pr-review
Performs targeted reviews of PyTorch PRs, focusing on aspects that standard CI pipelines often miss.
Install
mkdir -p .claude/skills/pr-review && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/929" && unzip -o skill.zip -d .claude/skills/pr-review && rm skill.zipInstalls to .claude/skills/pr-review
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Review PyTorch pull requests for code quality, test coverage, security, and backward compatibility. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".Key capabilities
- →Fetch PR metadata and file diffs using GitHub CLI
- →Generate line-by-line review comments for local branches
- →Summarize branch changes compared to main
- →Analyze commit logs for branch scope identification
How it works
Interrogates repository state using git diffs and gh CLI to compare current changes against the main branch branch before generating feedback.
Inputs & outputs
When to use pr-review
- →Reviewing a specific PR number for code quality
- →Checking local branch changes before pushing
- →Generating line-by-line comments for a code review
About pr-review
This skill assists in reviewing code changes, focusing on architectural quality, security vulnerabilities, and backward compatibility. It processes PR numbers or local branches to provide detailed, actionable feedback.
Review PyTorch pull requests for code quality, test coverage, security, and backward compatibility. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".
When not to use it
- →When the user is not working on a PyTorch-compatible codebase
- →For reviewing non-code documents or configuration files exclusively
Prerequisites
Limitations
- →Requires established git history and main branch tracking
- →Needs network access to GitHub via CLI
How it compares
It focuses on CI-untestable metrics like architectural quality and backward compatibility rather than just syntax checking.
Compared to similar skills
pr-review side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| pr-review (this skill) | 6 | 5mo | Review | Intermediate |
| django-verification | 5 | 7mo | Review | Intermediate |
| lint-and-validate | 6 | 10mo | Review | Beginner |
| moai-foundation-quality | 0 | 6mo | No flags | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by pytorch
View all by pytorch →You might also like
django-verification
affaan-m
Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.
lint-and-validate
davila7
Automatic quality control, linting, and static analysis procedures. Use after every code modification to ensure syntax correctness and project standards. Triggers onKeywords: lint, format, check, validate, types, static analysis.
moai-foundation-quality
modu-ai
Enterprise code quality orchestrator with TRUST 5 validation, proactive analysis, and automated best practices enforcement
s-lint
Falkicon
>
code-quality-enforcer
T-rav
>
verification-loop
tom237ttkk
A comprehensive verification system for Codex work sessions.