autoreview

Automate structured pre-commit code reviews across multiple AI engines.

9.3k|1.4k|Updated Jan 3, 2026
One-click install
npx skills add https://github.com/openclaw/clawhub --skill autoreview-openclaw
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: autoreview
Source: https://github.com/openclaw/clawhub/tree/main/.agents/skills/autoreview
Command: npx skills add https://github.com/openclaw/clawhub --skill autoreview-openclaw

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Pre-commit/ship code reviews are error-prone and time-consuming; autoreview provides a structured, engine-powered review gate that evaluates changes before they are committed or merged.

Core Features & Use Cases

  • Supports Codex, Claude, Droid, Copilot, Pi, and OpenCode engines to evaluate patches.
  • Enforces scope governance, isolation, and reproducible prompts for safe reviews.
  • Generates actionable findings with deterministic outputs to guide PRs and releases.

Quick Start

Run autoreview on your repository to start an engine-guided code review before shipping.

Frequently Asked Questions about autoreview

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

FAQPage Schema
How do I automate pre-commit code reviews using multiple AI agents?

Automated pre-commit code reviews coordinate multiple AI agents to evaluate patches before shipping. This process isolates prompts and enforces scope governance to generate structured, actionable findings for pull requests and branches.

Can I use AI code review engines like Claude and Copilot before merging a pull request?

Yes, AI code review engines like Claude and Copilot evaluate pull requests by analyzing patches within a safe environment. They apply reproducible prompts to ensure deterministic outputs that guide merges and releases.

What is scope governance in automated pre-commit code reviews?

Scope governance in pre-commit code reviews restricts the evaluation boundary so AI engines only assess targeted changes. This isolation ensures reproducible prompts and prevents unrelated code from skewing actionable findings.

Does automated pre-commit review work with local commits or only pull requests?

Automated pre-commit review works across local commits, branches, and pull requests. It processes patch changes through multiple engines to surface deterministic findings before code is merged or shipped.

What's the best way to structure AI code review outputs for release management?

The best way to structure AI code review outputs is through deterministic results that enforce scope governance. This approach generates actionable findings formatted to directly guide pull requests and release decisions.

Why do my AI code review prompts produce inconsistent results across different branches?

Inconsistent AI code review results often stem from missing prompt isolation and scope governance. Applying reproducible prompts within a safe environment ensures deterministic outputs when evaluating patches across branches.