claude-skills

An open-source library of modular “Claude Code skills” / agent plugins plus supporting Python CLI tools, personas, and orchestration patterns. It provides structured instructions (e.g., SKILL.md), stdlib-only Python scripts, and converts/install packages for multiple coding agents/tools (Claude Code marketplace/plugin, OpenAI Codex via scripts, Gemini CLI, OpenClaw, Cursor, Aider, Windsurf, Kilo Code, OpenCode, Augment, Antigravity).

Evaluated Mar 29, 2026 (0d ago)
Homepage ↗ Repo ↗ DevTools agent-plugins agent-skills ai-coding-agent prompt-engineering python-cli offline tooling
⚙ Agent Friendliness
56
/ 100
Can an agent use this?
🔒 Security
28
/ 100
Is it safe for agents?
⚡ Reliability
31
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
0
Documentation
70
Error Messages
0
Auth Simplicity
100
Rate Limits
0

🔒 Security

TLS Enforcement
0
Auth Strength
50
Scope Granularity
0
Dep. Hygiene
60
Secret Handling
35

The README claims a “skill-security-auditor” that scans skills for issues like command injection, code execution, data exfiltration, prompt injection, and supply-chain risks, and also notes “stdlib-only, zero pip installs” for Python tools. However, as a general community skill bundle that may contain executable scripts/instructions, you should still assume the need for review/sandboxing before installing third-party skills. No explicit guidance is provided here about secret handling practices in the scripts or about TLS/auth for any hosted service (none described).

⚡ Reliability

Uptime/SLA
0
Version Stability
55
Breaking Changes
45
Error Recovery
25
AF Security Reliability

Best When

You want offline/local, tool-agnostic “skill” packages that can be installed into many agent clients and executed via Python scripts without external dependencies.

Avoid When

You cannot vet or sandbox third-party code/instructions, or you need first-class hosted APIs/webhooks/SDKs with strong runtime governance from a single vendor.

Use Cases

  • Install domain-specific workflow/knowledge packs into coding agents (engineering, product, marketing, compliance, C-level advisory, finance)
  • Run stdlib-only Python CLI utilities for analysis/generation (e.g., metrics calculations, prioritization, audits, scaffolders)
  • Use curated personas to standardize agent thinking and communication styles
  • Apply orchestration patterns (solo sprint, domain deep-dive, multi-agent handoff, skill chain)
  • Pre-audit skills for security risks using the included skill-security-auditor before installation

Not For

  • Production usage that requires a hosted SaaS API with a documented service contract and SLA
  • Use cases needing managed secrets storage, hosted authentication flows, or customer-managed compliance controls from the provider
  • Environments where arbitrary third-party code execution is forbidden without additional sandboxing

Interface

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

Authentication

Methods: No service authentication described (local repo/plugin installation)
OAuth: No Scopes: No

Authentication is not applicable as this is a local/open-source repo. Agent clients may have their own auth, but no centralized API auth is described here.

Pricing

Free tier: No
Requires CC: No

Repo indicates MIT license and appears to be open-source; no hosted pricing model is described.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • This is primarily an instruction/tooling bundle; success depends on the target agent client’s expected skill/plugin format and installation location
  • Skills may include scripts that execute locally; ensure you review/sandbox when running on untrusted skills
  • No centralized API means agent runtime error-handling/retry semantics are not standardized across tools

Alternatives

Full Evaluation Report

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

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 2026-03-29.

5347
Packages Evaluated
21056
Need Evaluation
586
Need Re-evaluation
Community Powered