Official Anthropic Agent Skills repo with document and example packs
Context Optimization
SkillFit more useful work into the same context window with budgeting, masking and cache-friendly prompts
Clone or download it from github.com, then drop the folder into ~/.claude/skills/ (Claude Code) or your agent's skills directory.
Product badge
Share this product's name and rating in your README or on your website.
Updates may be delayed by image caching.
About Context Optimization
A playbook for stretching a context window. Your agent learns to budget tokens, hide old tool output it no longer needs, keep prompt prefixes stable so caching kicks in, split work across sub-contexts and scope retrieval tightly.
The techniques come ordered by payoff and risk, with a reminder to measure before and after. Good if your agent bills are climbing or runs keep hitting the limit.
Part of the Agent Skills for Context Engineering pack by Muratcan Koylan.
No reviews yet
Used it? Write the first review.
Similar skills
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