json-schema

1 stars
14
B

Use when working with JSON Schema for validation, OpenAPI schemas, type definitions, and data structure specification

Also in: json database data analysis

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/json-schema
skilz install mcclowes/omg/json-schema --agent opencode
skilz install mcclowes/omg/json-schema --agent codex
skilz install mcclowes/omg/json-schema --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/json-schema ~/.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

B
Score: 82/100 Click to see breakdown

Score Breakdown

Spec Compliance
12/15
PDA Architecture
22/30
Ease of Use
21/25
Writing Style
9/10
Utility
15/20
Modifiers: +3

Areas to Improve

  • No Reference Files for Deep Topics
  • Missing Workflow Steps
  • No Validation Feedback Loops

Recommendations

  • Address 1 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've been digging into JSON Schema validation tooling lately, and I like how your skill approaches the problem—the structured breakdown of validation patterns is solid, though I'm curious about some of the edge cases your implementation handles at scale.

Links:

The TL;DR

You're at 82/100, solid B-grade territory. This is based on Anthropic's agentic skills best practices. Your writing style is chef's kiss (9/10)—the imperative voice and technical objectivity are exactly right—but you're leaving points on the table with Progressive Disclosure Architecture (22/30) because everything lives in one 73-line file and Utility (15/20) because there's no validation feedback loop or testing guidance.

What's Working Well

  • Trigger phrases are dialed in. "JSON Schema", "OpenAPI", "validation", "type definitions"—developers searching for this stuff will find it. The metadata is doing heavy lifting.
  • Writing is lean and purposeful. Every sentence in the tables earns its space. No fluff, no marketing speak. The examples like {"type": "object", "properties": {...}} are complete and actionable.
  • Composition patterns section actually helps. The allOf, oneOf, anyOf breakdown is exactly what someone needs when they're stuck deciding between composition strategies.

The Big One: Missing Reference Files for Deep Topics

Here's what's holding you back from a A: you've got all your content jammed into SKILL.md with no external references for the complex stuff. When someone needs to understand advanced validation patterns, conditional schemas, or the nuances of OpenAPI 3.1 integration, there's nowhere to dig deeper.

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

  • references/advanced-composition.md — `all...

Report Security Issue

Found a security vulnerability in this agent skill?