Skillz

A lightweight MCP server that loads Claude-style SKILL.md skill files and exposes them as callable tools to any MCP-compatible AI agent (Codex, Copilot, Cursor), acting as a universal shim for skill portability across non-Claude clients.

Evaluated Mar 07, 2026 (0d ago) vlatest
Homepage ↗ Repo ↗ Developer Tools mcp skills claude-skills python codex cursor copilot docker stdio sse
⚙ Agent Friendliness
68
/ 100
Can an agent use this?
🔒 Security
75
/ 100
Is it safe for agents?
⚡ Reliability
67
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
65
Documentation
72
Error Messages
50
Auth Simplicity
75
Rate Limits
62

🔒 Security

TLS Enforcement
90
Auth Strength
75
Scope Granularity
68
Dep. Hygiene
72
Secret Handling
68

Gaming platform API. SDK key auth. Player data is PII — COPPA compliance for minors. Cash prize gaming — verify age and region restrictions.

⚡ Reliability

Uptime/SLA
72
Version Stability
68
Breaking Changes
62
Error Recovery
65
AF Security Reliability

Best When

You have Claude skills defined in SKILL.md format and want to reuse them with other MCP-compatible agents without platform-specific rewrites.

Avoid When

You need a production-hardened skill management system with audit trails and access control; Skillz is experimental and treats skill code as potentially untrusted.

Use Cases

  • Share Claude skill packs with Codex, GitHub Copilot, or Cursor without rewriting skills for each platform
  • Package and distribute reusable agent workflows as ZIP or .skill archives discoverable by any MCP client
  • Make supplementary resources (scripts, datasets, examples) available to agents alongside skill instructions
  • Run skills in Docker containers for isolated, reproducible agent execution environments
  • Rapidly prototype and test skill libraries using stdio, HTTP, or SSE transport modes

Not For

  • Production deployments requiring enterprise-grade security — explicitly described as an experimental proof-of-concept
  • Teams needing skill versioning, access control, or centralized skill registry management
  • Scenarios where running untrusted skill code is a security concern

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: none
OAuth: No Scopes: No

No authentication documented. Skills directory access is controlled by the local filesystem and Docker volume mounts.

Pricing

Model: open_source
Free tier: Yes
Requires CC: No

MIT open source with no associated service costs.

Agent Metadata

Pagination
none
Idempotent
Unknown
Retry Guidance
Not documented

Known Gotchas

  • Explicitly described as 'experimental proof-of-concept' — not production-ready
  • Users advised to treat skill code as untrusted — skills can execute arbitrary scripts
  • No skill sandboxing or permission model; Docker is the only isolation mechanism
  • SKILL.md format is tied to Claude's skill convention — not a universal standard
  • 369 stars and ~102 commits indicates early-stage adoption; API may change

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for Skillz.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-07.

6228
Packages Evaluated
26150
Need Evaluation
173
Need Re-evaluation
Community Powered