AgentSkillsCN

skill-authoring

代理技能编写指南。触发语句包括：创建技能、新技能、编写技能、技能模板、技能结构、评审技能、技能 PR、技能合规性、Agentskills 规范、SKILL.md 格式、技能 Frontmatter、技能最佳实践。

SKILL.md
--- frontmatter
name: skill-authoring
description: "Guidelines for writing Agent Skills. TRIGGERS: create a skill, new skill, write a skill, skill template, skill structure, review skill, skill PR, skill compliance, agentskills spec, SKILL.md format, skill frontmatter, skill best practices"

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, explain WHAT and WHEN
  • •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
  • •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

bash
# Run from the scripts directory
cd scripts
npm run tokens -- check plugin/skills/my-skill/SKILL.md

Reference Documentation