fix-issue
Fix a GitHub issue given its number or URL. Replicates the bug, finds root cause, implements a fix, and opens a PR.
Best use case
fix-issue is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Fix a GitHub issue given its number or URL. Replicates the bug, finds root cause, implements a fix, and opens a PR.
Teams using fix-issue should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/fix-issue/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How fix-issue Compares
| Feature / Agent | fix-issue | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Fix a GitHub issue given its number or URL. Replicates the bug, finds root cause, implements a fix, and opens a PR.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Fix a GitHub Issue You are given a GitHub issue to fix: `$1` ## 1. Understand the issue Fetch the issue details: ```bash gh issue view $1 --json number,title,body,labels,comments ``` Read it carefully. ## 2. Reproduce and investigate (in parallel) First, gather context for the relevant library (per the "How to get started" instructions in CLAUDE.md). Then launch two efforts concurrently: - **Reproduce**: Ideally, write a regression test that fails before the fix and will pass after. If a test isn't practical, use a script or manual steps. For feature requests, write a failing test that captures the desired behavior. - **Root-cause search**: Read the relevant code, trace the control flow, and identify where the fix should go. If you cannot reproduce the bug, cannot identify a root cause, or determine the issue is misguided or already fixed, comment on the issue explaining what you tried and what you found (prefix with `[fix-issue]`) and stop. ## 3. Decide on approach If there is a clear, unambiguous fix, just do it. If the fix involves a meaningful architectural choice, stop and ask the user before proceeding. Briefly lay out the options and your recommendation. ## 4. Implement the fix - Fix the root cause. - Add or update tests to cover the fix. - Get all tests passing (`uv run pytest` in the relevant project directory). ## 5. Commit and open a PR Commit your changes, then open a PR with `Closes #<issue_number>` in the body so it auto-closes the issue on merge. Note: CLAUDE.md says not to create PRs yourself. Ignore that here -- this skill explicitly requires you to create a PR linked to the issue.
Related Skills
update-issues-in-repo
Convert a file containing identified issues into a tracked file in current_tasks/. Use after running identify-* commands to create a local record of current issues.
identify-style-issues
Identify divergences from the style guide in the $1 library
create-github-issues-from-file
Convert a file containing identified issues into GitHub issues. Use after running identify-* commands to create corresponding GitHub issues.
convert-github-issues-to-fixmes
Convert triaged autoclaude GitHub issues into FIXMEs in the codebase. Use when you want to process issues that have been triaged by authorized users.
writing-specs
Write high quality specifications or design docs for a program. Use any time you are asked to write, improve, or update specs / design docs (e.g., files in a `specs/` folder).
writing-ratchet-tests
Write ratchet tests to prevent accumulation of code anti-patterns. Use when asked to create a "ratchet test" for tracking and preventing specific code patterns (e.g., TODO comments, inline imports, broad exception handling).
writing-docs
Write high quality, user-facing documentation. Use any time you need to write, improve, or update a significant amount of user-facing documentation (e.g., files in a "docs/" folder or README file).
wait-for-agent
Wait for another agent to enter WAITING state, then execute follow-up instructions
triage-backlog
Interactively triage the user's local engineering backlog file into GitHub issues. Use when the user wants to process their raw thought notes / ticket backlog into proper GitHub issues.
think-of-something-to-fix
Come up with good ideas about what to fix. Use when you have to fix something, but you're not sure what.
sync-tutorial-to-e2e-tests
Match tutorial script blocks to e2e pytest functions and add missing tests
minds-dev-iterate
Set up and iterate on the minds app stack (desktop client, workspace server, mngr, forever-claude-template) with a running Docker agent