SkillCheck — Validate Agent Skills for Claude, Cursor, VS Code

You built a skill. But is it good?

Agent Skills are now an open standard adopted by Microsoft, Cursor, and dozens of coding agents. Your skill needs to work everywhere.

? Does the YAML frontmatter follow the spec?
? Will it trigger when users actually need it?
? Is it accessible? Readable? Not full of LLM slop?

You won't know until someone complains. Or you run SkillCheck.

What It Checks

Category	Tier	What We Catch
Structure	Free	Missing fields, invalid names, broken YAML
Body	Free	Content requirements, length, formatting
Naming	Free	Conventions, specificity, reserved words
Semantics	Free	Contradictions, ambiguous instructions
Quality (Basic)	Free	Examples, error handling, triggers, output format, structured instructions, prerequisites
Anti-Slop	Pro	"Let's dive in", hedge words, filler phrases
Security	Pro	PII detection, credential safety, path traversal
Token Budget	Pro	Context efficiency, budget analysis
WCAG	Pro	Color contrast, accessibility for visual skills
Enterprise	Pro	Hardcoded paths, env config, audit support
Workflow	Pro	Step-by-step structure for complex workflows
Quality (Advanced)	Pro	Marketplace readiness, documentation score, success criteria

How It Works

Free (Skill File)

A SKILL.md file that Claude reads and follows to run checks.

1 Copy skill-check folder to ~/.claude/skills/

2 Say "skillcheck my skill" in Claude Code

3 Get instant feedback

Pro (MCP Server Binary)

A Go binary that integrates directly with Claude Code via MCP.

1 Download binary from purchase email

2 Add to ~/.claude.json with license key

3 All Pro checks unlocked automatically

## my-awesome-skill Check Results [PRO]

### Critical Issues (1)
- Description missing WHEN clause. Add trigger context.

### Warnings (2)
- Line 47: Vague term "several" — specify a number
- No error handling documented

### Passed Checks: 47

### Pro Scores
✓ Anti-slop: 92/100
✓ WCAG AA: Pass
✓ Enterprise ready: Yes

Status: Needs Attention

Pricing

Free

$0 forever

✓ Structure validation
✓ Body & naming checks
✓ Semantic consistency
✓ Quality patterns (strengths)
✓ Run locally, unlimited
✓ Open source (MIT)

Get Started

Pro

$79 lifetime

✓ Everything in Free
✓ Anti-slop detection
✓ Security scanning
✓ Token budget analysis
✓ WCAG accessibility
✓ Enterprise readiness
✓ Advanced quality analysis
✓ Go binary & MCP server

Get Pro

COMING SOON

Team

$49 /month

up to 10 users

✓ Everything in Pro
✓ Custom rulesets
✓ Team dashboard
✓ CI/CD integration

FAQ

Is this official Anthropic tooling?

No. SkillCheck is an independent project. The Free tier validates against the Agent Skills open standard (created by Anthropic). Pro adds extra quality checks like anti-slop detection, WCAG accessibility, and security scanning.

What platforms does it work with?

Built and tested for Claude Code. Since it follows the Agent Skills open standard and MCP protocol, it should work with other compatible tools like Cursor, VS Code, and Windsurf.

What about MCP servers?

SkillCheck validates skill definitions, not MCP server implementations. Skills and MCP are complementary; MCP provides connectivity, skills provide procedural knowledge.

Can I use it in CI/CD?

Pro and Team tiers will include GitHub Actions integration. Block PRs that introduce low-quality skills.

What if I disagree with a check?

SkillCheck reports issues; you decide what to fix. Some checks are suggestions, not requirements.

Ship better skills.
Catch issues before your users do.