bugfix
Skill4 starsChanged 4 days agoMITView on GitHub
Fix a reported bug with a regression test. Invoke with a bug description and reproduction steps.
35 other projects use a version of this.
Adopted by
Most recently taken up by
- 5uck1ess/devkittheir own version, first seen Nov 15, 2026
- isanchez-aguilar/relayrace-aitheir own version, first seen Nov 8, 2026
- icarloscornejo/doertheir own version, first seen Nov 7, 2026
- ClaireAll/skillstheir own version, first seen Nov 5, 2026
- bhoon716/skill-forgetheir own version, first seen Nov 2, 2026
- Snowflake-Labs/coco-skillstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use refactor, commit and 5 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.
GitHubSkillrefactor
Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.
Also in 6 projects that use this
SentrySkillcommit
Create commit messages following Sentry conventions. Use when committing code changes, writing commit messages, or formatting git history. Follows conventional commits with Sentry-specific issue references.
Also in 8 projects that use this
Microsoft AzureSkilldocs
Also in 3 projects that use this
MicrosoftSkillpr-review
Verify the technical accuracy of a vscode-docs pull request against the VS Code source code in microsoft/vscode. Use when reviewing a docs PR for factual correctness: setting names, command IDs, default values, API shapes, keybindings, versioned availability, and described behavior.
Also in 3 projects that use this
Hugging FaceSkillimplement
Make tests pass. Invoke after /write-tests produces failing tests.
Also in 3 projects that use this
NVIDIASkillresearch
Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.
Also in 3 projects that use this
Other versions35 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 35
- alibaba/MNN★ 17ksame name
- SparkDevNetwork/Rock★ 701same name
- oasm-platform/open-asm★ 277same name
- atelier-fashion/adlc-toolkit★ 174same name
- team-attention/hoyeon★ 173same name
- irahardianto/awesome-agv★ 157same name
- Snowflake-Labs/coco-skills★ 54same name
- mrveiss/AutoBot-AI★ 44same name
- dan-the-dev/xp-developer-skills★ 31same name
- ecodelearn/template-claude-code-open★ 25same name
25 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository16 other files it gives its agents.
- benchmarkSkill
- designSkill
- deterministic-pr-gatesSkill
- featureSkill
- gatesSkill
- parallel-reviewSkill
- pipeline-reviewSkill
- planSkill
- pr-followupSkill
- releaseSkill
- reviewSkill
- specSkill
- statusSkill
- sync-workflowSkill
- testSkill
- trim-contextSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 32 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
Read AGENTS.md/CLAUDE.md before touching any file.
- Distinctive: line 28
Before changing any production code, write a test that:
- Distinctive: line 32
Run it to confirm it fails:
- Distinctive: line 40
Do not proceed until it fails for the right reason.
- Distinctive: line 46
Run the new test — must pass
- Distinctive: line 47
Run the full test suite — must all pass, no regressions:
- Very specific: line 83
All fixes must respect the layer boundaries in AGENTS.md/CLAUDE.md:
- Distinctive: line 86
No business logic moved into Views to work around a bug
“Common” is measured: kept by at least 6 in 10 of the 32 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.
Files
Bug Fix Agent
You are the Bug Fix Agent for an iOS app project. Your job is to fix a reported bug with a regression test.
Trigger
Invoked with a bug report: description + reproduction steps (e.g. /bugfix "CSV import creates duplicate transactions when imported twice").
Process
1. Create the branch
Regular bug: Branch fix/<bug-name> off develop.
Hotfix (production bug on main): Branch hotfix/<bug-name> off main, then merge to both main and develop.
Read AGENTS.md/CLAUDE.md before touching any file.
Also read if they exist — skip silently if absent:
.claude/context/invariants.md— inviolable rules; ensure the fix does not violate any.claude/context/rejections.md— past review violations; ensure the fix does not repeat known bad patterns.claude/context/incidents.md— past bugs and their root causes; check whether this symptom matches one already diagnosed before investigating from scratch
2. Write the failing test first
Before changing any production code, write a test that:
- Reproduces the exact bug described
- Fails with a clear error message that matches the symptom
Run it to confirm it fails:
xcodebuild test <BuildTarget> -scheme <AppName> \
-destination 'platform=iOS Simulator,name=<simulator from AGENTS.md/CLAUDE.md>' \
-only-testing:<AppName>Tests/<SuiteName>/<testName> \
2>&1 | grep -E "Test.*passed|Test.*failed|BUILD"Do not proceed until it fails for the right reason.
3. Implement the minimal fix
Change only what's needed to make the failing test pass. Do not refactor, rename, or clean up surrounding code unless it's the direct cause of the bug.
4. Confirm the fix
- Run the new test — must pass
- Run the full test suite — must all pass, no regressions:
xcodebuild test <BuildTarget> -scheme <AppName> \
-destination 'platform=iOS Simulator,name=<simulator from AGENTS.md/CLAUDE.md>' \
2>&1 | grep -E "TEST SUCCEEDED|TEST FAILED"5. Update CHANGELOG
Append a one-line entry to the ## [Unreleased] section of CHANGELOG.md (create the section if absent). Skip only for internal refactors with no user-visible behaviour change.
6. Log the incident
Append an entry to .claude/context/incidents.md (create the file with a one-line header if it doesn't exist):
## YYYY-MM-DD — <bug name>
**Symptom:** <what was observed — error message, wrong behavior, exact repro condition>
**Root cause:** <one line — the actual mechanism, not just "logic error">
**Fix:** <file:line or brief description of the change>
**Search terms:** <keywords a future symptom description might match — error strings, type names, subsystem>The point is a searchable root-cause record, not a duplicate of the CHANGELOG entry (which is user-facing) or the git commit message (which is buried in history until someone thinks to git log for it). Keep each entry to what a future /bugfix run skimming this file needs to recognize "this is the same thing" from a different symptom description.
7. Commit and PR
git add <changed files>
git commit -m "fix: <short description of what was wrong>"Regular bug: Open PR to develop. The Review Agent (/review) runs on the PR.
Hotfix: Open PR to main — also open a second PR to develop. Both go through /review and, on the app lane, code-review (medium) (via /pr-followup) before merging; /test's coverage audit runs before /gates. Unlike release/SKILL.md's develop back-merge (safe as a raw git merge because a release branch only ever contains commits develop already reviewed), a hotfix branches directly off main and its commits have never been through /review on develop — so its back-merge needs the same gate its main PR got, not a raw merge.
Architecture rules
All fixes must respect the layer boundaries in AGENTS.md/CLAUDE.md:
- Domain Service fixes stay in
Services/ - Repository fixes stay in
Repositories/(implementation subfolder per your architecture) - No business logic moved into Views to work around a bug
Done when
Failing test passes, full suite green, PR open.
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
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.

