yao-meta-skill
YAO is a system for creating, evaluating, and managing reusable AI skills.
- Type
- Agent Skill
- Open source
- Yes
- GitHub Stars
- ★ 1.6k
- Source
- skill-github
- Repository
- github.com/yaojingang/yao-meta-skill
Overview
YAO (Yielding AI Outcomes) is a rigorous engineering, evaluation, governance, and portable system for creating, evaluating, and managing reusable AI skills. It provides a complete lifecycle management system covering skill creation, compilation, evaluation, review, publication, and iteration. With YAO, users can transform repetitive workflows into installable, readable, and cross-platform skill packages, supporting compilation and adaptation across multiple target platforms. Ideal for developers and teams building and managing complex AI skills.
Capabilities
- ▪Create reusable AI skills
- ▪Evaluate and test skill behavior
- ▪Multi-target platform compilation and adaptation
- ▪Generate detailed evaluation reports
- ▪Manage and track skill iterations
Use cases
Setup
Please follow the quick start guide in the project documentation for installation and configuration.
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
Which target platforms does YAO support?
Supports OpenAI, Claude, general agent skills, and more.
How do I get started with YAO?
Please refer to the quick start guide in the project documentation.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
private-gpt
Provides a complete API layer for local models, supporting RAG, skills, tools, and more.
planning-with-files
File-based persistent planning skill, ideal for AI coding agents and long-running tasks.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.