Updated 2w ago
by agent-ecosystem
skill-validator
Validate Skill content against Agent Skill specification, with additional content density and quality checks.
266 GitHub stars (266)
+11 in 30 days
| Period | New stars |
|---|---|
| Sep 27 | 0 |
| Sep 28 | 0 |
| Sep 29 | 0 |
| Sep 30 | +1 |
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | +2 |
| Oct 5 | +1 |
| Oct 6 | 0 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | +1 |
| Oct 10 | +2 |
| Oct 11 | 0 |
| Oct 12 | 0 |
| Oct 13 | 0 |
| Oct 14 | 0 |
| Oct 15 | +1 |
| Oct 16 | 0 |
| Oct 17 | +1 |
| Oct 18 | 0 |
| Oct 19 | 0 |
| Oct 20 | +1 |
| Oct 21 | 0 |
| Oct 22 | 0 |
| Oct 23 | −1 |
| Oct 24 | +1 |
| Oct 25 | 0 |
| Oct 26 | 0 |
| Oct 27 | +1 |
| Oct 28 | +2 |
| Oct 29 | 0 |
| Oct 30 | 0 |
| Oct 31 | +2 |
| Nov 1 | 0 |
| Nov 2 | 0 |
| Nov 3 | 0 |
| Nov 4 | 0 |
| Nov 5 | 0 |
- 13 skills (13 skills found in its SKILL.md files)
- 32 forks (32 forks)
- 2w ago last update (Last updated 2w ago)
Install
Skills CLI
npx skills add agent-ecosystem/skill-validator
Asks which skills and agents to install. Just one: npx skills add agent-ecosystem/skill-validator --skill review-skill — add -g for every project.
Claude Code
git clone https://github.com/agent-ecosystem/skill-validatorcp -r "skill-validator/examples/review-skill" ~/.claude/skills/
Copies the review-skill skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add agent-ecosystem/skill-validator
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
review-skill
Review a proposed Agent Skill for structural validity and content quality before publishing. Runs the skill-validator CLI to check for structural issues, scores the skill with an LLM judge, and interprets results to advise authors on what to address. Use when a user wants to review, validate, or quality-check an Agent Skill.
examples/review-skill/ on GitHub (opens in a new tab)SKILL.md -
allowed-dirs-skill
A skill with development directories that require --allow-dirs.
testdata/allowed-dirs-skill/ on GitHub (opens in a new tab)SKILL.md -
auxiliary-only-skill
A skill that uses only shell and config code blocks for testing contamination.
testdata/auxiliary-only-skill/ on GitHub (opens in a new tab)SKILL.md -
broken-frontmatter bad_indent: this line has a tab that breaks YAML parsing
No description in the SKILL.md.
testdata/broken-frontmatter/ on GitHub (opens in a new tab)SKILL.md -
flat-skill
A skill using a flat layout with all files at the root level.
testdata/flat-skill/ on GitHub (opens in a new tab)SKILL.md -
Wrong-Name
No description in the SKILL.md.
testdata/invalid-skill/ on GitHub (opens in a new tab)SKILL.md -
nested-paths-skill
A fixture with two intentionally nested asset bundles.
testdata/nested-paths-skill/ on GitHub (opens in a new tab)SKILL.md -
rich-skill
A skill with code blocks and imperative instructions for testing content and contamination analysis.
testdata/rich-skill/ on GitHub (opens in a new tab)SKILL.md -
token-exclusion-skill
A fixture with generated and non-generated non-standard content.
testdata/token-exclusion-skill/ on GitHub (opens in a new tab)SKILL.md -
valid-skill
A well-formed example skill for testing the validator.
testdata/valid-skill/ on GitHub (opens in a new tab)SKILL.md -
warnings-only-skill
A skill that produces warnings but no errors.
testdata/warnings-only-skill/ on GitHub (opens in a new tab)SKILL.md -
skill-alpha
A valid skill for multi-skill testing.
testdata/multi-skill/ on GitHub (opens in a new tab)skill-alpha/ SKILL.md -
skill-beta
A minimal valid skill.
testdata/multi-skill/ on GitHub (opens in a new tab)skill-beta/ SKILL.md
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.