yao-meta-skill
GitHub用于创建、改进或评估 Agent Skill 的元技能，涵盖脚手架、发布及评测流程。支持自适应意图澄清与自更新机制，确保 Skill 的可复用性与合规性。
Trigger Scenarios
Install
npx skills add yaojingang/yao-meta-skill --skill yao-meta-skill -g -y
SKILL.md
Frontmatter
{
"name": "yao-meta-skill",
"metadata": {
"author": "Yao Team"
},
"description": "Create, improve, or evaluate an existing skill from workflows, prompts, SOPs, scripts. Use for migration\/release\/package, routing, evals\/tests, install\/trust checks, 优化已有 skill, 补 trigger 评测. Exclude summary\/translation\/docs, brainstorming, one-off prompts, copy-only edits, outline-only requests."
}
Yao Meta Skill
Router Rules
- Route by frontmatter
descriptionusing the lightest mode. - Keep
SKILL.mdlean: guidance inreferences/, logic inscripts/, evidence inreports/.
Modes
Scaffold: exploratory;Production: team;Library: shared;Governed: release-critical.- Rules: Method, Modes, Boundaries.
Compact Workflow
- Require
repeated use+reusable output contract; skip one-offs. - Lock target path + identity before writes; self-edits require
--self. - Capture job, output, exclusions, constraints, standards, mode.
- Scan
3-5useful external/user/local references. - Write
descriptionearly; route edits needtrigger_eval.py; release gates follow risk. - Add deeper profiles only when earned.
Playbooks: Target Safety, Intent, Skill IR, Output Eval, Review Studio.
Updates
Activation: scripts/yao.py check-update --notice --self; show notice_text if requested; continue. “更新”: scripts/yao.py self-update --self --yes.
Skill OS 2.0 Gates
For production/library/governed releases, run Skill IR, compiler, trigger/output eval, Atlas, conformance, trust, package/install, upgrade, drift, waiver, Review Studio.
Governed Package Boundary
Governed/file-backed packages: label input_files a file-backed fixture; include owner, review cadence, output contract, rollback boundary; require trust report and reports/output_quality_scorecard.md; mark unavailable telemetry/approvals/metrics/benchmarks as missing evidence; never fabricate evidence.
Preserve labels literally when they apply: file-backed fixture, input_files, output contract, rollback boundary, trust report, reports/output_quality_scorecard.md, missing evidence.
First-Turn Style
- Infer non-core gaps; ask one core-fork question per round, max two, then use recorded preferred inference.
- In Chinese, sound soft and companion-like; use Intent Dialogue.
Output Contract
Builds: SKILL.md, aligned interface, justified assets, boundary/gate summary. Audits: findings + fixes; edit only when asked. No-skill: no files.
Reference Map
Primary: Method, Artifact Design, Systems, Governance, SkillOps.
Version History
-
f5d8f68
Current 2026-08-19 14:41
新增自适应意图澄清功能，支持通过脚本验证自更新并升级至2.1.0版本；强化治理包边界与安全门禁要求。
- c37915e 2026-07-05 12:03
