Yao Meta Skill
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.
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.4---5
6# Yao Meta Skill
7
8## Router Rules
9
10- Route by frontmatter `description`.
11- Keep `SKILL.md` lean; put guidance in `references/`, logic in `scripts/`, and evidence in `reports/`.
12- Use the lightest reliable process.
13
14## Modes
15
16- `Scaffold`: exploratory/personal. `Production`: team reuse. `Library`: shared infrastructure. `Governed`: high-trust, policy-sensitive, or release-critical.
17- Rules: [Method](references/skill-engineering-method.md), [Operating Modes](references/operating-modes.md), [Resource Boundaries](references/resource-boundaries.md).
18
19## Compact Workflow
20
211. For one-off/no reusable process: `Do not create a skill`; `near-neighbor`; require `repeated use` + `reusable output contract`.
222. Capture job, output, exclusions, constraints, standards, and the lightest fit.
233. Scan references in order: external benchmark, user source, local fit; surface only uncertainty or conflict.
244. Write `description` early, test route quality, then add only earned folders and gates.
255. Add output-risk, artifact-design, prompt-quality, system-model, and next directions only when useful.
26
27Playbooks: [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).
28
29## Skill OS 2.0 Gates
30
31For 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.
32
33## Governed Package Boundary
34
35For 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.
36
37Preserve audit labels literally when they apply: `file-backed fixture`, `input_files`, `output contract`, `rollback boundary`, `trust report`, `reports/output_quality_scorecard.md`, `missing evidence`.
38
39## First-Turn Style
40
41- Start from the user's work/outcome before structure.
42- Ask only `2-3` key questions unless enough detail exists.
43- In Chinese, sound soft and companion-like; use [Intent Dialogue](references/intent-dialogue.md).
44
45## Output Contract
46
47Unless asked otherwise, produce `SKILL.md`, aligned `agents/interface.yaml`, justified assets, and a short summary of boundary, exclusions, gates, and next steps.
48
49## Reference Map
50
51Primary: [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).
aiskillstore