# yaojingang/yao-meta-skill

YAO = Yielding AI Outcomes. A rigorous engineering, evaluation, governance, and portability system for reusable agent skills.

Repository: https://github.com/yaojingang/yao-meta-skill
Canonical: https://ross.abutalabs.com/products/yao-meta-skill
Homepage: https://github.com/yaojingang/yao-meta-skill#readme
Language: Python
License: MIT
License Family: permissive
Topics: agent-skills, ai-agents, meta-skill, skill-engineering, workflow-automation, evaluation, governance, portability
Last push: 2026-08-17T09:19:43+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 35, longevity 11
- inputs: {"age_days": 155, "days_push": 16, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2521, forks 239 (observed 2026-08-28T04:06:58.235872+00:00)

## What it is
Yao Meta Skill (YAO = Yielding AI Outcomes) is a Python-based system for engineering, evaluating, packaging, and governing reusable AI agent skills. It provides a platform-neutral Skill IR, target compilers for OpenAI/Claude/VS Code surfaces, an evaluation lab, and release governance gates forming a 'Skill OS' lifecycle.

## Use cases
- turn repeated workflows into installable agent skill packages
- compile one skill definition for multiple AI agent platforms
- evaluate and benchmark agent skill behavior before release
- govern skill releases with evidence and review gates
- package reusable prompts as cross-platform AI assets
- track adoption drift and iterate on agent skills

## When to choose
- you build many AI agent skills and need a repeatable engineering pipeline
- you want one skill definition compiled to OpenAI, Claude, and other agent targets
- you need evaluation, benchmarking, and release governance for LLM skill packages

## When to avoid
- you just need a single one-off prompt with no reuse
- you want a general agent runtime rather than a skill authoring/governance system
- you need a production agent orchestration framework with tool calling built in

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, prompt-engineering, testing, workflow-automation, developer-tools
- domain: large-language-models, developer-tools
- platform: python, cli, cross-platform
- tags: agent-skills, skill-engineering, skill-ops, evaluation, governance, meta-skill, skill-packaging, llm-workflows, ai-agents, automation

## Member repositories
- yaojingang/yao-meta-skill (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:58.235872+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:26:05.407803+00:00, confidence not recorded.
  - readme: https://github.com/yaojingang/yao-meta-skill (fetched 2026-08-28T04:06:58.235872+00:00, sha 477cdbf41e56)
  - homepage: https://github.com/yaojingang/yao-meta-skill#readme (fetched 2026-08-29T10:08:11.178475+00:00, sha 7172b50bbb61)
- Data as of 2026-08-30T08:39:29.467469+00:00.