YAO = Yielding AI Outcomes. A rigorous engineering, evaluation, governance, and portability system for reusable agent skills.
From thought to skill. From signal to structure.
Engineer production-ready Codex skills with behavior contracts, quality lint, and forward testing / 将 Skill 构建从 vibe prompting 变成工程化流程
12 evidence-backed skill-writing principles plus repository engineering for real-world agent skills, inspired by Matt Pocock / 十二条有证据支撑的 Skill 写作原则与仓库工程指南
Turn goals, existing Skills, and authorized work records into bounded Agent Loops, then export a Codex Skill or Compact Prompt with separate verifiable evidence.
Audit any Claude Code SKILL.md file. Scored report with critical issues, triggering score, and exact fixes. Free skill-engineering tool by Anvil & Code.
Production-grade Claude Code skill engineering tools. Scaffolder, validator, security auditor, tester, optimizer and more. Build once, ship reliably.
Optimize Claude Code SKILL.md description fields for maximum trigger reliability. 3 scored variants, clear recommendation. Free skill-engineering tool by Anvil & Code.
三线 Agent Skill 体系——47 个原子技能。这不是一份技能清单，而是一套方法论的沉淀：让 AI 助手在「软件开发生命周期」、「知识管理」与「陌生领域学习」三条工作流上，每次都以相同的过程工作。
Meta-skills for creating, reviewing, and maintaining production-quality Agent Skills.
AI Skill 的开发工作台与工厂机制（冻结思想展示版）——开发态/发布态分离、配置驱动多 Agent 分发、四个元 skill 方法论。
Skill Engineering Stack v5.5 — A multi-pass compiler that transforms natural-language sources into formal, typed, executable generative models
7-Aspects for AI Agent Skill Engineering — VDA 6.3 Process Turtle Diagram framework for systematic Skill design and evaluation (CN/EN)
Edge AIOps — Multi-Agent Incident Response for Edge + AI Fleets (AgentTeams). Demo for Agent Infra competition.
To associate your repository with the skill-engineering topic, visit your repo's landing page and select "manage topics."