mcpField
Y
yao-meta-skill

yao-meta-skill

github.com/yaojingangAgent workflows2.7k670 installsUpdated 10w ago
Repository

About yao-meta-skill

Yao Meta Skill is a system for engineering, evaluating, governing, and packaging reusable agent skills. It defines modes and release gates, with workflows for evidence, output quality, trust, and package lifecycle checks.

Key features

  1. 01Scaffold, Production, Library, and Governed modes
  2. 02Reusable-skill qualification and workflow
  3. 03Skill IR and evaluation gates
  4. 04Governance and trust evidence requirements
  5. 05Package, install, upgrade, and drift checks

Use cases

  1. 01Scaffolding a reusable agent skill
  2. 02Preparing a skill for production or library release
  3. 03Auditing skill outputs and trust evidence
  4. 04Managing governed, file-backed packages

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/yaojingang/yao-meta-skill --skill yao-meta-skill

After installing, type/yao-meta-skillin Claude Code to confirm it loaded.

Details

From the project README

Yao Meta Skill

Router Rules

  • Route by frontmatter description using the lightest mode.
  • Keep SKILL.md lean: guidance in references/, logic in scripts/, evidence in reports/.

Modes

  • Scaffold: exploratory; Production: team; Library: shared; Governed: release-critical.
  • Rules: Method, Modes, Boundaries.

Compact Workflow

  1. Require repeated use + reusable output contract; skip one-offs.
  2. Lock target path + identity before writes; self-edits require --self.
  3. Capture job, output, exclusions, constraints, standards, mode.
  4. Scan 3-5 useful external/user/local references.
  5. Write description early; route edits need trigger_eval.py; release gates follow risk.
  6. 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.

Comments

Markdown supported