skillmd.
Docslibrary

skill-authoring

Guidelines for writing Agent Skills that comply with the agentskills.io specification. WHEN: \"create a skill\", \"new skill\", \"write a skill\", \"skill template\", \"skill structure\", \"review skill\", \"skill PR\", \"skill compliance\", \"SKILL.md format\", \"skill frontmatter\", \"skill best practices\".

microsoft/github-copilot-for-azureagentskills.io
View source

Install

npx skills add https://github.com/microsoft/github-copilot-for-azure --skill skill-authoring

Use with your agent

ClaudeCursorOpenAIGemini

Install the skill-authoring skill, then use it as build context. Run: npx skills add https://github.com/microsoft/github-copilot-for-azure --skill skill-authoring. Then read the installed skill.md and follow its guidance to build or refactor my project.

Skill Authoring Guide

This skill provides guidance for writing Agent Skills that comply with the agentskills.io specification.

When to Use

  • Creating a new skill for this repository
  • Reviewing a skill PR for compliance
  • Checking if an existing skill follows best practices
  • Understanding token budgets and progressive disclosure

Constraints

  • name: 1-64 chars, lowercase + hyphens, match directory
  • description: 1-1024 chars, ≤60 words, explain WHAT and WHEN
  • Use WHEN: with quoted trigger phrases (preferred over USE FOR:)
  • Avoid DO NOT USE FOR: unless the skill has trigger overlap with a broader skill (see frontmatter guidelines)
  • Use inline double-quoted strings (not >- folded scalars)
  • SKILL.md: <500 tokens (soft), <5000 (hard)
  • references/*.md: <1000 tokens each

Structure

  • SKILL.md (required) - Instructions
  • references/ (optional) - Detailed docs
  • scripts/ (optional) - Executable code

Frontmatter: name (lowercase-hyphens), description (WHAT + WHEN)

Progressive Disclosure

Metadata (~100 tokens) loads at startup. SKILL.md (<5000 tokens) loads on activation. References load only when explicitly linked (not on activation). Keep SKILL.md lean.

Reference Loading

References are JIT (just-in-time) loaded:

  • Only files explicitly linked via [text](references/file.md) load
  • Link to files, not folders - [Recipes](references/recipes/README.md) not [Recipes](references/recipes/)
  • Each file loads in full (not sections)
  • No caching between requests - write self-contained files
  • Use recipes/services patterns for multi-option skills

See REFERENCE-LOADING.md for details.

Validation

# Run from the scripts directory
cd scripts
npm run references              # Validate all skill links
npm run tokens -- check         # Check token limits

Integrity Checks

When reviewing or authoring skills, verify:

  1. No broken links - All referenced files exist
  2. No orphaned references - All reference files are linked
  3. Token budgets - References under 1000 tokens (split if exceeded)
  4. No duplicates - Consolidate repeated content
  5. No out-of-place guidance - Service-specific content belongs in service-specific references

See Validation for detailed procedures.

Reference Documentation