If you're building skills for Claude, this is the meta tool you want. It walks you through the full cycle: drafting the skill, writing test prompts, running evals in the background while helping you set up quantitative benchmarks, then iterating based on results. The progressive disclosure guidance is solid (metadata always loads, skill body loads on trigger, bundled resources load as needed), and there's a separate flow for optimizing skill descriptions to fix undertriggering. What I like is the flexibility: it meets you wherever you are in the process, whether you're starting from scratch or refining an existing draft. Just be aware it assumes familiarity with the skill format and evaluation workflows.
npx -y skills add feiskyer/claude-code-settings --skill skill-creator --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
metabase/metabase
github/awesome-copilot
UKGovernmentBEIS/inspect_evals
addyosmani/agent-skills