Claude Skill
yaojingang/yao-meta-skill
YAO (Yielding AI Outcomes) is a rigorous system for engineering, evaluating, governing, and porting reusable agent skills. Build reliable, cross-platform AI agents with structured skill design and...
Overview
Repository
Install this Skill
git clone https://github.com/yaojingang/yao-meta-skill.gitRegistry
Summary
YAO (Yielding AI Outcomes) is a rigorous engineering, evaluation, governance, and portability system for reusable agent skills. It provides a structured framework to design, test, and deploy AI agent skills with high reliability and cross-platform compatibility.
YAO = 可产出AI成果。一个针对可复用智能体技能的严谨工程、评估、治理与可移植性系统。
Key features
- Skill engineering with structured design patterns
- Built-in evaluation and governance mechanisms
- Portability across different agent platforms
- Workflow automation support for agent skills
- Meta-skill abstraction for reusable components
Use cases
- Building reliable AI agents for enterprise workflows
- Creating portable agent skills that work across platforms
- Evaluating and governing agent skill performance
- Automating complex multi-step agent tasks
- Developing reusable skill libraries for AI teams
README excerpt
# Yao Meta Skill [](https://github.com/yaojingang/yao-meta-skill/actions/workflows/test.yml) [](LICENSE) [](README.md) [](docs/README.zh-CN.md) [](docs/README.ja-JP.md) [](docs/README.fr-FR.md) [](docs/README.ru-RU.md) `YAO` stands for `Yielding AI Outcomes` — the goal is not to generate more prompt text, but to produce reusable AI assets and real operational outcomes. `yao-meta-skill` is a lightweight but rigorous system for creating, evaluating, packaging, and governing reusable agent skills. [Quick Start](#quick-start) · [Examples](examples/README.md) · [Evals](evals/README.md) · [Failure Library](failures/README.md) · [Method Doctrine](#method-doctrine) It turns rough workflows, transcripts, prompts, notes, and runbooks into reusable skill packages with: - a clear trigger surface - a lean `SKILL.md` - optional references, scripts, and evals - a front-loaded intent dialogue with an intent confidence gate, so the system keeps clarifying when the true job, outputs, exclusions, or standards are still fuzzy - a silent-by-default GitHub benchmark scan plus reference synthesis that studies top public repositories and world-class pattern tracks, then surfaces only real conflicts or uncertainty to the user - a generated visual HTML overview for each newly initialized