Skill validator

Skill Fyzel/claude-skills/skills/skill-validator

Validate Claude Code skill files (SKILL.md) against Anthropic's structural requirements. Use this skill whenever the user asks to validate, lint, check, or verify a skill file or skill structure. Triggers on "validate skill", "lint skill", "check skill", "verify SKILL.md", "does my skill meet requirements", or any request to confirm a skill is correctly structured before publishing or importing.From its SKILL.md

Install

npx -y skills add Fyzel/claude-skills --skill skill-validator

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
runs commandsInstructs the agent to run 8 commands, including `.venv/Scripts/python skills/skill-validator/scripts/validate-skills.py` and 7 more.

SKILL.md

1.8 KB, 359 tokens by cl100k_base, as published. Nobody here has run it

Skill Validator

Validates SKILL.md files in the skills/ directory against Anthropic's requirements using skills/skill-validator/scripts/validate-skills.py.

What it checks

name field present and matches the skill's directory name
description field present
No XML tags (<...>) in description — Claude Code rejects these on load
Combined description + when_to_use length ≤ 1,536 characters
Frontmatter parsed via PyYAML (handles block scalars correctly)
Packaging simulation writes skills/<name>/.test/<name>.skill and reports archive size

Run

Validate all skills:

# Windows
.venv/Scripts/python skills/skill-validator/scripts/validate-skills.py

# Linux / macOS
.venv/bin/python skills/skill-validator/scripts/validate-skills.py

Validate one skill by name:

# Windows
.venv/Scripts/python skills/skill-validator/scripts/validate-skills.py <skill-name>

# Linux / macOS
.venv/bin/python skills/skill-validator/scripts/validate-skills.py <skill-name>

Skip packaging simulation:

# Windows
.venv/Scripts/python skills/skill-validator/scripts/validate-skills.py --no-package

# Linux / macOS
.venv/bin/python skills/skill-validator/scripts/validate-skills.py --no-package

Exit code 0 = all pass. Exit code 1 = one or more failures.

Setup

Requires Python in .venv:

python -m venv .venv
pip install -r requirements.txt

What ships with it: 2 files

4.7 KB alongside SKILL.md, 1 of them executable

.claude-plugin/

plugin.json464 B

scripts/

validate-skills.pyruns4.2 KB

Gives 0 of the 12 instructions most quality gates skills give in 359 tokens

Counted across 1,524 of the 2,830 authors here whose files we hold, read 2026-09-06

Read full output and check exit codein 45 of 1524, across 40 files
Verify output confirms the claimin 44 of 1524, across 39 files
Identify the command that proves the claimin 43 of 1524, across 39 files
Execute the full verification commandin 36 of 1524, across 30 files
Produce a verification reportin 34 of 1524, across 18 files
Review git diff changesin 30 of 1524, across 16 files
Fix build failures immediatelyin 29 of 1524, across 9 files
Group findings by severityin 28 of 1524
State claim only with evidencein 27 of 1524, across 22 files
Verify regression tests with red-green cyclein 26 of 1524, across 22 files
Run the full test suitein 26 of 1524, across 25 files
Run test suite with coveragein 25 of 1524, across 10 files

Said here and by no other author read

Validate a specific skill by name
Use the no-package flag to skip packaging simulation

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.