Yao Meta Skill
When to Use
Use when this workflow matches the user request: Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.
Source: yaojingang/yao-meta-skill (MIT).
Router Rules
- Route by frontmatter
description.
- Keep
SKILL.md lean; put guidance in references/, logic in scripts/, and evidence in reports/.
- Use the lightest reliable process.
Modes
Scaffold: exploratory/personal. Production: team reuse. Library: shared infrastructure. Governed: high-trust, policy-sensitive, or release-critical.
- Rules: Method, Operating Modes, Resource Boundaries.
Compact Workflow
- For one-off/no reusable process:
Do not create a skill; near-neighbor; require repeated use + reusable output contract.
- Capture job, output, exclusions, constraints, standards, and the lightest fit.
- Scan references in order: external benchmark, user source, local fit; surface only uncertainty or conflict.
- Write
description early, test route quality, then add only earned folders and gates.
- Add output-risk, artifact-design, prompt-quality, system-model, and next directions only when useful.
Playbooks: Method, Intent, Skill IR, Output Eval, Review Studio.
Skill OS 2.0 Gates
For production, library, governed, or team-distributed work, run Skill IR, target compiler, trigger + output eval, Skill Atlas, conformance, trust, registry/package/install, upgrade, drift, waiver, and Review Studio gates before release.
Governed Package Boundary
For file-backed, release-critical, or governed packages, name input_files as file-backed fixture evidence; include owner, review cadence, input_files, output contract, rollback boundary; require trust report and reports/output_quality_scorecard.md; mark unavailable telemetry, approvals, metrics, or benchmarks as missing evidence; do not fabricate evidence.
Preserve audit 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
2-3 key questions unless enough detail exists.
- In Chinese, sound soft and companion-like; use Intent Dialogue.
Output Contract
Unless asked otherwise, produce SKILL.md, aligned agents/interface.yaml, justified assets, and a short summary of boundary, exclusions, gates, and next steps.
Reference Map
Primary: Method, Artifact Design, Systems Thinking, Governance, SkillOps Decision.
Limitations
- Requires the upstream tool, account, API key, or local setup when the workflow names one.
- Does not authorize destructive, production, paid, or external-message actions without explicit user approval.
- Validate generated artifacts or recommendations against the user's real sources before treating them as final.
1---2name: yao-meta-skill3description: Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.4metadata:5 source: https://skillmd.com/skills/yaojingang/yao-meta-skill6 author: Yao Team7category: "skill-authoring"8risk: "safe"9source: "community"10source_repo: "yaojingang/yao-meta-skill"11source_type: "community"12date_added: "2026-06-19"13author: "Yao Team"14license: "MIT"15license_source: "https://github.com/yaojingang/yao-meta-skill/blob/main/LICENSE"16tags:17 - skill-authoring18 - agent-skills19 - evaluation20 - packaging21tools:22 - claude-code23 - codex-cli24 - cursor25 - gemini-cli26---2728# Yao Meta Skill2930## When to Use3132Use when this workflow matches the user request: Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.333435_Source: [yaojingang/yao-meta-skill](https://github.com/yaojingang/yao-meta-skill) (MIT)._3637## Router Rules3839- Route by frontmatter `description`.40- Keep `SKILL.md` lean; put guidance in `references/`, logic in `scripts/`, and evidence in `reports/`.41- Use the lightest reliable process.4243## Modes4445- `Scaffold`: exploratory/personal. `Production`: team reuse. `Library`: shared infrastructure. `Governed`: high-trust, policy-sensitive, or release-critical.46- Rules: [Method](references/skill-engineering-method.md), [Operating Modes](references/operating-modes.md), [Resource Boundaries](references/resource-boundaries.md).4748## Compact Workflow49501. For one-off/no reusable process: `Do not create a skill`; `near-neighbor`; require `repeated use` + `reusable output contract`.512. Capture job, output, exclusions, constraints, standards, and the lightest fit.523. Scan references in order: external benchmark, user source, local fit; surface only uncertainty or conflict.534. Write `description` early, test route quality, then add only earned folders and gates.545. Add output-risk, artifact-design, prompt-quality, system-model, and next directions only when useful.5556Playbooks: [Method](references/skill-engineering-method.md), [Intent](references/intent-dialogue.md), [Skill IR](references/skill-ir-method.md), [Output Eval](references/output-eval-method.md), [Review Studio](references/review-studio-method.md).5758## Skill OS 2.0 Gates5960For production, library, governed, or team-distributed work, run Skill IR, target compiler, trigger + output eval, Skill Atlas, conformance, trust, registry/package/install, upgrade, drift, waiver, and Review Studio gates before release.6162## Governed Package Boundary6364For file-backed, release-critical, or governed packages, name `input_files` as `file-backed fixture` evidence; include `owner`, `review cadence`, `input_files`, `output contract`, `rollback boundary`; require `trust report` and `reports/output_quality_scorecard.md`; mark unavailable telemetry, approvals, metrics, or benchmarks as `missing evidence`; do not fabricate evidence.6566Preserve audit labels literally when they apply: `file-backed fixture`, `input_files`, `output contract`, `rollback boundary`, `trust report`, `reports/output_quality_scorecard.md`, `missing evidence`.6768## First-Turn Style6970- Start from the user's work/outcome before structure.71- Ask only `2-3` key questions unless enough detail exists.72- In Chinese, sound soft and companion-like; use [Intent Dialogue](references/intent-dialogue.md).7374## Output Contract7576Unless asked otherwise, produce `SKILL.md`, aligned `agents/interface.yaml`, justified assets, and a short summary of boundary, exclusions, gates, and next steps.7778## Reference Map7980Primary: [Method](references/skill-engineering-method.md), [Artifact Design](references/artifact-design-doctrine.md), [Systems Thinking](references/systems-thinking-doctrine.md), [Governance](references/governance.md), [SkillOps Decision](references/skillops-decision-policy.md).818283## Limitations8485- Requires the upstream tool, account, API key, or local setup when the workflow names one.86- Does not authorize destructive, production, paid, or external-message actions without explicit user approval.87- Validate generated artifacts or recommendations against the user's real sources before treating them as final.