validate-skills
FreeNo executable scriptsNot checkedValidates skills in this repo against agentskills.io spec and Claude Code best practices. Use via /validate-skills command.
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)
| 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, whereb.mdis not linked fromSKILL.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:
fd -t d -d 1 . skills/For each skill, read
SKILL.mdand check against the rules aboveReport 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
Install validate-skills in Claude Code & Claude Desktop
Sign up to install this skill
Create a free account to reveal the install command and save the skill to your library.
- Reveal the one-line install command
- Save skills to your synced library
- Get notified when skills update
Allowed tools
Tools this skill is permitted to call.
No restriction — this skill can use any tool.
FAQ
What does the validate-skills skill do?
Validates skills in this repo against agentskills.io spec and Claude Code best practices. Use via /validate-skills command.
How do I install the validate-skills skill?
Copy the skill folder into ~/.claude/skills (the Claude Code tab above does this in one command), or install it as a plugin.
Does the validate-skills skill run scripts?
No, this skill is instructions only (SKILL.md) with no executable scripts.
Related skills
MCP Builder
Scaffold a Model Context Protocol server
by AnthropicCommit Helper
Write clean, conventional git commit messages
by Unylyalgorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generati
by Anthropicclaude-api
|-
by Anthropic