Agent Native

code-review

Reviews code changes by analyzing diffs, pull requests, and patches against a structured rubric covering correctness, API compatibility, maintainability, test…

by FactoryOfficial publisherNot reviewed

Identity proven by GitHub's verified organisation badge (Factory-AI)

Agents
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode, claude.ai and API
License
MIT (permissive)
Pin
21a74depinned Oct 9, 2026
Context cost
about 720 tokenswhen the skill loads
GitHub stars
8on factory-ai/skills
Scripts
None found

What it does

“Review code changes (diffs, PRs, patches) and provide structured, actionable feedback on correctness, maintainability, and test coverage. Use when the user asks for a code review, requests feedback on a patch/PR, or wants an assessment of changes.”
The author's description, from SKILL.md

Generated summary from the skill's own text

Reviews code changes by analyzing diffs, pull requests, and patches against a structured rubric covering correctness, API compatibility, maintainability, test coverage, performance, and security. The agent provides categorized feedback with specific file locations and concrete improvement suggestions.

When to use it

  • User submits a PR or commit range for review
  • Need feedback on a patch or code diff before merging
  • Assessing whether changes introduce bugs or breaking changes
  • Evaluating test coverage for new functionality

When not to

  • Requesting automated code quality metrics or style enforcement
  • Need real-time code review during pair programming
  • Reviewing code that requires domain-specific expertise outside engineering basics

Install

These commands install from the publisher's repository and need no account.

skills CLI

npx skills add factory-ai/skills --skill code-review

Installs from the repository's default branch, which may have changed since the commit we checked.

GitHub CLI 2.90 or later

gh skill install factory-ai/skills code-review@21a74dec467a1424e3e067712d004cd987d6a0ce

Installs the commit we checked (21a74de).

Copy by hand

Download the folder at 21a74de and put it in .claude/skills/code-review for Claude Code and in .agents/skills/code-review for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at 21a74de

Copy for your agent

A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.

Prompt

Install the agent skill "code-review" by Factory.

Source, pinned to commit 21a74dec467a1424e3e067712d004cd987d6a0ce:
https://github.com/factory-ai/skills/tree/21a74dec467a1424e3e067712d004cd987d6a0ce/skills/code-review

1. Download that folder at exactly this commit. Do not use the default branch.
2. Copy every file unchanged, keeping the folder structure, into .claude/skills/code-review/ for Claude Code and .agents/skills/code-review/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist.
3. Do not edit the files, and do not run any script in the folder unless I ask you to.
4. When you are done, list the files you copied and where you put them.

Listing and checks: https://www.agentnative.dev/skills/factory/code-review

SKILL.md at the pin

---
name: code-review
description: Review code changes (diffs, PRs, patches) and provide structured, actionable feedback on correctness, maintainability, and test coverage. Use when the user asks for a code review, requests feedback on a patch/PR, or wants an assessment of changes.
---

# Code Review

You are a senior engineer conducting a thorough code review.

## Establish Review Target

Determine what to review:
1. If a PR link or commit range is provided, use that
2. Otherwise, check for staged changes: `git diff --staged`
3. Or unstaged changes: `git diff`
4. Or a user-provided patch/diff

## Review Rubric (Priority Order)

Evaluate the changes against these criteria, in order of importance:

### 1. Correctness & Edge Cases
- Does the code do what it's supposed to do?
- Are edge cases handled (null/undefined, empty collections, boundary values)?
- Are error conditions handled appropriately?
- Is the logic sound?

### 2. API & Behavior Changes
- Are there breaking changes to public APIs?
- Do changes affect backwards compatibility?
- Are behavior changes documented or intentional?

### 3. Maintainability & Readability
- Is the code easy to understand?
- Are names descriptive and consistent with codebase conventions?
- Is there unnecessary complexity that could be simplified?
- Is code duplication avoided where appropriate?

### 4. Tests
- Are there tests for new functionality?
- Do existing tests need to be updated?
- Are edge cases covered by tests?
- Do tests actually verify the intended behavior?

### 5. Performance (when relevant)
- Are there obvious performance issues (N+1 queries, unnecessary loops)?
- Are expensive operations cached or optimized where needed?
- Only flag performance issues that are clearly problematic

### 6. Security Basics
- Is user input validated before use?
- Are there authorization checks where needed?
- Are secrets/credentials properly handled (not hardcoded, not logged)?
- Is sensitive data protected?

