When building an AI agent skill, you need to decide where to put information. A single file is simple, but it can get too long. Splitting into smaller files saves space in the agent's working memory. This skill helps you choose the best way to organize your skill content.
Use this when your main skill file grows past 300 to 400 lines. It also helps when you are unsure if something belongs in the main file or a reference file. The goal is to keep the agent's thinking clear and efficient.
Progressive disclosure means the agent only loads extra details when needed. This skill explains the trade-offs between staying in one file and splitting. It helps you make a smart choice for your specific situation.
Global
mkdir -p ~/.claude/skills/skill-progressive-disclosure-designProject
mkdir -p .claude/skills/skill-progressive-disclosure-designSource Repository
Setup Matt Pocock Skillsmattpocock/skills
Set up your repo for engineering skills with just a few guided steps
Lark Skill Makerlarksuite/cli
Create reusable skills to automate Feishu tasks with lark-cli commands
Teachmattpocock/skills
Teach yourself any skill with guided lessons and mission-driven practice
Write A Skillmattpocock/skills
Build new agent skills with clear structure and bundled resources
Writing Great Skillsmattpocock/skills
A guide for writing predictable AI agent skills with clear principles and reliable behavior
Ask Mattmattpocock/skills
Pick the perfect skill or flow for your project every time
Writing Skillsobra/superpowers
Test your agent skills like code to make them truly effective
Animejsheygen-com/hyperframes
Safely add Anime.js animations to your HyperFrames compositions with seek control