clawfu-skills — security grade SAFE, quality 73/100

Security audit verdict: SAFE · quality 73/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by guia-matthieu · MCP Server · ★ 145

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is clawfu-skills safe to install? View the security audit →

About clawfu-skills

ClawFu Skills 175 expert marketing methodologies for AI agents. Free. Open source. MIT licensed. Dunford on positioning. Schwartz on copywriting. Cialdini on persuasion. Ogilvy on advertising. Hormozi on offers. Voss on negotiation. And 160+ more — encoded as structured, agent-readable instructions. Skills compound. Prompts don't. Install Claude Desktop / Claude Code / Copilot (MCP) Cursor / Windsurf Add to your MCP config: Clone as Claude Code skills directory Browse & download individual skills clawfu.com/skills Catalog 175 skills across 28 categories: pipeline forecasting, forecast scenarios, revenue attri

ai-skillsanthropicclaude-codeclaude-skillsmarketingmcp-serverprompt-engineeringskills

Quick Facts

Stars145
Forks28
LanguagePython
CategoryMCP Server
LicenseMIT
Quality Score72.5844535549079/100
Open Issues5
Last Updated2026-04-02
Created2026-01-31
Platformsclaude-code, mcp, python
Est. Tokens~216k

Compatible Skills

These tools work well together with clawfu-skills for enhanced workflows:

  • skene-cookbook — semantic(0.39)+complementary+rare_topics+same_lang+similar_pop+shared_platform (68%)
  • ai-marketing-claude — semantic(0.35)+complementary+rare_topics+same_lang+similar_pop+shared_platform (62%)
  • Agentic-SEO-Skill — semantic(0.17)+complementary+rare_topics+same_lang+similar_pop+shared_platform (60%)

clawfu-skills alternative? Top 6 similar tools

Looking for a clawfu-skills alternative? If you're comparing clawfu-skills with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • Claude-Skills by borghei · ⭐ 475

    368 AI skills, 76 expert agents, and 859 stdlib Python tools for every team: engineering, PM, marketing, C-lev

  • marketplace by aiskillstore · ⭐ 419

    Security-audited skills for Claude, Codex & Claude Code. One-click install, quality verified.

  • claude-skills by OneWave-AI · ⭐ 247

    200+ production-ready Claude Code skills for sales, marketing, design, engineering, and AI agent architecture.

  • claudepro-directory by JSONbored · ⭐ 217

    HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve

  • AbsolutelySkilled by AbsolutelySkilled · ⭐ 182

    Awesome Skills from Around the World

  • skill-conductor by smixs · ⭐ 160

    Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-ca

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is clawfu-skills?

clawfu-skills is 172 expert marketing skills for AI agents — ClawFu MCP Server. It is categorized as a MCP Server with 145 GitHub stars.

What programming language is clawfu-skills written in?

clawfu-skills is primarily written in Python. It covers topics such as ai-skills, anthropic, claude-code.

How do I install or use clawfu-skills?

You can find installation instructions and usage details in the clawfu-skills GitHub repository at github.com/guia-matthieu/clawfu-skills. The project has 145 stars and 28 forks, indicating an active community.

What license does clawfu-skills use?

clawfu-skills is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to clawfu-skills?

The top alternatives to clawfu-skills on Agent Skills Hub include Claude-Skills, marketplace, claude-skills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools