Skill Authoring

microsoft/github-copilot-for-azureOfficial

If you're writing skills for the agentskills.io spec, this walks you through the constraints: frontmatter rules, token budgets (SKILL.md under 500 tokens soft limit, references under 1000 each), and progressive disclosure patterns. It's clear about the gotchas, like linking to specific reference files instead of folders, and the fact that references only load when explicitly linked. Includes validation scripts for checking broken links and token counts. The guidance is crisp and example-driven, which matters when you're trying to figure out whether to use WHEN triggers or how to structure multi-option skills with the recipes pattern. Authored by Microsoft, so it reflects real production constraints.

skills.sh installs: 1K
GitHub stars: 217
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add microsoft/github-copilot-for-azure --skill skill-authoring --agent claude-code

Installs into .claude/skills of the current project.

Files

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