yao-meta-skill
GitHub用于创建、优化和评估 Agent Skill 的元技能。支持从工作流或脚本生成 Skill，涵盖脚手架、生产发布及治理模式。提供触发器评测、输出合约验证及安全边界检查，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\/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."
}
Yao Meta Skill
Router Rules
- Route by frontmatter
description. - Keep
SKILL.mdlean; put guidance inreferences/, logic inscripts/, and evidence inreports/. - Use the lightest reliable process.
Modes
Scaffold: exploratory/personal.Production: team reuse.Library: shared infra.Governed: high-trust/release-critical.- Rules: Method, Operating Modes, Resource Boundaries.
Compact Workflow
- One-off/no reusable process:
Do not create a skill;near-neighbor; requirerepeated use+reusable output contract. - Capture job, output, exclusions, constraints, standards, lightest fit.
- Scan up to
3-5references: external, user, local; skip tiny edits; surface only uncertainty/conflict. - Write
descriptionearly; route/boundary edits needtrigger_eval.py; releases need risk-matched gates before folders. - Add output-risk, artifact-design, prompt-quality, system-model, next directions only when earned.
Playbooks: Method, Intent, Skill IR, Output Eval, Review Studio.
Skill OS 2.0 Gates
For production/library/governed/team releases, run Skill IR, compiler, trigger/output eval, Skill Atlas, conformance, trust, registry/package/install, upgrade, drift, waiver, Review Studio.
Governed Package Boundary
For file-backed/release-critical/governed packages, name input_files as file-backed fixture; include owner, review cadence, input_files, output contract, rollback boundary; require trust report and reports/output_quality_scorecard.md; mark unavailable telemetry/approvals/metrics/benchmarks as missing evidence; do not 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
- Start from the user's work/outcome before structure.
- Ask only
2-3key questions unless enough detail exists. - In Chinese, sound soft and companion-like; use Intent Dialogue.
Output Contract
Create/refactor/package: produce SKILL.md, aligned agents/interface.yaml, justified assets, boundary/exclusion/gate summary. Audit/evaluate-only: findings + proposed fixes; edit files only if asked. No-skill: no files.
Reference Map
Primary: Method, Artifact Design, Systems, Governance, SkillOps.
Version History
- c37915e Current 2026-07-05 12:03
