Skill11.2k repo starsupdated today
pr-review-triage
The pr-review-triage skill automates pull request assessment by evaluating CI status, review approvals, blocking comments, and merge readiness for each watched PR. Use this skill to quickly triage multiple PRs, identify blockers, flag security or breaking-change risks for human escalation, and route straightforward fixes through automated loops while flagging stalled or high-risk reviews for manual intervention.
Install in Claude Code
Copygit clone --depth 1 https://github.com/cobusgreyling/loop-engineering /tmp/pr-review-triage && cp -r /tmp/pr-review-triage/starters/pr-babysitter/.grok/skills/pr-review-triage ~/.claude/skills/pr-review-triageThen start a new Claude Code session; the skill loads automatically.
Definition
SKILL.md
# PR Review Triage Skill For each watched PR, report: ## Per-PR Output ```markdown ### PR #N — title - Checks: passing | failing | pending | absent/unknown — list names and conclusions - Required-check policy: known and satisfied | known and unsatisfied | unknown - Reviews: approved N | changes requested | review required | absent/unknown - Mergeability: clean | conflicts | unknown - Blocking comments: (list actionable ones) - Ready to merge: yes | no — reason - Suggested loop action: none | minimal-fix | rebase | escalate-human ``` ## Rules - Zero checks, or no check runs/status contexts returned, means `absent/unknown`, not `passing`, unless the repository policy explicitly requires no checks. - Separate functional CI from administrative statuses such as a CLA or labeler; list both, but do not use administrative success as evidence that tests passed. - `mergeable` or a clean merge state only means Git found no conflict. It does not mean the PR is ready, reviewed, or verified. - "Ready to merge" requires a known project policy, every required check satisfied, required approvals present, no changes requested, no blocking comments, and no merge conflict. - If the required-check or review policy cannot be established, report `Ready to merge: no` and escalate to a human. - Non-actionable nits → note but do not spawn fix. - If PR idle >4 days → suggest human handoff. - High-risk labels (security, breaking) → escalate-human always.
More from this repository
loop-budgetSkill
Check token budget and run-log spend before and after a loop run. Enforces early exit when over budget or when there is no actionable work.
loop-triageSkill
>
loop-verifierSubagent
Independent checker for loop-produced changes. Rejects unless tests pass and scope is minimal. Never implement fixes.
minimal-fixSkill
>
changelog-scanSkill
>
draft-release-notesSkill
>
ci-triageSkill
>
dependency-triageSkill
>