Validate Skills

by callstackincubator61e6e7dfdf3aMIT1.6K starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated today

Validates skills in this repo against agentskills.io spec and Claude Code best practices. Use via /validate-skills command.

Instructions onlyAI & Agents

AI-generated overview

Validates skill folders against the agentskills.io spec and Claude Code best practices, reporting pass/fail issues.

What it does: This skill provides a checklist for auditing skill directories in a repository. It verifies spec compliance items such as name format, name-to-directory matching, description length and optional fields, plus best-practice items such as description style, body length, one-level-deep loading, markdown links, redundancy and conciseness. It produces a validation report listing each skill with pass or fail lines for the checked rules.
When to use it: Use it when reviewing or maintaining a collection of skills and you want a consistent compliance and quality check. It suits pre-commit or review-time audits of skill folders before publishing or merging.
Requirements: Instructions only; no scripts are shipped. It expects skill directories under a skills/ folder and references the agentskills.io specification and Claude Code best practices documentation. The example command uses the fd tool, and network access may be needed to consult the linked documentation.

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)

Check	Rule
`name` format	1-64 chars, lowercase alphanumeric + hyphens, no leading/trailing/consecutive hyphens
`name` matches directory	Directory name must equal `name` field
`description` length	1-1024 characters, non-empty
Optional fields valid	`license`, `metadata`, `compatibility` if present

Best Practices (Claude Code)

Check	Rule
Description format	Third person, describes what + when to use
Body length	Under 500 lines
Loading is one-level deep	`SKILL.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 markdown	Use `[text](path)` not bare filenames
No redundancy	Don't repeat description in body
Concise	Only 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.md → a.md → b.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

Find all skill directories:

For each skill, read SKILL.md and check against the rules above

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)

## 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

Source and attribution

Source:callstackincubator/agent-skillsin.claude/skills/validate-skillsat commit61e6e7d

License: MIT

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal

Validate Skills

Validate Skills

Validation Checklist

Spec Compliance (agentskills.io)

Best Practices (Claude Code)

How to Run

References

Source and attribution

More from callstackincubator/agent-skills

Writing User Docs

Upgrading React Native

React Navigation

Github Actions

Create React Native Library

More in AI & Agents

Skill Development

Plugin Structure

Command Development

Claude Md Improver

Google Cloud Solution Agentic Ai Data Science Workflow

Google Cloud Solution Agentic Ai Borderless Data Lakehouse