Tools for creating, distilling, and managing AI Skills themselves — book→skill, repo→skill, codebase→skill, and cross-IDE skill sync. Meta-tools that build other skills.
Of the 25 skill creation & meta-tools here, the best one to start with is book-to-skill (rated SAFE by our security scan, ★ 36.9k). Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.
Skill Creation & Meta-Tools are AI-powered software designed to help developers and teams tackle skill creation & meta-tools-related tasks more efficiently. These tools are typically published as open-source projects on GitHub and can be integrated into existing workflows via MCP (Model Context Protocol), Claude Skills, or standalone agent frameworks. On Agent Skills Hub, we index 25 quality-scored Skill Creation & Meta-Tools across languages including Python, Shell, TypeScript.
In 2026, the AI agent ecosystem is maturing rapidly. Skill Creation & Meta-Tools can significantly boost development efficiency by automating repetitive tasks, reducing human error, and providing intelligent suggestions. The top 3 tools — skills, skill-based-architecture, skills-link — have earned an average of 3,441 GitHub stars, reflecting strong community validation. 19 of the listed tools come with clear open-source licenses, ensuring freedom to use and modify.
When choosing among Skill Creation & Meta-Tools, consider these factors: 1) Community activity — GitHub stars and recent commit frequency indicate reliability; 2) Integration method — check if it supports MCP, Claude, or your preferred agent framework; 3) Language compatibility — the most common language in this list is Python; 4) Quality score — Agent Skills Hub's composite score evaluates code quality, documentation completeness, and maintenance activity. Our recommendation: start with skills — it ranks highest in both star count and quality score.
301 open-source coding agent skills across 22 domains — methodology, judgment & gotchas packaged as Claude Agent Skills for the Asgard AI Platform.
A meta-skill that produces skills. Point it at any codebase and it distills the project's rules, workflows, and hard-won lessons into a dedicated skills/<name>/ directory — a project skill that becomes the single source of truth every AI agent (Cursor, Claude Code, Codex, Windsurf, Gemini) consults before every task.
/plugin marketplace add WoJiSama/skill-based-architecture
Sync your local skills across 41+ AI coding agents with a single command.
npm i -g skills-link
Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.
A standalone BMAD module that transforms code repositories, documentation websites, and developer discourse into agentskills.io-compliant, version-pinned, provenance-backed agent skills.
npx bmad-module-skill-forge install
The meta-skill that builds and improves all your skills, including itself. Watches your work sessions (autonomous or human-led), captures patterns, corrections and judgement calls, and turns them into skill improvements and new skill candidates for your review. Practical application of the Augmented Expertise methodology. Open source: CC BY 4.0.
A skill creator that proves its skills work. Evidence-driven skill creation for Claude Code and Codex: baseline-tested generation, per-skill regression evals, ecosystem doctor, cross-runtime compile, and an opt-in proactive advisor.
git clone https://github.com/tripleyak/SkillForge.git /tmp/skillforge
OpenClaw AI trading agents - Skill Forge, Chat, BankrBot, Polyclaw, Alpaca, Kalshi, Whale TrackingOpenClaw AI trading agents OpenClaw AI trading agents
git clone https://github.com/leionion/ClawForge.git
From thought to skill. From signal to structure.
npx skills add agentsope/SkillAlchemy
End-to-end Claude Code framework — orchestrates projects, workspace health, behavioral rules, ideation, audits, and skill creation from a single installer
npx @chrisai/skillsmith
SkillDock is an AI skill manager and skill management desktop app for Claude Code, Cursor, Codex, Windsurf, Gemini CLI, and other AI coding tools. Install, organize, edit, sync, and update Skills, MCP servers, and plugins with real-directory scanning and Git-aware Diff previews. AI Skill Manager / Skill 管理软件 / MCP 管理工具.
Ultimate Claude Code skill creator — design, scaffold, build, review, evolve, and publish production-grade AI agent skills
git clone https://github.com/AgriciDaniel/skill-forge.git
A modular framework for building intelligent AI agents powered by Claude, with rule-based workflows, skill management, and clean JS, TS architecture.
A Python framework for modular, self-contained skill management for machines.
pip install skillware
收录最全、更新最快的技能Skills商店：精选原创技能包（涵盖文档处理、内容创作、编程开发、机器学习、自动化工作流），全部打包好可直接安装使用！同时自动抓取GitHub上万个Skills项目，按分类、更新时间、Star数量整理。The most comprehensive and frequently updated AI Agent skill library, featuring curated skill packs across document processing, content creation, programming, machine learning, automated workflows, and many more domains.
git clone https://github.com/anbeime/skill.git
🤖 CLI for creating Claude Agent Skills with progressive disclosure validation. Built for Claude Code to use when humans ask it to create skills.
