Check skill metadata and code against official agentskills.io specs and Claude Code practices.

Install

mkdir -p .claude/skills/validate-skills && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/2791" && unzip -o skill.zip -d .claude/skills/validate-skills && rm skill.zip

Installs to .claude/skills/validate-skills

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Validates skills in this repo against agentskills.io spec and Claude Code best practices. Use via /validate-skills command.
123 charsno explicit “when” trigger
Beginner

Key capabilities

  • Validate skill metadata against spec
  • Check directory naming conventions
  • Verify documentation standards
  • Lint skill structure

How it works

It scans skill directories to ensure they meet agentskills.io specifications and Claude Code best practices.

Inputs & outputs

You give it
Skill directory path
You get back
Validation pass/fail report

When to use validate-skills

  • Validate new skill metadata
  • Check skill for spec compliance
  • Ensure documentation standards

About this skill

Validate Skills

Validate all skills in skills/ against the agentskills.io spec and Claude Code best practices.

Validation Checklist

For each skill directory, verify:

Spec Compliance (agentskills.io)

CheckRule
name format1-64 chars, lowercase alphanumeric + hyphens, no leading/trailing/consecutive hyphens
name matches directoryDirectory name must equal name field
description length1-1024 characters, non-empty
Optional fields validlicense, metadata, compatibility if present

Best Practices (Claude Code)

CheckRule
Description formatThird person, describes what + when to use
Body lengthUnder 500 lines
Loading is one-level deepSKILL.md is the only progressive-disclosure entry point: every reference file must be reachable from SKILL.md. References may cross-link each other for navigation (see note below).
Links are markdownUse [text](path) not bare filenames
No redundancyDon't repeat description in body
ConciseOnly add context Claude doesn't already have

One-level-deep vs. cross-linking. The one-level-deep rule targets progressive-disclosure loading chains — a reference that can only be discovered by loading another reference first (SKILL.mda.mdb.md, where b.md is not linked from SKILL.md). That is a defect: it hides content from the loader.

It does not forbid navigational cross-links. Per AGENTS.md, reference files end with a "Related Skills" footer linking sibling references, and this is required. A cross-link is fine as long as both endpoints are also reachable directly from SKILL.md. Only flag a reference that is reachable exclusively through another reference.

How to Run

  1. Find all skill directories:

    fd -t d -d 1 . skills/
    
  2. For each skill, read SKILL.md and check against the rules above

  3. Report issues in this format:

    ## Validation Results
    
    ### skills/example-skill
    - [PASS] name format valid
    - [FAIL] name "example" doesn't match directory "example-skill"
    - [PASS] description length OK (156 chars)
    

References

When not to use it

  • When validating non-skill directories
  • When skipping spec compliance checks

Prerequisites

Skill directory structure

Limitations

  • Requires adherence to specific naming rules
  • Limited to agentskills.io spec

How it compares

It provides automated, spec-based validation rather than manual review of skill structure.

Compared to similar skills

validate-skills side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
validate-skills (this skill)26moReviewBeginner
deepwiki-rs259moReviewIntermediate
python-code-style96moReviewIntermediate
code-review-excellence195moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

deepwiki-rs

sopaco

AI-powered Rust documentation generation engine for comprehensive codebase analysis, C4 architecture diagrams, and automated technical documentation. Use when Claude needs to analyze source code, understand software architecture, generate technical specs, or create professional documentation from any programming language.

25170

python-code-style

wshobson

Python code style, linting, formatting, naming conventions, and documentation standards. Use when writing new code, reviewing style, configuring linters, writing docstrings, or establishing project standards.

971

code-review-excellence

wshobson

Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.

1958

code-walk-thru

pchalasani

Use this when user wants you to walk through (code or text) files in a EDITOR to either explain how some code works, or to show the user what changes you made, etc. You would typically use this repeatedly to show the user your changes or code files one by one, sometimes with specific line-numbers. This way the user is easily able to follow along in their favorite EDITOR as you point at various files possibly at specific line numbers within those files.

670

cookbook-audit

anthropics

Audit an Anthropic Cookbook notebook based on a rubric. Use whenever a notebook review or audit is requested.

568

schema-markup

davila7

When the user wants to add, fix, or optimize schema markup and structured data on their site. Also use when the user mentions "schema markup," "structured data," "JSON-LD," "rich snippets," "schema.org," "FAQ schema," "product schema," "review schema," or "breadcrumb schema." For broader SEO issues, see seo-audit.

1042

Search skills

Search the agent skills registry