Skip to content
/pr-reviewBeta

Comprehensive pull request review using specialized agents for code, tests, types, and silent failures.

QualityCollaboration· 1 min read

Quick import: Download the .md file and save it to .claude/commands/ (Claude Code), .cursorrules (Cursor), or paste as a system prompt in ChatGPT, Gemini, or any LLM API.

#What it does

The /pr-review skill performs a comprehensive pull request review by deploying multiple specialized agents in parallel.

#How to use

bash
/pr-review 123

Where 123 is the PR number.

#Specialized agents

The skill runs these agents concurrently:

  1. Code Reviewer — Bugs, logic errors, security issues, style violations
  2. Silent Failure Hunter — Catch blocks that swallow errors, inadequate fallbacks
  3. Test Analyzer — Test coverage gaps, missing edge cases
  4. Type Design Analyzer — Type safety, proper encapsulation, invariant expression
  5. Comment Analyzer — Comment accuracy, potential comment rot

#Output

Each agent reports independently with confidence-filtered findings. Only high-priority issues are surfaced — no noise.

#When to use

  • Before merging any PR
  • After receiving review feedback to verify fixes
  • When reviewing someone else's contribution
Orel Ohayon·
View all skills