Skip to content
TrustedSkillsbeta
Back to all skills

Pr Review

Official
pytorch·vlatest·ai-ml

Analyzes PyTorch pull requests, identifying potential issues like style violations, test failures, and performance bottlenecks.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add pytorch/pytorch --skill pr-review -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

pytorch

Matched to the vendor's own GitHub organisation.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned pytorch/pytorch at edd4fc2d34.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
edd4fc2d34
Manifest
.claude/skills/pr-review/SKILL.md
Scanned
3 files, 711 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The Pr Review skill analyzes PyTorch pull requests to identify potential issues that standard CI systems might miss. It focuses on code quality, test coverage adequacy, security vulnerabilities, and backward compatibility. The skill can operate in different modes (local CLI, local branch, or GitHub Actions) depending on how it's invoked and the available context.

When to use it

  • Reviewing a specific pull request: When you need an expert opinion on a PyTorch PR before merging.
  • Evaluating changes in a local branch: To ensure code quality and identify potential issues before creating a pull request.
  • Automated review within GitHub Actions: For automated checks during the pull request workflow, leveraging pre-fetched metadata.

Key capabilities

  • Analyzes PyTorch pull requests for various issues (code quality, security, etc.).
  • Supports reviewing PRs by number or URL.
  • Provides detailed line-by-line comments when requested.
  • Can review changes in a local branch compared to the main branch.
  • Operates in different modes: Local CLI, Local Branch, and GitHub Actions.
  • Leverages git commands for diffs and commit history (in certain modes).

Example prompts

  • /pr-review 12345 - Review pull request number 12345.
  • /pr-review https://github.com/pytorch/pytorch/pull/12345 detailed - Perform a detailed review of the specified pull request.
  • /pr-review branch - Review changes in the current local branch compared to main.

Tips & gotchas

  • When invoked without arguments, the skill will prompt you for input (PR number or URL).
  • In GitHub Actions mode, only git commands are available; the skill automatically receives PR metadata and comments.
  • The "Summary" for local branch reviews describes what the changes accomplish based on commit messages and diffs.