review

Orchestrates automated code review agents for pull request analysis and fixes.

Updated Feb 26, 2026
One-click install
npx skills add https://github.com/Ouaish-Labs/ouaish.com --skill review-ouaish-labs
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/Ouaish-Labs/ouaish.com/tree/main/.claude/skills/review
Command: npx skills add https://github.com/Ouaish-Labs/ouaish.com --skill review-ouaish-labs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Manual pull request reviews are slow and inconsistent, often missing silent failures, test coverage gaps, and type design issues. This Skill automates multi-agent code review so every PR gets systematic scrutiny before merge. ## Core Features & Use Cases - Automated Review Loop: Runs code-reviewer, silent-failure-hunter, and pr-test-analyzer agents automatically after a PR is posted, with a fixer agent addressing findings across up to 3 rounds. - Specialized Review Agents: Six agents covering CLAUDE.md compliance, error handling, code simplification, type design, test coverage, and comment accuracy, runnable in parallel. - Finding Triage and Issue Creation: Categorizes findings as Critical, Important, or Suggestions, posts them via gh pr review, and creates GitHub issues for high-confidence bugs and test gaps. - Use Case: After pushing a branch and opening a PR, the review agents automatically analyze the diff, post categorized findings with file:line references, and a fixer agent resolves critical issues before you merge. ## Quick Start Ask the assistant to review pull request 42 using the pr-review-toolkit review workflow with tests and error analysis enabled.

Frequently Asked Questions about review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run an automated code review on a GitHub pull request?▼

Run the review-pr command with the PR number, optionally adding flags like tests, errors, all, or parallel. The workflow dispatches code-reviewer, silent-failure-hunter, and pr-test-analyzer agents, then posts categorized findings to the PR.

What review agents are available for pull request analysis?▼

Six agents are available: code-reviewer for general compliance, silent-failure-hunter for error handling, code-simplifier for duplication, type-design-analyzer for type safety, pr-test-analyzer for coverage gaps, and comment-analyzer for documentation accuracy.

Do I need to manually run review after creating a PR with worktree-pr?▼

No. When using the worktree-pr workflow, review agents run automatically as a built-in phase after the PR is posted. A fixer agent then addresses findings across up to three rounds without manual intervention.

Can review agents run in parallel instead of sequentially?▼

Yes. Independent agents like code-reviewer, silent-failure-hunter, and type-design-analyzer should be dispatched in a single message with multiple agent calls. Sequential execution wastes time without improving results.

What happens to issues found during automated code review?▼

Findings are categorized as Critical, Important, or Suggestions and posted to the PR with file:line references. High-confidence bugs and test coverage gaps can be converted into GitHub issues using the gh issue create command.