code-review-pr
Skill0 starsChanged 24 days agoMITView on GitHub
Review pull requests and code changes for correctness, security, API compatibility, missing tests and CI failures; inspect reviewer comments and GitHub checks before merge.
In this repository28 other files it gives its agents.
- agent-skill-security-auditorSkill
- backend-api-engineerSkill
- backend-debuggingSkill
- backup-disaster-recoverySkill
- database-transaction-integritySkill
- dependency-supply-chain-auditorSkill
- devops-ci-cdSkill
- documentation-handoverSkill
- frontend-design-directionSkill
- llm-api-integrationSkill
- load-resilience-testingSkill
- mcp-integration-builderSkill
- observability-monitoringSkill
- performance-accessibilitySkill
- playwright-webapp-testingSkill
- privacy-data-governanceSkill
- product-business-analystSkill
- project-bootstrap-environmentsSkill
- qa-release-gatekeeperSkill
- qa-test-strategySkill
- react-artifacts-builderSkill
- security-authorization-auditorSkill
- skill-authoring-toolkitSkill
- skill-evaluation-benchmarkSkill
- software-architectSkill
- technical-project-orchestratorSkill
- theme-design-systemSkill
- visual-assets-designSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use when an actual diff, PR, merge request, or requested code review exists.
- Distinctive: line 14
Verify that requested changes are within scope, relevant test coverage exists, and required CI gates have actually completed.
- Distinctive: line 16
When asked to fix, implement narrow changes on an authorized branch and repeat targeted tests and review.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Evidence-based PR and code review
Use when an actual diff, PR, merge request, or requested code review exists; do not imply a PR exists because a branch exists.
- Identify target repository, base/head, exact diff and user-approved scope; read applicable AGENTS.md/ADRs and functional acceptance criteria.
- Inspect changed code and its callers for behavior regressions, missing server-side authorization, race conditions, schema/API compatibility, performance and observability impacts.
- Where GitHub CLI is authorized, run the repo's read-only
scripts/pr_review_report.py --repo OWNER/REPO --pr Nand inspect reviews, inline and general comments, and CI check status. For other hosts use equivalent authenticated read-only tools. - Identify findings with severity, path and line, triggering scenario, impact and concrete correction; separate confirmed defects from hypotheses.
- Verify that requested changes are within scope, relevant test coverage exists, and required CI gates have actually completed. Do not infer that all review threads are resolved from a mere list of comments.
- Recommend a merge verdict: READY, NEEDS CHANGES, or INSUFFICIENT EVIDENCE. Do not merge, push, dismiss reviews, or resolve threads without authorization.
- When asked to fix, implement narrow changes on an authorized branch and repeat targeted tests and review.
Handoff to database-transaction-integrity for concurrency/schema changes; security-authorization-auditor for privilege surfaces; qa-release-gatekeeper for release decision.
Output: PR SHA/base, evidence table (severity, file:line, effect, fix), CI/review summary, missing tests and verdict. If tools/data unavailable, report NOT CHECKED rather than PASS.
Execution dependency
The optional pr_review_report.py helper lives in the source repository's scripts/ folder, not inside this installed SKILL.md folder. If the source checkout and authenticated GitHub CLI are available, run that helper from the checkout. Otherwise use documented read-only gh pr view, gh api and actual diff review, or mark evidence NOT CHECKED. Do not download or execute remote scripts as a shortcut.
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
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.