What problem does it solve? Writing an effective skill is hard to get right on the first try — descriptions may undertrigger, instructions may be ambiguous, and there is no built-in way to know whether a skill actually improves Claude's output. This Skill provides a structured draft-test-review-iterate workflow with quantitative evals and benchmarks so skills are validated against real test prompts instead of guesswork. ## Core Features & Use Cases - Guided Skill Authoring: Captures intent through an interview process, then drafts SKILL.md files following progressive disclosure, writing-style, and anatomy best practices. - Evaluation & Benchmarking: Runs test prompts with and without the skill in parallel, grades assertions, aggregates pass rates, timing, and token statistics, and generates an HTML review viewer for human feedback. - Description Optimization: Iteratively rewrites the skill's description and measures triggering accuracy against train/test query sets to improve when the skill activates. - Use Case: You want a skill that formats weekly status reports. Use this Skill to draft it, run three realistic test prompts, review the outputs in the eval viewer, refine the instructions, and benchmark the final version against a no-skill baseline. ## Quick Start Help me create a new skill that converts meeting transcripts into structured action-item lists, then test and improve it.
