yao-meta-skill
The yao-meta-skill provides a framework for creating, refactoring, evaluating, and packaging AI agent skills. It enforces structured workflows for skill development, ranging from exploratory scaffolding to governed, team-ready production releases.
Is yao-meta-skill safe to install?
Safe to install: our audit of yao-meta-skill's source files found 0 shell commands, 0 external URLs, file reads and writes (low risk). Every command and URL listed appears verbatim in the skill's source. The skill operates by reading and writing local project files, including SKILL.md, interface.yaml, and various reference documents. It does not execute shell commands or perform network requests.
How we audit skills: our security review methodology.
Who is this skill for?
Developers and teams building, maintaining, and distributing reusable AI agent skills.
What can you do with it?
- Scaffolding new agent skills from workflows or documentation
- Refactoring existing prompts and logic into reusable packages
- Evaluating skill output quality through standardized gates
- Packaging skills for team distribution with governance and audit requirements
How good is this skill?
Quality score: 9/10. The skill documentation is highly structured and provides clear operational guidelines. It lacks specific implementation code, focusing instead on the methodology and governance framework.
What does the skill file contain?
# 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](references/skill-engineering-method.md), [Operating Modes](references/operating-modes.md), [Resource Boundaries](references/resource-boundaries.md). ## Compact Workflow 1. For one-off/no reusable ...
Frequently asked questions
What output does the skill generate by default?
It produces a SKILL.md file, an aligned agents/interface.yaml file, justified assets, and a summary covering boundaries, exclusions, gates, and next steps.
How does the skill handle governed or release-critical packages?
It requires specific audit labels including file-backed fixture, input_files, output contract, rollback boundary, trust report, and a reports/output_quality_scorecard.md.
What are the available operating modes?
The skill supports Scaffold, Production, Library, and Governed modes.