yaojingang/yao-meta-skill
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.
npx skills add https://github.com/yaojingang/yao-meta-skill --skill yao-meta-skill
description.SKILL.md lean; put guidance in references/, logic in scripts/, and evidence in reports/.Scaffold: exploratory/personal. Production: team reuse. Library: shared infra. Governed: high-trust/release-critical.Do not create a skill; near-neighbor; require repeated use + reusable output contract.3-5 references: external, user, local; skip tiny edits; surface only uncertainty/conflict.description early; route/boundary edits need trigger_eval.py; releases need risk-matched gates before folders.Playbooks: Method, Intent, Skill IR, Output Eval, Review Studio.
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.
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.
2-3 key questions unless enough detail exists.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.
Primary: Method, Artifact Design, Systems, Governance, SkillOps.
Take yaojingang/yao-meta-skill from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.