soul.md — security grade CAUTION, quality 67/100

Security audit verdict: CAUTION · quality 67/100

Flagged: reads agent memory. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by aeonfun · Claude Skill · ★ 687

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

🔒 Is soul.md safe to install? View the security audit →

About soul.md

SOUL.MD The best way to build a personality for your agent. Let Claude Code / OpenClaw ingest your data & build your AI soul. Best used with Aeon — background intelligence that evolves with you. What Is This? A soul file captures who you are in a format AI agents can embody. Not a chatbot that talks about you — an AI that thinks and speaks as you. Dump your tweets, essays, and posts into a folder. The agent reads everything, extracts you

agentsclaude-codeclaude-code-skillclaude-skillsopenclawsecond-brainsoul

Quick Facts

Stars687
Forks75
LanguageJavaScript
CategoryClaude Skill
LicenseMIT
Quality Score67.256496162011/100
Last Updated2026-09-07
Created2026-02-02
Platformsclaude-code, node
Est. Tokens~17k

Compatible Skills

These tools work well together with soul.md for enhanced workflows:

  • soul.md — semantic(1.00)+rare_topics+same_lang+similar_pop+shared_platform (65%)
  • SkillCompass — semantic(0.25)+complementary+same_lang+similar_pop+shared_platform (59%)
  • souls-directory — semantic(0.39)+complementary+rare_topics+similar_pop+shared_platform (58%)
  • ai-agent-team — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (58%)
  • everything-claude-code-zh — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (58%)

soul.md alternative? Top 6 similar tools

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

  • soul.md by aaronjmars · ⭐ 606

    The best way to build a personality for your agent. Let Claude Code / OpenClaw ingest your data & build your A

  • developer-kit by giuseppe-trisciuoglio · ⭐ 343

    Modular plugin marketplace for Claude Code and agentic CLIs, with validated, spec-driven skills, agents, comma

  • souls-directory by thedaviddias · ⭐ 155

    🧠 Directory of SOUL.md personality files for OpenClaw agents

  • skillshare by runkids · ⭐ 2.8k

    📚 Sync skills, agents, MCP, plugins to all AI CLI tools with one command and simplify team sharing.

  • terraform-skill by antonbabenko · ⭐ 2.4k

    Terraform & OpenTofu Skill for AI Agents - testing, modules, CI/CD, and production patterns

  • claude-blog by AgriciDaniel · ⭐ 2.3k

    Claude Code blog skill suite: 30 sub-skills, 5 agents, 5-gate v1.9.0 Blog Delivery Contract, dual-optimized fo

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular JavaScript Agent Tools

Frequently Asked Questions

What is soul.md?

soul.md is The best way to build a personality for your agent. Let Claude Code / OpenClaw ingest your data & build your AI soul.. It is categorized as a Claude Skill with 687 GitHub stars.

What programming language is soul.md written in?

soul.md is primarily written in JavaScript. It covers topics such as agents, claude-code, claude-code-skill.

How do I install or use soul.md?

You can find installation instructions and usage details in the soul.md GitHub repository at github.com/aeonfun/soul.md. The project has 687 stars and 75 forks, indicating an active community.

What license does soul.md use?

soul.md is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to soul.md?

The top alternatives to soul.md on Agent Skills Hub include soul.md, developer-kit, souls-directory. 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 Claude Skill tools