
Official Anthropic Agent Skills repo with document and example packs
Diagnose why your agent gets dumber as the session grows, and fix it before it spirals
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.
Long sessions go bad in predictable ways: facts lost in the middle, a wrong early answer that poisons everything after, conflicting instructions, too much noise. This skill helps your agent name which failure is happening and apply the matching fix.
It treats context rot as an engineering problem with signals you can watch for, not bad luck. Useful when an agent that started strong starts looping or contradicting itself.
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