## Feedback Guidelines

- **Cite exact locations**: Reference file paths and line numbers
- **Provide concrete suggestions**: Show how to fix, not just what's wrong
- **Categorize severity**:
  - **Must-fix**: Bugs, security issues, breaking changes
  - **Suggestions**: Improvements that would make the code better
  - **Nits**: Minor style or preference issues (optional to address)
- **Be constructive**: Explain why something is an issue
- **Don't over-engineer**: Avoid suggesting large refactors unless truly necessary
- **Acknowledge good patterns**: Call out well-written code when you see it

## Output Format

Structure your review as follows:

### Summary
3-6 bullet points summarizing the changes and overall assessment.

### Must-Fix Issues
Issues that should be addressed before merging. Include:
- File and line reference
- Description of the issue
- Concrete fix suggestion

### Suggestions
Improvements that would make the code better but aren't blocking.

### Nits (Optional)
Minor style or preference items. Keep this section brief.

### Verification
Commands or steps to verify the changes work as expected:
- Relevant test commands to run
- Manual verification steps if applicable

From factory-ai/skills at 21a74de, shown as plain text under its license: MIT (permissive). The license text is in LICENSE.

View SKILL.md on GitHub at 21a74de

Files

1 file, 3.2 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at 21a74de
All 34 skills from Factory

More from Factory

  • autoresearch

    This skill runs an autonomous optimization loop to improve a measurable metric through systematic experimentation.

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 4K tokens · pinned 6 days ago

  • ban-type-assertions

    This skill enables the TypeScript ESLint rule that bans `as` type assertions in a package, replacing them with compiler-verified alternatives like Zod…

    Claude Code, Codex, Cursor +4 · about 1.6K tokens · pinned 6 days ago

  • browser-navigation

    This skill enables agents to automate browser interactions including navigation, form filling, element clicking, screenshots, and data extraction from web…

    Claude Code, Codex, Cursor +3 · about 2.5K tokens · pinned 6 days ago

  • create-pr

    Creates a pull request with Conventional Commits formatting, templated body, and optional ticket linking.

    Claude Code, Codex, Cursor +4 · about 2.2K tokens · pinned 6 days ago

  • droid-control

    Automate terminals, browsers, and desktop applications by routing to specialized drivers for recording, testing, and generating visual demonstrations.

    Claude Code · about 3.5K tokens · pinned 6 days ago

  • fix-knip-unused-exports

    Fixes knip unused export violations by identifying their type (test-only, dead barrel re-export, or internally-only-used) and applying the appropriate fix…

    Claude Code, Codex, Cursor +4 · about 2.4K tokens · pinned 6 days ago

All Coding workflow skills
  • planning

    This skill orchestrates multi-workflow projects with dependencies and shared data tables by creating a task graph in the orchestrator via the create-tasks tool.

    by n8nOfficial publisher

    Claude Code, Codex, Cursor +3 · about 2.4K tokens · pinned 6 days ago

  • progressive-building

    This skill implements incremental workflow development for agents building or extending workflows.

    by n8nOfficial publisher

    Claude Code, Codex, Cursor +3 · about 1.4K tokens · pinned 6 days ago

  • workflow-builder

    Builds and edits n8n workflows using the TypeScript SDK.

    by n8nOfficial publisher

    Claude Code, Codex, Cursor +3 · about 14.2K tokens · pinned 6 days ago

  • remotion-upgrade

    This skill upgrades Remotion and its related packages to the latest stable version.

    by RemotionOfficial publisher

    Claude Code, Codex, Cursor +3 · about 460 tokens · pinned 6 days ago

  • remotion-upgrade

    This skill upgrades Remotion and related packages across a project, automatically detecting the package manager and workspaces.

    by RemotionOfficial publisher

    Claude Code, Codex, Cursor +3 · about 460 tokens · pinned 6 days ago

  • final-release-review

    Audits Python SDK release candidates or plans against the previous release, comparing diffs for regressions, API changes, and version compatibility.

    by OpenAIOfficial publisher

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 5.4K tokens · pinned 6 days ago

Open roles at Factory

5 of 7 open roles on the jobs board

The skills listed here are third-party software, collected from public GitHub repositories as a catalog of recent skills and provided as is. Agent Native does not write or control them and is not responsible for any harm, loss or damage caused by installing or using them. Labels and checks describe what we saw at one commit and are not a guarantee. Read a skill's files before you run it. Terms of use