github-actions

1 stars
14
C

Use when creating GitHub Actions workflows for CI/CD - testing, building, publishing npm packages, and automating repository tasks

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 →
skilz install mcclowes/omg/github-actions
skilz install mcclowes/omg/github-actions --agent opencode
skilz install mcclowes/omg/github-actions --agent codex
skilz install mcclowes/omg/github-actions --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
Download Agent Skill ZIP

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

1. Clone the repository:
git clone https://github.com/mcclowes/omg
2. Copy the agent skill directory:
cp -r omg/.claude/skills/github-actions ~/.claude/skills/

Need detailed installation help? Check our platform-specific guides:

Related Agentic Skills

Agentic Skill Details

Repository
omg
Stars
1
Type
Technical
Meta-Domain
development
Primary Domain
github
Market Score
14

Agent Skill Grade

C
Score: 75/100 Click to see breakdown

Score Breakdown

Spec Compliance
12/15
PDA Architecture
18/30
Ease of Use
19/25
Writing Style
8/10
Utility
15/20
Modifiers: +3

Areas to Improve

  • Missing TOC for 103-line file
  • No numbered workflows or procedures
  • Missing validation and troubleshooting

Recommendations

  • Address 2 high-severity issues first
  • Add trigger phrases to description for discoverability
  • Add table of contents for files over 100 lines

Graded: 2026-01-24

Developer Feedback

I was poking around your GitHub Actions skill and noticed you've got solid foundational coverage—the workflow structure is clean and the examples are practical—but there's some room to tighten up the explanations for developers hitting the more nuanced edge cases.

Links:

The TL;DR

You're at 75/100, which lands you in C territory (adequate, but has gaps). This is based on Anthropic's best practices for agentic skills. Your strongest area is Spec Compliance (12/15)—the YAML frontmatter and naming conventions are spot-on. The weakness is Progressive Disclosure Architecture (18/30)—a 103-line file without a table of contents makes it harder to navigate, and there's some padding in the Tips section that could tighten up token usage.

What's Working Well

  • Solid trigger coverage: Your description nails the discovery phase with "CI/CD, testing, building, npm"—developers looking for GitHub Actions workflows will find this
  • Practical code examples: The Quick Start template and Common Patterns section (matrix testing, npm publishing) give real, copy-paste-ready configurations
  • Clean terminology: You're consistent throughout with GitHub Actions vocab—no confusing the reader with misaligned terms

The Big One

Missing table of contents for a 103-line file. Once skills cross 100 lines, readers need a navigation landmark. Right now someone skimming has to read linearly. Add this after the frontmatter:

## Contents
- [Quick Start](#quick-start)
- [Common Patterns](#common-patterns)
- [Triggers](#triggers)
- [Key Features](#key-features)
- [Tips](#tips)

This is a +5 point swing and solves the Progressive Disclosure score immediately.

Other Things Worth Fixing

  1. **No verification/troubleshooting...

Report Security Issue

Found a security vulnerability in this agent skill?