.pi/skills/review-contributor-pr/SKILL.md
Review and manage pull requests from external contributors. Use when checking out, reviewing, editing, or merging a PR from a fork.
npx skillsauth add aliou/pi-extensions review-contributor-prInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Contributors submit PRs from their forks. To push changes back (commit message fixes, minor tweaks), add their fork as a remote:
# Extract fork owner from PR (visible in gh pr view or the PR URL)
git remote add <owner> [email protected]:<owner>/pi-harness.git
git fetch <owner>
git checkout <owner>/<branch> -b <branch>
This works when the contributor has "Allow edits from maintainers" enabled (GitHub default).
To push amended commits back:
git push <owner> <local-branch>:<remote-branch> --force-with-lease
main and is rebased on current main (no merge conflicts).This repo uses conventional commits with scopes. Every commit must match:
<type>(<scope>): <description>
Common types: feat, fix, chore, perf, refactor, docs, test.
Scopes match directory names: scout, lookout, breadcrumbs, subagents, defaults, qq, palette, etc.
If commits don't follow this format, amend them (keep original author, set yourself as committer).
Run locally before merging:
pnpm typecheck
pnpm lint
pnpm test
All checks must pass.
Prefer fast-forward merge to keep linear history:
git checkout main
git merge <branch> --ff-only
git push origin main
If fast-forward fails, rebase the branch on main first.
After merge, clean up the local branch:
git branch -d <branch>
tools
Create specialized subagents within the subagents extension. Use when asked to create a new subagent like scout, librarian, oracle, etc.
testing
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".
testing
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).
testing
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".