github-code-review

Comprehensive GitHub code review with AI-powered swarm coordination

Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security

Installation for Agentic Skill

View all platforms →

Claude Code (CLI) Fast

skilz install I-Onlabs/claude-code-skills/github-code-review

OpenCode (CLI) Fast

skilz install I-Onlabs/claude-code-skills/github-code-review --agent opencode

OpenAI Codex (CLI) Native

skilz install I-Onlabs/claude-code-skills/github-code-review --agent codex

Gemini CLI (Project) Project

skilz install I-Onlabs/claude-code-skills/github-code-review --agent gemini

First time? Install Skilz: pip install skilz

Works with 22+ AI coding assistants

Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...

View All Agents

For Claude Desktop Easy

Download Agent Skill ZIP

Extract and copy to ~/.claude/skills/ then restart Claude Desktop

Manual Installation

1. Clone the repository:

git clone https://github.com/I-Onlabs/claude-code-skills

2. Copy the agent skill directory:

cp -r claude-code-skills/github-code-review ~/.claude/skills/

Owner: I-Onlabs (GitHub)
Repository: claude-code-skills
Type: Non-Technical
Meta-Domain: general
Primary Domain: general
Sub-Domain: github review code review
Market Score: 88

Agentic Skill Grades →

Agent Skill Grade

Score: 88/100 Click to see breakdown

Score Breakdown

Spec Compliance

11/15

PDA Architecture

24/30

Ease of Use

24/25

Writing Style

9/10

Utility

20/20

Areas to Improve

Description needs trigger phrases
Excessive Length
Marketing Language

Recommendations

Add trigger phrases to description for discoverability
Add table of contents for files over 100 lines

Graded: 2026-01-19

Developer Feedback

I took a look at your github-code-review skill and wanted to share some thoughts.

Links:

The TL;DR

You're at 88/100, solid B grade territory. This is based on Anthropic's skill best practices rubric. Your strongest area is Utility (20/20) — the skill genuinely solves real problems with swarm-based code review. Weakest area is Spec Compliance (11/15) — mostly missing trigger phrases in the description, which affects discoverability.

What's Working Well

Utility is chef's kiss — You nailed the core value proposition. Swarm coordination for code review is genuinely useful, and your agents/orchestration pattern is well thought out.
Progressive structure — The skill has a clear table of contents, numbered steps, and workflow clarity (9/10 on layered structure). Developers can actually navigate this.
Strong trigger terms — Your discoverability score is solid (6/6) because you're using keywords like "code review", "github", "swarm", "PR" consistently throughout.
Real-world examples — The input/output pairs and checklists show you actually thought about how people will use this.

The Big One: Split Your File

Your skill is 1,141 lines in a single SKILL.md — that's bloated. This kills your Progressive Disclosure Architecture score (24/30). Best practices say:

The fix: Create a references/ directory with separate files:

references/github-cli-commands.md — Detailed CLI reference
references/swarm-patterns.md — Agent coordination patterns
references/review-templates.md — Configuration examples

Keep SKILL.md as the overview only (200-300 lines max). Link to references for deep dives. This alone gets you +3 points.

Other Things Worth Fixing

**Add trigg...

Browse Category

More general Agentic Skills

Report Security Issue

Found a security vulnerability in this agent skill?