json-schema
Use when working with JSON Schema for validation, including draft-07, 2019-09, and 2020-12 specifications
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/vague/json-schemaskilz install mcclowes/vague/json-schema --agent opencodeskilz install mcclowes/vague/json-schema --agent codexskilz install mcclowes/vague/json-schema --agent geminiFirst time? Install Skilz: pip install skilz
Works with 22+ AI coding assistants
Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...
Extract and copy to ~/.claude/skills/ then restart Claude Desktop
git clone https://github.com/mcclowes/vaguecp -r vague/.claude/skills/json-schema ~/.claude/skills/Need detailed installation help? Check our platform-specific guides:
Related Agentic Skills
command-name
by anthropics
This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components"...
mcp-integration
by anthropics
This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Contex...
rule-identifier
by anthropics
This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs g...
bloblang-authoring
by redpanda-data
This skill should be used when users need to create or debug Bloblang transformation scripts. Trigger when users ask about transforming data, mappi...
Agentic Skill Details
- Repository
- vague
- Stars
- 1
- Type
- Technical
- Meta-Domain
- productivity
- Primary Domain
- json
- Market Score
- 14
Agent Skill Grade
A Score: 91/100 Click to see breakdown
Score Breakdown
Areas to Improve
- Missing TOC in reference files
- Use case labels add verbosity
- Missing validation workflow
Recommendations
- 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 diving into your json-schema skill and really appreciate how you've structured the progressive disclosure—most schema validation tools bury their complexity upfront, but you've managed to keep the essentials accessible while still serving power users.
Links:
The TL;DR
You're at 91/100, solidly in A territory. This evaluation follows Anthropic's skill best practices and your strongest area is Progressive Disclosure Architecture (28/30)—you nailed the layering. The weakest relative area is Spec Compliance (12/15), which is fixable with a couple quick additions.
What's Working Well
- Perfect layering structure: SKILL.md stays concise while delegating all details to exactly three reference files. Most people try to cram everything into one file—you didn't.
- Token economy is tight: Quick Start gets straight to the point, heavy use of bullet lists, zero fluff. Every line earns its place.
- Strong trigger terms: "JSON Schema", "validation", draft version numbers—the skill activates for the right use cases.
- Realistic examples throughout: Your composition.md and ajv.md sections show actual input/output pairs that people can copy and modify, not abstract theory.
The Big One: Spec Compliance Description
Your description currently has only 1-2 trigger phrases, but it could be doing more heavy lifting for discoverability. Right now it reads pretty narrowly—you're leaving value on the table for users searching.
Current state: Generic description doesn't capture the breadth of what you cover (multiple JSON Schema drafts, Ajv integration, composition patterns).
The fix: Expand the description in your frontmatter to include more trigger phrases. Something like:
description: JSON Schema validation, draft version selection (Dr...
Browse Category
More productivity Agentic SkillsReport Security Issue
Found a security vulnerability in this agent skill?
Report Security Issue
Thank you for helping keep SkillzWave secure. We'll review your report and take appropriate action.
Note: For critical security issues that require immediate attention, please also email security@skillzwave.ai directly.