mcpbeat Sign in

Review Pr Agent Skill

> Review a Site Kit GitHub pull request end-to-end against the project's conventions and quality rubric. Use when the user asks to review, critique, or give feedback on a pull request by number (e.g. "review PR #12345", "review pull request 12345", "/review-pr 12345") in the google/site-kit-wp repo.

601 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
1393
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/google/site-kit-wp --skill review-pr

What it tells the agent to use

found in the instruction text
Bash runs shell commands — read the instruction before connecting

The instruction itself

3 sections, as written by the author

Review a pull request

Review pull request #$ARGUMENTS (if no number was given, ask for one) by following the

project's shared playbook. Do not reimplement the procedure here — read and follow the

playbook, which is the single source of truth shared with the other AI tools.

Procedure

  • Read the playbook docs/context/workflow/review-pr.md and follow every step: fetch the

PR data, read the linked issue, load only the relevant docs/context/{js,php} convention

docs (per the scope map), inspect the changed files, judge against the checklist, and produce

the structured review.

  • Fetch the PR: run gh pr view $ARGUMENTS --json number,title,body,author,baseRefName,headRefName,files,additions,deletions,commits

and gh pr diff $ARGUMENTS in parallel. Stop and ask the user if the PR is missing or the

diff is empty.

  • Read the linked issue: the PR body (per .github/PULL_REQUEST_TEMPLATE.md) links it

under "Addresses issue: - #<number>". Extract that number, run

gh issue view <number> --json title,body,labels, and parse its Acceptance criteria,

Implementation Brief, and Test Coverage — this is the spec the PR must satisfy. If no issue

is linked, note it and review conventions + code quality only.

  • Grade the change against docs/context/workflow/review-checklist.md — requirements

adherence (against the issue) first, then conventions, code quality, and verification —

citing the context file + section for every deviation.

  • Output the review in the exact structure defined by the playbook (Summary → Requirements

Adherence → Principles Compliance → Code Quality → Security → Performance → Test Coverage →

Nits → Verdict).

Important

  • Read-only: produce the review only. Never post comments, approve, or change the PR state

on GitHub unless the user explicitly asks.

  • Load only the convention docs the change touches — read what the PR touches, not everything.

Other skills for the same job

different authors, same section of the catalogue
Receiving Code Review
by ZhanlinCui
×7

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

2k tokens
Requesting Code Review
by ZhanlinCui
×6

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

2k tokens
Git Commit
by github
vendor ×3

Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping

799 tokens
Github Code Review
by ComeOnOliver
×3

Comprehensive GitHub code review with AI-powered swarm coordination

13k tokens
Karpathy Guidelines
by hyyhf
×3

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

629 tokens
Code Reviewer
by google-gemini
vendor ×2

Use this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability, and adherence to project standards.

795 tokens
Agent MD Refactor
by softaworks
×2

Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.

4k tokens
Commit Work
by softaworks
×2

Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.

2k tokens

How to use it

Copy the folder

Take google/review-pr from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.