Installable agent skills for browser automation, local knowledge, skill management, external CLI workflows, and session handoffs.
npx skills add Advai-X/advai-skills
Open-source agent skills by Testany: engineering, prompts, content, testing, and SkillDock for visual Codex skill management.
/plugin marketplace add TestAny-io/testany-agent-skills
基于 Claude Code 官方 skill-creator，我融入了自己对提示词架构、Skill 架构以及 CLI 工具运行机制的理解，对其进行了全面重构，打造了一个新版 Skill Creator。 在测评环节，我采用 Codex 的 Headless 模式（无需打开图形界面，直接在终端执行）进行了三轮以上的独立对话测试。测试结果显示，新版在各项维度上全面超越原版。完整的测试标准与评测报告已归档至「测评报告」文件夹，可供参考。 此外，新版在可维护性上也有显著提升——原版 Skill 一旦生成，提示词后续极难修改和维护；而新版的架构设计使得迭代和调整更加便捷，也更利于团队协作和长期维护。欢迎 star，作者 vx：yinyinGyL
git clone https://github.com/DazhuangJammy/DazhuangSkill-Creator.git
Distilly — Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill（原同事 Skill）.
git clone https://github.com/titanwings/distilly <DISTILLY_SKILL_DIR>
Comet: agent skill harness for turning ideas into evaluated workflows
npm install -g @rpamis/comet
YAO = Yielding AI Outcomes. A rigorous engineering, evaluation, governance, and portability system for reusable agent skills.
把工作流变成可研究、可评测、可发布的乔木 Agent Skill | Turn workflows into researched, tested, release-ready agent skills.
npx skills add joeseesun/qiaomu-meta-skill
| Tool | Stars | Score |
|---|---|---|
| skills | ★ 243 | 62 |
| skill-based-architecture | ★ 597 | 69 |
| skills-link | ★ 197 | 55 |
| book-to-skill | ★ 36.9k | 84 |
| bmad-module-skill-forge | ★ 100 | 62 |
| skillify-for-codex | ★ 0 | 50 |
| one-skill-to-rule-them-all | ★ 3.7k | 77 |
| SkillForge | ★ 914 | 76 |
| ClawForge | ★ 89 | 61 |
| SkillAlchemy | ★ 446 | 62 |
| skillsmith | ★ 141 | 51 |
| skill-builder | ★ 113 | 48 |
| skilldock | ★ 611 | 66 |
| skill-forge | ★ 187 | 72 |
| Class-AI-Agent | ★ 267 | 55 |
| skillware | ★ 170 | 66 |
| skill | ★ 9.2k | 73 |
| claude-skills-cli | ★ 88 | 66 |
| advai-skills | ★ 73 | 70 |
| testany-agent-skills | ★ 82 | 61 |
The top skill creation & meta-tools in 2026 are skills, skill-based-architecture, skills-link. Agent Skills Hub ranks 25 options by GitHub stars, quality score (6 dimensions including completeness, examples, and agent readiness), and recent activity. The list is rebuilt every 8 hours from live GitHub data.
skills (243 stars) is the most adopted choice for general skill creation & meta-tools workflows, written in Python. skill-based-architecture (597 stars) is a strong alternative and uses Shell instead. Pick by your existing stack: match the language and runtime your team already uses to minimize integration cost. If unsure, start with skills — it has the deepest community and the most examples online.
Avoid pre-built skill creation & meta-tools when (1) your use case requires deep customization that the tool's plugin system doesn't support, (2) you have strict compliance requirements that ban third-party dependencies, (3) the tool's maintenance is inactive (last commit >6 months ago), or (4) your data volume is small enough that a 50-line custom script is cheaper than learning the tool. For most production workflows above 100 requests/day, the time savings from a maintained tool outweigh the customization loss.
Skill Creation & Meta-Tools focuses specifically on tools for creating, distilling, and managing ai skills themselves — book→skill, repo→skill, codebase→skill, and cross-ide skill sync. meta-tools that build other skills. Claude Code Skills is a related but distinct category — see https://agentskillshub.top/best/claude-code-skills/ for those tools. The two often appear in the same agent pipeline but solve different problems: choose skill creation & meta-tools when your primary goal is the specific task, and claude code skills when the workflow is broader.
For most teams, yes. skills has 243 stars worth of community testing, handles edge cases you haven't thought of, and ships with documentation. Build your own only when (1) your requirements are deeply non-standard, (2) you have a security/compliance reason to avoid OSS dependencies, or (3) the maintenance burden is small enough (<200 lines of code) that you'll save time long-term. The break-even point is usually around 2-3 weeks of dev time saved.
Most skill creation & meta-tools listed are open source under permissive licenses (MIT, Apache 2.0). A handful offer paid managed/cloud versions on top of free self-hosted core. Always check the LICENSE file on each tool's GitHub repository before commercial use — some use AGPL or non-commercial restrictions that may not fit your deployment model.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: