skill-authoring-governance

Governs authoring, auditing, and reviewing of SKILL.md files under .github/skills/.

Updated Dec 24, 2025
One-click install
npx skills add https://github.com/JoyJoin-Tech-Limited/JoyJoin_app_v0.1 --skill skill-authoring-governance-joyjoin-tech-limited
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-authoring-governance
Source: https://github.com/JoyJoin-Tech-Limited/JoyJoin_app_v0.1/tree/main/.github/skills/skill-authoring-governance
Command: npx skills add https://github.com/JoyJoin-Tech-Limited/JoyJoin_app_v0.1 --skill skill-authoring-governance-joyjoin-tech-limited

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Teams maintaining a library of AI skills often end up with inconsistent frontmatter, bloated SKILL.md files, missing trigger phrases, and unauditable quality. This Skill defines a single governing standard so every skill in the repository stays consistent, triggerable, and reviewable. ## Core Features & Use Cases - Authoring standard: Enforces kebab-case naming, description discipline (what + when + trigger phrases, under 1024 chars), and progressive disclosure with a 100-line hard limit on SKILL.md. - Audit framework: Provides an eight-area golden checklist (frontmatter, structure, disclosure, instruction quality, patterns, validation, technical correctness, distribution readiness) with a repeatable audit report format. - PR review support: Supplies review checklists and output templates for evaluating PRs that add or change skill docs. - Use Case: When a contributor opens a PR adding a new skill, run the audit checklist to verify frontmatter, examples, troubleshooting, and review checklist sections before merge. ## Quick Start Ask the AI to audit the skills under .github/skills/ against the governance checklist and report pass or fail per area.

Frequently Asked Questions about skill-authoring-governance

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I write a good SKILL.md description field?▼

Keep the description under 1024 characters with three parts: what the skill does, when to use it, and 3-5 explicit trigger phrases. The description is the only text an agent sees when deciding which skill to load, so vague summaries like 'helps with documents' fail the standard.

How do I audit existing skills for quality and consistency?▼

Run the eight-area audit framework: YAML frontmatter, file structure, progressive disclosure, instructions quality, patterns, testing and validation, technical correctness, and distribution readiness. Produce a per-area PASS, FAIL, or PARTIAL verdict with an overall count of items to fix before merge.

What is the maximum length for a SKILL.md file?▼

SKILL.md has a hard limit of 100 lines. Core rules and workflow stay in SKILL.md while detailed examples, checklists, and reference material move into a references/ directory linked with relative paths.

Why is my skill not being triggered by the AI agent?▼

Missing trigger phrases in the frontmatter description is the most common cause. Add 3-5 short phrases that naturally precede loading the skill, plus concrete scenarios in a 'When to use this skill' section.

When should a skill include a scripts/ directory?▼

Add scripts when the operation is deterministic, the same code would be generated repeatedly, or errors need explicit handling. Scripts save tokens and improve reliability compared to regenerated code, and must be referenced from SKILL.md with relative paths.