Create, test, and iteratively improve AI agent skills with structured evaluation and benchmarking. Guides you through the full skill development lifecycle: intent capture, drafting, test case creation, evaluation, and iteration based on user feedback Runs parallel test cases with and without the skill to measure impact, capturing timing and token usage for quantitative comparison Generates an interactive browser-based reviewer showing outputs, qualitative feedback, and benchmark metrics (pass rates, latency, token efficiency) across iterations Includes description optimization to improve skill triggering accuracy by testing 20 realistic trigger/non-trigger queries and iterating the description through up to 5 rounds
Install
Add to Contextium Workspace
Sign up free to add this skill to your workspace and sync it across Claude, Cursor, VS Code, and more.
Install via CLI
Run this command to install directly into your Contextium workspace.
contextium skill get anthropics-skill-creator
New to the CLI? npm install -g @contextium/[email protected] then contextium login
Is this yours?
This listing was imported from skills.sh under the handle @@anthropics. If you created this, you can claim it and take ownership of the listing.