openapi

1 stars

Use when working with OpenAPI Specification files to validate, create/modify paths and schemas, check references, and enforce best practices

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 mcclowes/vague/openapi

OpenCode (CLI) Fast

skilz install mcclowes/vague/openapi --agent opencode

OpenAI Codex (CLI) Native

skilz install mcclowes/vague/openapi --agent codex

Gemini CLI (Project) Project

skilz install mcclowes/vague/openapi --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/mcclowes/vague

2. Copy the agent skill directory:

cp -r vague/.claude/skills/openapi ~/.claude/skills/

Owner: mcclowes (GitHub)
Repository: vague
Stars: 1
Type: Technical
Meta-Domain: web api
Primary Domain: api
Market Score: 14

Agentic Skill Grades →

Agent Skill Grade

Score: 75/100 Click to see breakdown

Score Breakdown

Spec Compliance

12/15

PDA Architecture

23/30

Ease of Use

20/25

Writing Style

8/10

Utility

16/20

Modifiers: -4

Areas to Improve

Quick Start Example Too Verbose
Missing Workflow Steps
No Input/Output Examples

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've been exploring how different teams structure their OpenAPI workflows, and I noticed your skill takes a pretty pragmatic approach to the schema validation side of things—definitely some solid fundamentals here, though there's room to tighten up the overall experience for developers who are new to the spec.

Links:

The TL;DR

You're at 75/100, solid C-range territory. This is based on Anthropic's 5-pillar skill evaluation framework. Your strongest area is Spec Compliance (12/15)—the YAML frontmatter is clean and your trigger terms are well-chosen. The weakest spots are Progressive Disclosure Architecture (23/30) and Utility (16/20), which is pretty typical—it's where skills often need structural work rather than content work.

What's Working Well

Trigger discoverability is solid. Your description nails the key phrases (OpenAPI, validate, create/modify paths, schemas, $ref)—developers searching for this skill will find it.
Core Principles are nicely condensed. You packed operational constraints (operationId uniqueness, $ref validation) into tight language that respects token economy at Level 2.
Consistent OpenAPI terminology. No conflicting terms, no casual language where precision matters—this builds trust.
The Common Operations section lists the right stuff (validate structure, manage schemas, configure security). The problem is presentation, not content.

The Big One: Quick Start Example Is Eating Your Tokens

Your Quick Start example spans 28 lines—way too verbose for Level 2 progressive disclosure. It shows the complete end state, but that's overkill when someone just needs to understand the pattern quickly.

Why it matters: You lose 3 points (PDA token_economy + layered_structure), and more impo...

Browse Category

More web api Agentic Skills

Report Security Issue

Found a security vulnerability in this agent skill?