agentleFS
Sign inStart free
claude-worldclaude-world/claude-agent/.claude/skills/gh-issues/SKILL.md

gh-issues

Skill5 starsChanged 8 months agoMITView on GitHub

Auto-fix GitHub issues by fetching open issues, spawning agents to implement fixes, and opening PRs. Monitors PR review comments. Use when user says "fix github issues", "auto-fix bugs", "work through issues on repo X".

  • Installs packages
  • Commits and pushes

35 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use discord-e2e, openclaw-repair-sweep 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.
  • molt-botSkill

    discord-e2e

    Test Discord with Convex-leased QA bots: check credentials without a Gateway, exercise owned messages, or prove OpenClaw replies, files, threads, reactions, streaming, and typing. Distinguish API and Gateway evidence from manual user interactions.

    Also in 10 projects that use this

  • molt-botSkill

    openclaw-repair-sweep

    Run scoped OpenClaw issue/PR repair campaigns: coordinate workers, prove root causes, and land or close verified work under the requested authority.

    Also in 10 projects that use this

  • clawdbotSkill

    openclaw-performance

    Performance work in OpenClaw: a slow or heavy flow (latency, CPU, memory, SQL, RPC, renders), writing or reviewing a perf PR, or adding a cache. Count the work, delete waste first, cache last.

    Also in 7 projects that use this

  • clawdbotSkill

    plugin-sdk-impact

    Count Plugin SDK consumers across live ClawHub releases and bundled OpenClaw plugins before deprecation, removal, or behavior changes; supports public release-date filters.

    Also in 7 projects that use this

  • AtomicBot-aiSkill

    taskflow-inbox-triage

    Also in 6 projects that use this

  • hkyutongSkill

    node-connect

    Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps. Use when QR/setup code/manual connect fails, local Wi-Fi works but VPS/tailnet does not, or errors mention pairing required, unauthorized, bootstrap token invalid or expired, gateway.bind, gateway.remote.url, Tailscale, or plugins.entries.device-pair.config.publicUrl.

    Also in 18 projects that use this

  • +2 more from molt-bot

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 35 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Read the issue body and comments for reproduction steps

    line 40
  2. Very specific:

    Create a feature branch: git checkout -b fix/issue-<number>

    line 42
  3. Distinctive:

    Run tests if available

    line 44
  4. Very specific:

    Commit with message: fix: <description> (closes #<number>)

    line 45
  5. Very specific:

    Always check if gh is installed first

    line 77
  6. Distinctive:

    Never merge PRs without explicit user approval

    line 78
  7. Distinctive:

    Create one PR per issue (not batch)

    line 79
  8. Distinctive:

    Run existing tests before creating PR

    line 80
  9. Distinctive:

    If fix is unclear, comment on the issue asking for clarification instead of guessing

    line 81

“Common” is measured: kept by at least 6 in 10 of the 35 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

GitHub Issues Auto-Fixer

Fetch GitHub issues, implement fixes, and open PRs — all automated.

Prerequisites

  • gh CLI installed and authenticated: brew install gh && gh auth login
  • Or: GH_TOKEN environment variable set

Process

1. Fetch Issues

# List open issues (default: bug label, limit 5)
gh issue list --repo <owner/repo> --label bug --limit 5 --json number,title,body,labels

2. For Each Issue

  1. Read the issue body and comments for reproduction steps
  2. Clone/navigate to the repo
  3. Create a feature branch: git checkout -b fix/issue-<number>
  4. Implement the fix (read code, understand context, make changes)
  5. Run tests if available
  6. Commit with message: fix: <description> (closes #<number>)
  7. Push and create PR:
gh pr create --repo <owner/repo> \
  --title "fix: <title>" \
  --body "Closes #<number>\n\n## Changes\n- <description>"

3. Monitor PRs (optional --watch flag)

# Check for review comments
gh pr view <number> --repo <owner/repo> --json reviewDecision,reviews,comments

Address review feedback and push updates.

Commands Reference

CommandPurpose
gh issue list --repo R --json number,title,bodyList open issues
gh issue view N --repo R --json body,commentsRead issue details
gh pr create --repo R --title T --body BCreate PR
gh pr view N --repo R --json reviews,commentsCheck PR reviews
gh pr merge N --repo R --squashMerge PR (with user approval)

Usage Examples

  • /gh-issues octocat/hello-world --label bug --limit 3
  • /gh-issues my-org/api --label "good first issue" --dry-run
  • /gh-issues owner/repo --watch (monitor and address PR reviews)

Rules

  • Always check if gh is installed first
  • Never merge PRs without explicit user approval
  • Create one PR per issue (not batch)
  • Run existing tests before creating PR
  • If fix is unclear, comment on the issue asking for clarification instead of guessing
  • Dry-run mode: show what would be done without making changes

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