PluginBench
Skill
Fail
Audit score 45

gh-issues

steipete/clawdis

Automate GitHub issue triage and PR creation with background fix agents.

What is gh-issues?

Fetches GitHub issues, filters by label/milestone/assignee, spawns background agents to implement fixes, opens PRs, and optionally processes review comments. Use this to automate issue-to-PR workflows at scale with optional watch/cron modes for continuous operation.

  • Fetch and filter GitHub issues by label, milestone, assignee, or state
  • Spawn up to 8 background fix agents per batch to implement solutions
  • Automatically open PRs against source repo with conventional commit messages
  • Process PR review comments and spawn review workers for actionable feedback
  • Support fork-based workflows with automatic remote configuration
  • Watch mode for continuous polling and processing with configurable intervals

How to install gh-issues

npx skills add https://github.com/steipete/clawdis --skill gh-issues
Prerequisites
  • GitHub CLI (gh) installed and authenticated with GH_TOKEN or gh auth
  • Git installed and configured
  • Write access to source repository (or fork for fork-based workflows)
  • Coding agent runtime (e.g., Claude Code, Cursor) to execute worker tasks
Claude Code
Cursor
Windsurf
Cline

How to use gh-issues

  1. 1.Run `npx skills add https://github.com/steipete/clawdis --skill gh-issues` to install
  2. 2.Authenticate with GitHub: `gh auth login` or set GH_TOKEN environment variable
  3. 3.Run `gh-issues owner/repo` to fetch and process open issues (or omit repo to infer from git remote)
  4. 4.Use `--label`, `--milestone`, `--assignee` flags to filter candidates
  5. 5.Confirm issue selection when prompted, or use `--yes` to skip confirmation
  6. 6.Monitor background workers; PRs will be created automatically with fix branches named `fix/issue-<n>`
  7. 7.Use `--watch --interval 5` for continuous polling, or `--cron` for scheduled execution

Use cases

Good for
  • Automate triage of bug reports by spawning fix agents for labeled issues
  • Run scheduled cron jobs to process open issues and convert them to PRs overnight
  • Monitor PRs for review feedback and spawn agents to address comments automatically
  • Manage contributions to forks with automatic branch and PR creation against upstream
  • Batch-process issues with specific milestones or assignees during sprint planning
Who it's for
  • DevOps engineers automating issue resolution workflows
  • Open-source maintainers managing high-volume issue queues
  • Development teams using GitHub for project management
  • CI/CD pipeline builders integrating issue-to-PR automation

gh-issues FAQ

How do I use this with a fork instead of pushing directly to the source repo?

Pass `--fork owner/fork-repo` to configure the push remote. The skill will add/update the fork remote and open PRs against the source repo from your fork branches.

What happens if an issue already has an open PR or branch?

The skill skips candidates with existing open PRs, branches named `fix/issue-<n>`, or active claims (less than 2 hours old) to avoid duplicate work.

Can I process only PR reviews without fixing issues?

Yes, use `--reviews-only` to skip issue fixing and only handle actionable comments on existing PRs. Use `--watch` to continuously poll for new reviews.

What if I want to run this on a schedule?

Use `--cron` to spawn workers and exit immediately without blocking. Combine with a system cron job or GitHub Actions workflow to run at intervals.

How do I customize the model used by worker agents?

Pass `--model <id>` (e.g., `claude-opus`) to forward the model preference to workers when supported by your agent runtime.

Full instructions (SKILL.md)

Source of truth, from steipete/clawdis.


name: gh-issues description: "Fetch GitHub issues, select candidates, spawn background fix agents, open PRs, and optionally process PR review comments." user-invocable: true metadata: { "openclaw": { "requires": { "bins": ["git", "gh"] }, "primaryEnv": "GH_TOKEN", "install": [ { "id": "brew", "kind": "brew", "formula": "gh", "bins": ["gh"], "label": "Install GitHub CLI (brew)", }, ], }, }

gh-issues

Use for issue-to-PR automation. Prefer gh CLI; fall back to gh api only when a high-level command lacks the needed field.

Arguments

  • positional owner/repo: optional; else infer from git remote get-url origin.
  • --label <label>: filter.
  • --limit <n>: default 10.
  • --milestone <title>: filter.
  • --assignee <login|@me>: filter.
  • --state open|closed|all: default open.
  • --fork <owner/repo>: push branches to fork, PR to source.
  • --watch: poll issues + reviews.
  • --interval <minutes>: default 5.
  • --dry-run: list only.
  • --yes: no confirmation.
  • --reviews-only: skip issue fixing; handle PR reviews.
  • --cron: spawn and exit; implies --yes.
  • --model <id>: pass to workers when supported.
  • --notify-channel <id>: optional final notification target.

