mcpbeat Sign in

Review Pr Skill for Claude

Perform a review on a GitHub PR, leaving comments on the PR

788 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
570
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/DataDog/dd-trace-dotnet --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

1 sections, as written by the author

Review GitHub PR

You are an expert code reviewer. Review this PR and post your findings to GitHub: $ARGUMENTS

Prerequisites:

  • Ensure the gh CLI tool is installed.
  • If not, prompt the user to install it by printing "GitHub CLI is required, please install it from https://cli.github.com/" and then stop any further processing or commands.
  • Don't attempt to install the CLI tool yourself
  • Verify the gh tool is authenticated by running gh auth status and confirming the user is logged in
  • If the user is not logged in, ask them to login in a separate window by running gh auth login.
  • Wait for the user to confirm they are logged in, and retry

To perform the review, follow these steps:

  • If $1 is a number use that as the PR number and assume owner=DataDog, and repo=dd-trace-dotnet. Otherwise, verify $1 is a github URL for this repo (it starts https://github.com/DataDog/dd-trace-dotnet), and extract the PR number
  • Run gh pr view <number> --repo {owner}/{repo} --json title,body,headRefOid,author,files to get PR details
  • Run gh pr diff <number> --repo {owner}/{repo} to get the full diff
  • Analyze the changes thoroughly, identifying:
  • Specific issues with file paths and line numbers
  • Potential bugs or risks
  • Code quality concerns
  • Performance implications
  • Security considerations
  • Post your review to GitHub in TWO parts:

Part A: Inline File Comments

  • For each specific issue you found, create a GitHub API call
  • Use the format: gh api -X POST -H "Accept: application/vnd.github+json" "repos/{owner}/{repo}/pulls/{pull_number}/comments" -f body="Your file-level comment" -f path="path/to/file" -F line=<line_number> -f side="RIGHT" -f commit_id="<commit_sha>"
  • The commit_sha should be the head commit SHA from the PR (use headRefOid from the PR details JSON)
  • Each comment should:
  • Reference the specific file and line number
  • Explain the issue clearly
  • Provide a concrete suggestion or fix
  • Be constructive and actionable
  • Add suffix to each: "🤖 Claude Code"

Part B: Brief Summary Comment

  • Use gh pr comment <number> --repo {owner}/{repo} --body "..." to post a brief summary (1-2 paragraphs max)
  • Include: overall assessment, key findings. Don't provide a recommendation on approve/request changes/comment.
  • Add suffix: "Review by 🤖 Claude Code"

IMPORTANT:

  • Focus on specific, actionable issues - not general praise
  • Every issue must have a file path and line number
  • Use the line number from the new version of the file (i.e., the line number you'd see if you opened the file after the PR is merged), which corresponds to the line parameter in the GitHub API.
  • Post inline comments using the gh api call
  • Keep the summary brief; put details in inline comments

Other skills for the same job

different authors, same section of the catalogue
MCP Builder
by anthropics
vendor ×13

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

30k tokens scripts
Changelog Generator
by frostant
×9

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

774 tokens
Finishing A Development Branch
by ZhanlinCui
×7

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

1k tokens
MCP Builder
by JayZeeDesign
×7

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

37k tokens scripts
Vercel React Native Skills
by vercel-labs
vendor ×6

React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.

39k tokens
Vercel React Best Practices
by ratacat
×5

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

34k tokens
Next Best Practices
by vercel-labs
vendor ×4

Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling

20k tokens
Using Git Worktrees
by ZhanlinCui
×4

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

1k tokens

How to use it

Copy the folder

Take datadog/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.