skills.rest
orban
orbanCOMMUNITY
Explore all skills by this author →
Website𝕏@ryanorbanGitHub

pr-review

Review PRs against Intent Layer contracts and pitfalls with risk scoring.

8|1|Updated Jan 21, 2026
Search Tags:#checklist#review#pr#contract#risk#ai-generated
One-click install
npx skills add https://github.com/orban/intent-layer --skill pr-review-orban
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pr-review
Source: https://github.com/orban/intent-layer/tree/main/skills/intent-layer/pr-review
Command: npx skills add https://github.com/orban/intent-layer --skill pr-review-orban

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Review PRs against the Intent Layer contracts and pitfalls to assess risk.

Core Features & Use Cases

  • Contract & Pitfall Verification: Automates checks to ensure PRs respect defined invariants, contracts, and potential pitfalls.
  • Risk Scoring & Checklists: Generates a risk score and actionable checklists for reviewers.
  • Workflow Automation: Supports AI-generated and human PRs with base/head references to streamline code review processes in CI/CD.

Quick Start

Use the pr-review script to start a review: scripts/review_pr.sh main HEAD scripts/review_pr.sh main HEAD --ai-generated scripts/review_pr.sh main HEAD --pr 123 --ai-generated

Frequently Asked Questions about pr-review

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

FAQPage Schema
How do I review a pull request for contract violations and risk?▼

Review a pull request for contract violations by running the review_pr.sh script with base and head references. It checks PRs against Intent Layer contracts and pitfalls, then outputs a structured review with a risk score and actionable checklists.

Can I assess AI-generated code drift in a PR?▼

Yes, you can assess AI-generated code drift by passing the --ai-generated mode to the review script. This tailors the pull request analysis to specifically detect AI-drift alerts and evaluate risk for AI-authored code changes.

What is a PR risk score and how is it calculated during code review?▼

A PR risk score quantifies the potential danger of code changes by verifying invariants and contracts against the base and head references. The review script outputs this score alongside critical items to help reviewers prioritize code checks.

Does the pr-review script support CI/CD workflow automation?▼

Yes, the pr-review script supports CI/CD workflow automation by accepting base and head references directly via command line. You can integrate scripts/review_pr.sh into pipelines to automatically generate risk scores and checklists for human or AI-generated PRs.

What do I need to run a risk assessment on a pull request?▼

To run a risk assessment on a pull request, you need the base and head Git references for your code changes. Optionally, provide a PR number with --pr or enable AI-drift detection with --ai-generated to tailor the contract verification analysis.

Related Skills

Explore More Software Engineering Skills→
russosalvrussosalv
5

requesting-code-review

Dispatch a code-reviewer subagent for git-range reviews with severity checklists.

Community
Intermediate
jankneumannjankneumann
4

cleanup-feature

Merge approved pull requests and archive OpenSpec proposals to finalize features.

Community
Advanced
jamesjlundinjamesjlundin
32

deploy-helper

Run pre-deploy checks and generate a deployment readiness report.

Community
Advanced
OneWave-AIOneWave-AI
245

code-review-pro

Review code for security vulnerabilities, performance bottlenecks, and maintainability issues.

Official
Basic