skills.rest
ukwhatn
ukwhatnCOMMUNITY
Explore all skills by this author →
𝕏@ukwhatnGitHub

pr-review

Automate PR reviews with Claude Code and GPT-5.4-High-Fast.

3|2|Updated Jan 12, 2026
Search Tags:#architecture#github#quality-assurance#code-review#pr-review#multimodel
One-click install
npx skills add https://github.com/ukwhatn/.claude --skill pr-review-ukwhatn
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pr-review
Source: https://github.com/ukwhatn/.claude/tree/main/skills/pr-review
Command: npx skills add https://github.com/ukwhatn/.claude --skill pr-review-ukwhatn

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Streamlines and strengthens PR evaluations by orchestrating cross-model analyses (Claude Code and GPT-5.4-High-Fast) to surface design flaws, security concerns, and quality gaps during code reviews.

Core Features & Use Cases

  • Cross-model analysis: run parallel reviews with Claude Code and GPT-5.4-High-Fast to surface issues across changed files.
  • Consolidated reporting: merge findings into a single, severity-scored report with actionable remediation steps.
  • Policy-aware evaluation: adheres to architectural rules, naming conventions, and coding standards described in CLAUDE.md.
  • Decision support: outputs a structured summary suitable for code reviews, audits, and documentation updates.

Quick Start

Review the specified PR by number or branch and return a unified, severity-scored report.

Frequently Asked Questions about pr-review

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

FAQPage Schema
How do I automate GitHub PR reviews for architecture and security flaws?▼

Automate GitHub PR reviews by running parallel cross-model analyses using Claude Code and GPT-5.4-High-Fast to detect design flaws, security concerns, and quality gaps across changed files.

Can I use multiple AI models for code review to catch quality gaps?▼

Yes, you can use multiple AI models for code review by orchestrating Claude Code and GPT-5.4-High-Fast in parallel to surface diverse issues and merge findings into a consolidated report.

How does multimodel PR review enforce coding standards and naming conventions?▼

Multimodel PR review enforces coding standards and naming conventions by validating the diff against architectural rules and policies described in your CLAUDE.md configuration file.

What is the best way to consolidate AI code review feedback for triage?▼

Consolidate AI code review feedback for triage by merging multi-model findings into a single, severity-scored report that provides structured summaries and actionable remediation steps.

Do I need a CLAUDE.md file to perform automated code reviews?▼

Yes, a CLAUDE.md file is required to perform policy-aware automated code reviews, as it contains the architectural rules, naming conventions, and coding standards used to validate the PR diff.

When should I trigger an automated PR review on GitHub?▼

Trigger an automated PR review when a pull request is opened or updated, or when a formal review is requested, provided a diff or PR metadata is available for analysis.

Related Skills

Explore More Software Engineering Skills→
xinbenlvxinbenlv
8

retrieve-diff-from-github-pr

Retrieve GitHub Pull Request diffs and metadata for automated code reviews.

Community
Intermediate
florianbuetowflorianbuetow
12

integrity

Detects integrity vulnerabilities in code, CI/CD configs, and dependencies.

Community
Advanced
eliottbusinesseliottbusiness

requesting-code-review

Automate pre-commit code review with static analysis and security scanning.

Community
Advanced
LetPeopleWorkLetPeopleWork
16

code-review-checklist

Evaluate code plans and implementations against structured review criteria with severity levels.

Official
Basic