Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.
How to install yao-meta-skill?
yaojingang/yao-meta-skill
$npx -y skills add yaojingang/yao-meta-skill --skill yao-meta-skillInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Run `npx skills use "https://github.com/yaojingang/yao-meta-skill" --skill "yaojingang/yao-meta-skill"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/yaojingang/yao-meta-skill" that are relevant to the current task. Run `npx skills add "https://github.com/yaojingang/yao-meta-skill"` and select the relevant skills, then follow their instructions.
SKILL.md
| 1 | # Yao Meta Skill |
| 2 | |
| 3 | [](https://github.com/yaojingang/yao-meta-skill/actions/workflows/test.yml) |
| 4 | [](LICENSE) |
| 5 | [](README.md) |
| 6 | [](docs/README.zh-CN.md) |
| 7 | [](docs/README.ja-JP.md) |
| 8 | [](docs/README.fr-FR.md) |
| 9 | [](docs/README.ru-RU.md) |
| 10 | |
| 11 | `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. |
| 12 | |
| 13 | `yao-meta-skill` creates, evaluates, packages, and governs reusable agent skills. The 1.0 line focused on turning repeated workflows into installable, readable, cross-platform skill packages. The 2.0 line expands that factory into a Skill OS: a governed system for modeling a skill once, compiling it for multiple targets, testing its behavior, reviewing its release evidence, and tracking the next iteration. |
| 14 | |
| 15 | [Quick Start](#quick-start) · [Skill OS 2.0](#skill-os-20-upgrade) · [1.0 vs 2.0](#from-10-to-20) · [Operator UX](#operator-ux-commands) · [Benchmark](#weighted-quality-benchmark) · [Examples](examples/README.md) · [Evals](evals/README.md) · [Failure Library](failures/README.md) · [Method Doctrine](#method-doctrine) |
| 16 | |
| 17 | ## Skill OS 2.0 Upgrade |
| 18 | |
| 19 | Skill OS 2.0 keeps the original promise of `yao-meta-skill`, but makes the package lifecycle more explicit. Instead of stopping at `SKILL.md`, it adds a semantic contract, target compilers, evaluation evidence, release gates, and operation reports around the skill. |
| 20 | |
| 21 | - **Skill IR**: a platform-neutral intermediate representation for intent, triggers, inputs, outputs, boundaries, references, and expected artifacts. |
| 22 | - **Target compilers and adapters**: generated surfaces for OpenAI, Claude, generic agent skills, Agent Skills compatible packages, and VS Code-oriented workflows. |
| 23 | - **Output Eval Lab**: trigger checks, output assertions, execution evidence, timing and token evidence, benchmark reproducibility, blind-review packs, answer keys, and adjudication reports. |
| 24 | - **Review Studio 2.0**: a single HTML gate page for intent, triggers, output eval, context cost, runtime checks, trust, Skill Atlas signals, adoption drift, waivers, annotations, release evidence, warnings, blockers, and fix actions. |
| 25 | - **Evidence and release governance**: evidence consistency checks, package verification, install simulation, runtime permission probes, world-class evidence intake, world-class ledger, operator runbook, and public claim guard. |
| 26 | - **SkillOps loop**: metadata-only adoption drift, telemetry hooks, adaptive proposals, daily and weekly curator reports, and portfolio-level drift signals. |
| 27 | |
| 28 | Current posture: the repository is ready for beta and external testing, while stronger public "world-class" claims remain evidence-gated. Provider-backed production evidence, human blind-review evidence, native permission execution, and real-client telemetry are tracked as separate evidence tasks instead of being treated as completed work. |
| 29 | |
| 30 | See the companion artifacts: |
| 31 | |
| 32 | - [Visual 1.0 vs 2.0 comparison report](.previews/yao-meta-skill-2-comparison/index.html) |
| 33 | - [Chinese desktop preview](.previews/yao-meta-skill-2-comparison/yao-meta-skill-1-vs-2.png) |
| 34 | - [English desktop preview](.previews/yao-meta-skill-2-comparison/yao-meta-skill-1-vs-2-en.png) |
| 35 | |
| 36 | ## From 1.0 to 2.0 |
| 37 | |
| 38 | | Dimension | 1.0 focus | 2.0 upgrade | |
| 39 | | --- | --- | --- | |
| 40 | | Product role | Create, refactor, evaluate, and package reusable skills. | Govern the full lifecycle of a skill: creation, compilation, evaluation, review, release, telemetry, and iteration. | |
| 41 | | Architecture | `SKILL.md`, `agents/in |
Related
6 picksType
- cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy.Jul 2026
- lark-im飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件（支持大文件分片下载）、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive…Jul 2026
- lark-calendar飞书日历：管理日历日程和会议室。查看/搜索日程、创建/更新日程、管理参会人、查询忙闲和推荐时段、预定会议室。当用户需要查看日程安排、创建/修改会议、查询/预定会议室时使用。不负责：查询过去的视频会议记录（走 lark-vc）、待办任务（走 lark-task）。Jul 2026
- lark-contact飞书 / Lark 通讯录:按姓名 / 邮箱解析成 open_id,或按 open_id 反查姓名 / 部门 / 邮箱 / 联系方式 / 个人状态 / 签名。当用户提到某人姓名要下一步发消息 / 排日程,或拿到 open_id 想查具体信息时使用。不负责部门树遍历、按部门列员工、组织架构图,这类需求走原生…Jul 2026
- lark-workflow-meeting-summary会议纪要整理工作流：汇总指定时间范围内的会议纪要并生成结构化报告。当用户需要整理会议纪要、生成会议周报、回顾一段时间内的会议内容时使用。Jul 2026
- lark-workflow-standup-report日程待办摘要：编排 calendar +agenda 和 task +get-my-tasks，生成指定日期的日程与未完成任务摘要。适用于了解今天/明天/本周的安排。Jul 2026
