktree from the affected branch (reproduce-in-worktree) so the investigation never disturbs the working checkout, and reproduce it there. If you can't, say what you tried and gather more evidence before changing code.
  2. Find the root cause, not the symptom. Read the code path end to end. Check the library's behaviour in its source or docs for the installed version. Then:

    • Separate three facts: the trigger (the input or event that starts the fault), the masking condition (the state, timing, cache, configuration or path that hides or exposes it), and the symptom (what the user sees). A masking condition can explain why the bug appears only sometimes without being its cause. Mark each fact verified or likely.
    • Compare with a path that works. Find the earliest point where the failing path and a working one diverge: inputs, state, dependencies, timing. Read the history (blame, commits, migrations) when it explains the divergence. A recent nearby change isn't the cause without evidence.
    • Confirm with the smallest counterfactual before fixing: change one condition that should flip the result if your explanation is right (a log line, a minimal repro, a toggle), and record what happened.
    • Try to prove yourself wrong. Name the observation that would falsify your explanation, and check it. Keep contradictory results; don't explain them away.

    The cause is confirmed when it explains both the failure and the path that works. Note anything else the cause affects.

  3. Write a failing test that reproduces it at the lowest layer that can show it: unit, then DB/policy, then integration. Run it and watch it fail for the right reason. If no automated test can capture it (platform lifecycle, device-only), write down the manual repro steps that will prove the fix.
  4. Fix minimally. Change only what the cause requires. Don't refactor nearby code. If the fix needs a product decision, ask.
  5. Verify: the new test passes, the full suite passes, and the original repro no longer fails in the real app. Also check the neighbouring cases the cause touched.
  6. Record:
    • The ticket: cause (verified) with its trigger and any masking condition, fix, and how it was verified. File new tickets for related problems you found.
    • A runbook "Traps already hit" row if a tool or platform behaved surprisingly.
    • An AGENTS.md rule if the bug came from a rule that wasn't written down (for example "dates from the API are parsed in the shared time module").
  7. Before you hand off to a person, the reproduction, the root cause and an attempted fix exist in the worktree, with the checks run there. Ask a person only for what you can't do: a product decision, a credential, a device. Then bring the fix back from the worktree branch and finish with ship-pr.

Never claim a cause you didn't verify: say "likely" and why.

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.