omg

1 stars
14
C

Use when writing or editing .omg.md files - the human-first DSL for API specification that compiles to OpenAPI 3.1

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/omg
skilz install mcclowes/omg/omg --agent opencode
skilz install mcclowes/omg/omg --agent codex
skilz install mcclowes/omg/omg --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/omg ~/.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
web api
Primary Domain
api
Market Score
14

Agent Skill Grade

C
Score: 73/100 Click to see breakdown

Score Breakdown

Spec Compliance
12/15
PDA Architecture
18/30
Ease of Use
19/25
Writing Style
8/10
Utility
13/20
Modifiers: +3

Areas to Improve

  • Missing workflow guidance
  • Insufficient examples
  • No feedback loop

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 checked out your skill and noticed the core logic is solid, but the documentation could use some work to help developers understand the intended use cases—especially since the grade came back at 73.

Links:

The TL;DR

You're at 73/100, which puts you in C territory — solid fundamentals, but there's some low-hanging fruit to bump this up. Based on Anthropic's best practices for agentic skills, your Spec Compliance is strong (12/15), but Ease of Use and Utility are dragging things down. The biggest gap is workflow guidance and examples.

What's Working Well

  • Metadata is sharp. Your description nails the trigger with "writing or editing .omg.md files" and explains purpose clearly.
  • Spec compliance is clean. Valid YAML frontmatter, correct naming conventions, and you're hitting 12 out of 15 points here.
  • Concise structure. At 48 lines, the skill is lean and doesn't bloat with unnecessary content—you earned points for that.

The Big One: Missing Workflow Guidance

Here's what's holding you back: developers don't know how to actually use this thing end-to-end. You list code block types (omg.path, omg.body, omg.response) but never show developers the decision tree—when do you use each? What's the structure of a complete endpoint?

The fix: Add a section called "Endpoint Structure Checklist" that walks through:

  1. Define method/path in frontmatter
  2. Use omg.path for parameters
  3. Use omg.body for POST/PATCH payloads
  4. Use omg.response for 200 success
  5. Use omg.response.400 for errors

This alone could add ~3 points and makes the skill immediately more useful.

Other Things Worth Fixing

  1. Only one example. You've got a single GET endpoint. Add a references/examples.md with POST (including body val...

Report Security Issue

Found a security vulnerability in this agent skill?