SkillAlchemy — security grade SAFE, quality 58/100

Security audit verdict: SAFE · quality 58/100

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 agentsope · Agent Tool · ★ 351

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

🔒 Is SkillAlchemy safe to install? View the security audit →

About SkillAlchemy

SkillAlchemy 一念落地,万象成形 把人物、方法和经验转化为可安装、可复用的 Agent Skill。 English · 中文 项目简介 创建可靠的 Skill 不只是总结资料。系统需要发现任务描述中遗漏的条件, 从公开来源中提取可执行步骤,并判断每条经验可以复用到多大的范围。 SkillAlchemy 支持三类任务: 蒸馏人物:从公开资料中提取决策方式、失败处理、价值取舍和表达特点,生成 Persona Skill。 蒸馏方法:将书籍、方法论、开源仓库或访谈整理为包含条件、步骤、分支和失败处理的可执行 Skill。 融合 Skill:组合已有 Skill 的工作流程与领域视角,形成新的复合能力。 安装 安装完整的 SkillAlchemy 工作流: 也可以直接告诉 Claude Code 或 Codex: 也可以单独安装核心组件: 安装仓库中其他 Skill: 浏览仓库中的全部 Skills 快速开始 安装后,直接告诉 Claude Code 或 Codex 你想蒸馏或融合什么。例如: SkillAlchemy 先用 Lens

agent-skillagent-skillsai-agentllm-agentskill-acquisitionskill-constructionskill-creationskill-engineeringskill-generationskill-pipeline

Quick Facts

Stars351
Forks19
LanguagePython
CategoryAgent Tool
LicenseMIT
Quality Score58.3952502893429/100
Last Updated2026-09-02
Created2026-05-20
Platformsnode, python
Est. Tokens~13k

Compatible Skills

These tools work well together with SkillAlchemy for enhanced workflows:

  • bria-skill — semantic(0.36)+complementary+same_lang+similar_pop+shared_platform (63%)
  • skill-optimizer — semantic(0.36)+complementary+same_lang+similar_pop+shared_platform (63%)
  • colin — semantic(0.29)+complementary+same_lang+similar_pop+shared_platform (60%)

SkillAlchemy alternative? Top 6 similar tools

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

  • agent-skills by oxylabs · ⭐ 875

    Official Agent skills of Oxylabs products

  • awesome-openclaw by SamurAIGPT · ⭐ 957

    A curated list of OpenClaw resources, tools, skills, tutorials & articles. OpenClaw (formerly Moltbot / Clawdb

  • comfyui-mcp by artokun · ⭐ 745

    Local-first, agent-native control plane for ComfyUI — MCP server + sidebar agent that generates images, video

  • wcgw by rusiaaman · ⭐ 674

    Shell and coding agent on mcp clients

  • compose-skill by aldefy · ⭐ 561

    Jetpack Compose Agent Skill — AI-powered coding guidance with actual androidx/androidx source code receipts. W

  • mcp-google-map by cablate · ⭐ 457

    A powerful Model Context Protocol (MCP) server providing comprehensive Google Maps API integration with LLM pr

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is SkillAlchemy?

SkillAlchemy is From thought to skill. From signal to structure.. It is categorized as a Agent Tool with 351 GitHub stars.

What programming language is SkillAlchemy written in?

SkillAlchemy is primarily written in Python. It covers topics such as agent-skill, agent-skills, ai-agent.

How do I install or use SkillAlchemy?

You can find installation instructions and usage details in the SkillAlchemy GitHub repository at github.com/agentsope/SkillAlchemy. The project has 351 stars and 19 forks, indicating an active community.

What license does SkillAlchemy use?

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

What are the best alternatives to SkillAlchemy?

The top alternatives to SkillAlchemy on Agent Skills Hub include agent-skills, awesome-openclaw, comfyui-mcp. 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 Agent Tool tools