agentleFS
Sign inStart free
isanchez-aguilarisanchez-aguilar/relayrace-ai/skills/bugfix/SKILL.md

bugfix

Skill0 starsChanged 11 days agoApache-2.0View on GitHub

Fix a bug, regression or pasted error in ANY repository with the short generic pipeline — reproduce it with a failing test first, fix the root cause minimally, tester breaks it again, another provider reviews it, draft PR. Use in places that do not define their own /fix skill (a repo with its own /fix keeps using it). The owner describes bugs in plain language; route them here yourself.

34 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use feature, refactor 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 7 projects that use this

  • GitHubSkill

    refactor

    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

  • SentrySkill

    spec

    Produce a verified spec — problem, desired outcome, and acceptance criteria — before building. Use when given a GitHub/Linear issue link, when starting from a fuzzy in-conversation idea, or asked to "figure out what to do" / "scope this" / "what should I build" — whenever the *what* isn't yet pinned down. Grills the ambiguities, checks the premise against the code, and produces acceptance criteria you sign off on — then hands to design-first.

    Also in 4 projects that use this

  • SentrySkill

    commit

    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

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 4 projects that use this

  • Microsoft AzureSkill

    docs

    Also in 3 projects that use this

  • +1 more from getsentry

The file

Create a free account to mount
Files
SKILL.md

/bugfix — generic pipeline for a bug

Say in one line that you are taking this route ("I am treating this as a bug"). The repository's own rules win over anything here.

1. Reproduce first

Gather the evidence (error text, steps, logs — without secrets). Rank the likely causes, then write the test that fails for the leading one. No fix before a failing test or an exact reproduction. If it cannot be reproduced, say so and ask the user for what is missing instead of guessing.

2. Root cause, minimal fix

Find why, not just where. Fix the cause with the smallest change; keep unrelated refactors out. The failing test now passes; run the repository's typecheck, linter and the tests of the touched area. Use implementer (model: sonnet) for the fix when the session is busy; opus only for a hard diagnosis. Never fable without asking the owner first.

3. Break it again

Launch tester (model: sonnet) to look for the same bug's siblings: the other callers, the boundary values, the error path.

4. Review and close

Branch, commit, push, draft PR, and a read-only review by a DIFFERENT provider (Antigravity or Codex) with .ai/prompts/review.md, exactly as /work step 4 describes. Merge only with the owner's authorization. Report the root cause, the test that now guards it, the commands with results, and what is still unverified.

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