.agents/skills/pr-review/SKILL.md
Review a Pull Request for code quality, tests, and merge readiness. Use when reviewing PRs, checking for merge conflicts, or providing feedback before merging.
npx skillsauth add agentjido/req_llm pr-reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
4 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Review this Pull Request: <url>
This skill is for review-only work. Prefer gh pr checkout <number> --detach so disposable local branches do not accumulate.
Analyze the quality of the code, the tests and the overall change. Check for merge conflicts with main, advise on fixes if a conflict exists.
Prioritize findings:
mainWhen the review is complete, update the PR review-state label on GitHub:
ready_to_merge and remove needs_work when there are no blocking findings, the PR is merge-clean, and GitHub CI is greenneeds_work and remove ready_to_merge when blocking findings remain, coverage is insufficient for the risk, merge conflicts exist, or GitHub CI is failingUse:
gh pr edit <number> --add-label ready_to_merge --remove-label needs_work
gh pr edit <number> --add-label needs_work --remove-label ready_to_merge
Give me feedback on the PR and whether it is ready to merge.
If asked to give feedback on the PR, do so with a terse response in a encouraging, warm and friendly tone. Be appreciative of the work and the effort put into the PR.
testing
Take a pull request labeled needs_work, address blocking review findings, strengthen test coverage, rerun validation, and flip it to ready_to_merge when it is clean.
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.