
Official Anthropic Agent Skills repo with document and example packs
The primer on what a context window really holds, how attention behaves, and why less is often more
Clone or download it from github.com, then drop the folder into ~/.claude/skills/ (Claude Code) or your agent's skills directory.
Share this product's name and rating in your README or on your website.
Updates may be delayed by image caching.
The foundation skill in Muratcan Koylan's Agent Skills for Context Engineering collection.
It explains the core mental models: what counts as context (system prompt, tools, retrieved docs, history, tool output), the U-shaped attention curve, and why a small high-signal context usually beats a big one. It is meant for onboarding and background reasoning, and it routes hands-on work to the collection's more specific skills for degradation, optimization, and compression.
Used it? Write the first review.

Official Anthropic Agent Skills repo with document and example packs

Official Browserbase skills for cloud browser automation

Production agent skills from Matt Pocock's .agents directory

Official OpenAI Agent Skills for Codex and ChatGPT workflows

Official Claude document skills for Word, PDF, PowerPoint, Excel

Curated collection of 1000+ SKILL.md packs for coding agents