pr-review · proffesor-for-testing — Claude Code skill: PR review and setup
The pr-review skill reviews GitHub PRs for scope, trust-tier assignments, code quality, and security. Use it to prepare clear feedback with actionable next steps.
MIT 155 installs ★ 533 updated 2026-10-25
npx skills add proffesor-for-testing/agentic-qe --skill pr-review -a claude-codeWhat pr-review does
The skill reads the full diff and PR description with gh pr diff and gh pr view, then checks whether the changes fit the AQE/QE scope. Claude Flow platform skills are excluded from that scope, and their changes in an AQE-focused PR should be flagged. The workflow calls for reading every changed file.
For modified skills, it checks trust_tier against the available evaluation setup: evals/, schemas/, or scripts/ indicate tier 3; tested skills without an eval framework map to tier 2; untested skills map to tier 1. It also checks hardcoded version strings, production risks, missing test coverage, and security issues. The review should focus on outcomes and author actions. You can post it with gh pr review.
What it helps with
- read the full PR diff and description before reviewing
- spot platform-skill changes in an AQE-focused PR
- check
trust_tieragainst evaluation infrastructure - find security concerns and missing test coverage
- draft actionable feedback for the PR author
Example prompts for the agent
- Review PR
42: read the complete diff and description, then check whether its changes fit AQE/QE scope. - Compare the changed skills’
trust_tiervalues with their evaluation setup and report mismatches. - Check this PR for hardcoded versions, production risks, test gaps, and security issues; draft constructive feedback.
How to install pr-review
1Skills CLI (Vercel)
npx skills add proffesor-for-testing/agentic-qe --skill pr-review -a claude-code2Manually: put the files in place
~/.claude/skills/pr-review/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/pr-review/
1Skills CLI (Vercel)
npx skills add proffesor-for-testing/agentic-qe --skill pr-review -a codex2Manually: put the files in place
.agents/skills/pr-review/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add proffesor-for-testing/agentic-qe --skill pr-review -a cursor2Manually: put the files in place
.cursor/skills/pr-review/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install proffesor-for-testing/agentic-qe assets/skills/pr-review2Manually: put the files in place
.github/skills/pr-review/SKILL.md1Skills CLI (Vercel)
npx skills add proffesor-for-testing/agentic-qe --skill pr-review -a gemini-cli2Platform CLI
gemini skills install https://github.com/proffesor-for-testing/agentic-qe --path assets/skills/pr-reviewManually: put the files in place
.devin/skills/pr-review/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add proffesor-for-testing/agentic-qe --skill pr-review -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about pr-review
How do I install pr-review in Claude Code?
Run npx skills add proffesor-for-testing/agentic-qe --skill pr-review -a claude-code. The skill file is at ~/.claude/skills/pr-review/SKILL.md.
What does pr-review do?
It checks GitHub PR scope, trust_tier assignments, code quality, and security, then helps produce feedback focused on concrete changes for the author.
How does pr-review validate trust tiers?
It maps evaluation files such as evals/, schemas/, or scripts/ to tier 3, tested skills without an eval framework to tier 2, and untested skills to tier 1.
Source text
SKILL.md · MIT
--- name: pr-review description: "Use when reviewing a GitHub PR for quality, scope correctness, trust tier compliance, or generating user-friendly review feedback." trust_tier: 0 domain: code-review --- # PR Review Workflow Review pull requests with correct AQE scope boundaries, clear communication, and actionable feedback. ## Arguments - `<pr-number>` — GitHub PR number to review. If omitted, prompt the user. ## Steps ### 1. Read the Full Diff ```bash gh pr diff <pr-number> gh pr view <pr-number> ``` Read the complete diff and PR description. Do not skim — read every changed file. ### 2. Scope Check - Only analyze AQE/QE skills (NOT Claude Flow platform skills) - Platform skills to EXCLUDE: v3-*, flow-nexus-*, agentdb-*, reasoningbank-*, swarm-*, github-*, hive-mind-advanced, hooks-automation, iterative-loop, stream-chain, skill-builder, sparc-methodology, pair-programming, release, debug-loop - If the PR touches skills, verify the count/scope matches expectations (~82 AQE skills) - Flag any platform skill changes that may have leaked into an AQE-focused PR ### 3. Summarize Changes Write a user-friendly summary of what changed and why: - Focus on outcomes, not implementation details - Avoid overly technical jargon - Keep it to 3-5 bullet points ### 4. Trust Tier Validation For any skill changes, validate trust_tier assignments: - **tier 3** = has eval infrastructure (evals/, schemas/, scripts/) - **tier 2** = tested but no eval framework - **tier 1** = untested - Flag inconsistencies (e.g., a skill with evals at tier 2 should be tier 3) ### 5. Code Quality Review Check for: - Hardcoded version strings - Production safety concerns (adapter changes, breaking changes) - Missing test coverage for new code - Security issues (exposed secrets, injection risks) ### 6. Post Review ```bash gh pr review <pr-number> --body "review comments" ``` ## Communication Rules - Keep tone constructive and actionable - Be outcome-focused: what should the author do, not what's wrong - Group related comments together instead of posting many small ones - If approving with minor suggestions, use APPROVE with comments, not REQUEST_CHANGES
© proffesor-for-testing · MIT · proffesor-for-testing/agentic-qe
Similar skills
All skills for Code review and refactoring →pr-review by other authors comes first.