
Official Anthropic Agent Skills repo with document and example packs
Keep long agent sessions on track by summarizing context without losing the decisions that matter
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.
For long agent sessions where the context window keeps filling up. This skill teaches your agent to compress and hand off context in a structured way, keeping the decisions, files touched, open risks and next steps.
The main idea is to save tokens over the whole task, not just on each request. If a summary drops something and the agent has to fetch it again, you saved nothing. Useful if you run Ralph-style loops or overnight builds.
Part of the Agent Skills for Context Engineering pack by Muratcan Koylan.
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

Build and review ASP.NET Core apps with current official guidance

Official OpenAI Agent Skills for Codex and ChatGPT workflows

Translate Figma into production code at 1:1 fidelity