Phase 1: resolve repo

git remote get-url origin
if [ -z "${GH_TOKEN:-}" ]; then
  CONFIG_PATH="${OPENCLAW_CONFIG_PATH:-${OPENCLAW_STATE_DIR:-$HOME/.openclaw}/openclaw.json}"
  GH_TOKEN=$(jq -r '.skills.entries["gh-issues"].apiKey // empty' "$CONFIG_PATH" 2>/dev/null || true)
  if [ -n "$GH_TOKEN" ]; then export GH_TOKEN; fi
fi
gh auth status
gh repo view OWNER/REPO --json nameWithOwner,defaultBranchRef

If gh auth status fails and GH_TOKEN is missing, stop and ask for GitHub auth/config.

Derived:

  • SOURCE_REPO: issue repo.
  • PUSH_REPO: fork if set, else source.
  • BASE_BRANCH: source default branch unless user says otherwise.
  • PUSH_REMOTE: fork in fork mode, else origin.

Stop on dirty worktree unless user confirms that workers should ignore uncommitted changes.

In fork mode, do not mutate remotes before confirmation or during --dry-run.

Verify auth/read access only:

gh auth token >/dev/null || test -n "${GH_TOKEN:-}"
gh repo view "$PUSH_REPO" --json nameWithOwner
git ls-remote --exit-code origin HEAD

Phase 2: fetch issues

Build filters and fetch:

gh issue list --repo "$SOURCE_REPO" --state open --limit 10 --json number,title,labels,url,body,assignees,milestone

Add --label, --milestone, --assignee, --state, --limit as requested. gh issue list already excludes PRs.

If none found: report no matches. If --dry-run: show compact list and stop.

Phase 3: avoid duplicate work

For each candidate:

gh pr list --repo "$SOURCE_REPO" --search "$SOURCE_REPO#<n>" --state open --json number,url,title,headRefName
gh pr list --repo "$SOURCE_REPO" --head "fix/issue-<n>" --state open --json number,url
gh api "repos/$PUSH_REPO/branches/fix/issue-<n>" >/dev/null

Skip candidates with an open PR, existing branch, or active local claim.

Claim file:

${OPENCLAW_STATE_DIR:-$HOME/.openclaw}/gh-issues-<owner>-<repo>.json

Expire claims older than 2 hours. Create the parent directory before writing.

Phase 4: confirm

Unless --yes or --cron, ask user to choose:

  • all
  • comma-separated issue numbers
  • cancel

After confirmation, in fork mode, configure the push remote before handing work to agents:

gh auth setup-git
git remote get-url fork || git remote add fork "https://github.com/$PUSH_REPO.git"
git remote set-url fork "https://github.com/$PUSH_REPO.git"
git ls-remote --exit-code fork HEAD

Phase 5: spawn workers

Launch up to 8 background workers. Do not block on each worker when --cron.

Before each spawn, write a claim for SOURCE_REPO#<n> with the current ISO timestamp. After a worker reports PR/failure, remove or update the claim. This prevents watch/cron overlap before a branch or PR exists.

Worker prompt must include:

  • issue URL, title, body, labels.
  • SOURCE_REPO, PUSH_REPO, BASE_BRANCH, PUSH_REMOTE, fork mode.
  • target branch fix/issue-<n>.
  • required proof and PR body.
  • notification route.

Worker instructions:

Use gh and git. Do not handwave.
Checkout/create fix/issue-<n> from BASE_BRANCH.
Implement minimal fix.
Run relevant tests.
Commit with conventional message.
Push to PUSH_REMOTE.
Open PR against SOURCE_REPO BASE_BRANCH.
PR body: What Problem This Solves + Why This Change Was Made + User Impact + Evidence + visible Fixes SOURCE_REPO#<n>.
Report PR URL or failure reason.
Send completion/failure with openclaw message send if route provided.

Use coding-agent launch rules when available.

Phase 6: collect

Poll workers with process or task registry. Report:

  • issue number + title.
  • status: PR opened, skipped, failed, timed out.
  • PR URL or reason.

Notify channel only with final compact summary.

Reviews-only / watch reviews

Discover open PRs:

gh pr list --repo "$SOURCE_REPO" --state open --json number,title,url,headRefName,reviewDecision \
  --jq '[.[] | select(.headRefName | startswith("fix/issue-"))]'

Fetch review threads/comments:

gh pr view <n> --repo "$SOURCE_REPO" --json url,headRefName,comments,reviews
gh api "repos/$SOURCE_REPO/pulls/<n>/comments"
gh api "repos/$SOURCE_REPO/issues/<n>/comments"

Only process fix/issue-* PRs created by this workflow unless the user explicitly named PR numbers. Group actionable comments by PR. Ignore praise, status, duplicates, and already-addressed comments. Spawn one worker per selected/scoped PR, same background rules.

Review worker instructions:

Checkout PR branch.
Read all actionable review comments.
Patch minimal changes.
Run relevant tests.
Commit and push normally; do not force-push unless explicitly told.
Reply to addressed comments with fix + commit/file reference.
Report comments addressed/skipped and proof.

Watch mode

Loop:

  1. Fetch issues.
  2. Spawn eligible issue workers.
  3. Process actionable PR reviews.
  4. Sleep --interval.
  5. Stop when user says stop.

Keep cumulative summary small.