agentleFS
Sign inStart free
poshan0126poshan0126/dotclaude/skills/fix-issue/SKILL.md

fix-issue

Skill871 starsChanged 5 months agoMITView on GitHub

Take a GitHub issue from number to tested fix — read the issue and comments, reproduce, locate the cause, fix with a regression test, and prep a PR that closes it.

53 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use prepare-release, document 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.
  • ShopifySkill

    prepare-release

    Prepare the changeset-release/main branch for release by syncing version.ts files and running pnpm install

    Also in 4 projects that use this

  • nicolasestremSkill

    document

    Create focused documentation for specific components or features

    Also in 4 projects that use this

  • SentrySkill

    write-tests

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

    Also in 3 projects that use this

  • Microsoft AzureSkill

    build

    Build the TypeSpec Rust emitter from source. Run this after cloning the repo, after pulling changes, or when TypeScript source files have been modified.

    Also in 4 projects that use this

  • MicrosoftSkill

    adversarial-review

    Adversarial review of a system design from 6 critical perspectives -- SRE, security, staff engineer, finance, operator, and developer advocate. Produces a unified risk assessment. Use for INTERACTIVE on-demand reviews during a design conversation (/adversarial-review). For RECIPE-DRIVEN reviews (where prior step context is needed), use the systems-design-critic agent instead.

    Also in 3 projects that use this

  • Microsoft AzureSkill

    test

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 51 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the issue is ambiguous on something that changes the fix (which behavior is correct?

    line 26
  2. Distinctive:

    Every bug fix ships with a regression test that fails on the old code.

    line 38
  3. Distinctive:

    Run the tests for the touched area, then lint/typecheck.

    line 43
  4. Very specific:

    After the PR exists, offer to comment the PR link on the issue (gh issue comment — requires confirmation.

    line 50
  5. Distinctive:

    Never start coding before Step 1 is complete — the thread often contains a decision that invalidates the obvious fix.

    line 54
  6. Distinctive:

    If reproduction is impossible (can't access the environment, missing credentials), report exactly what's missing instead of fixing blind.

    line 56

“Common” is measured: kept by at least 6 in 10 of the 51 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

Work a GitHub issue end to end. $ARGUMENTS is the issue number or URL; if omitted, run gh issue list --assignee @me --state open and ask which one.

Step 1: Understand the issue

The live issue thread (or your open assigned issues, when no number was given) is injected below — no need to fetch it again:

!gh issue view $ARGUMENTS --comments 2>/dev/null || gh issue list --assignee @me --state open 2>/dev/null || echo "(no issue arg — paste the issue details)"

  • The thread above is the real spec — read the body AND the discussion; the decision that changes the fix is often in comment 7.
  • Extract: expected behavior, actual behavior, reproduction steps, acceptance criteria, and any decisions already made in the thread.
  • If the issue is ambiguous on something that changes the fix (which behavior is correct? which platform?), ask the user — do NOT guess and do NOT ask in the issue thread without being told to.

Step 2: Classify and branch

  • Bug → follow /debug-fix discipline: reproduce it first (failing test or manual repro), then investigate. No fix before reproduction.
  • Small feature / chore → follow /tdd discipline if a test runner exists: failing test, minimum code, refactor.
  • Propose a branch named fix/issue-$NUMBER-<slug> (or feat/...), matching any existing convention visible in git branch -a. Confirm before creating.

Step 3: Locate and fix

  • Find the code path from the symptoms: grep for the error message, the feature's entry point, or names from the issue.
  • Make the smallest change that satisfies the acceptance criteria. Resist adjacent refactoring — note it for a follow-up instead.
  • Every bug fix ships with a regression test that fails on the old code. If you can't write one, say why in the PR body.

Step 4: Verify against the issue

  • Re-run the reproduction from Step 1 — confirm the reported behavior is gone.
  • Run the tests for the touched area, then lint/typecheck.
  • Walk the acceptance criteria one by one; quote each with its status.

Step 5: Ship it

  • Hand off to /ship (or follow its discipline): commit message and PR body must include Fixes #$NUMBER so the merge auto-closes the issue.
  • PR body: one-line cause, one-line fix, the regression test, and anything from the issue thread that influenced the approach.
  • After the PR exists, offer to comment the PR link on the issue (gh issue comment — requires confirmation; it's outward-facing).

Rules

  • Never start coding before Step 1 is complete — the thread often contains a decision that invalidates the obvious fix.
  • One issue per branch per PR. If the issue is really three issues, say so and fix the one that was asked.
  • If reproduction is impossible (can't access the environment, missing credentials), report exactly what's missing instead of fixing blind.

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