What problem does it solve? Writing an effective skill is hard to get right on the first try, and without structured testing there is no way to know whether a skill actually improves Claude's output or triggers when it should. This Skill provides a complete workflow for drafting skills, running controlled evaluations against baselines, collecting human feedback, and optimizing trigger descriptions. ## Core Features & Use Cases - Guided Skill Authoring: Interviews the user about intent, edge cases, and output formats, then drafts a SKILL.md following progressive disclosure and writing-style best practices. - Benchmarked Evaluation Loop: Runs test prompts with and without the skill in parallel, grades outputs against assertions, aggregates pass rates, timing, and token usage into benchmark reports, and renders an HTML review viewer for qualitative feedback. - Description Optimization: Generates realistic should-trigger and should-not-trigger queries, then runs an automated train/test optimization loop to improve the skill's triggering accuracy. - Use Case: A user says "I want a skill that turns meeting notes into Jira tickets." This Skill drafts the skill, creates test cases, runs with-skill and baseline comparisons, presents results in a browser viewer, and iterates until the user is satisfied. ## Quick Start Help me create a new skill that converts my weekly status notes into a formatted changelog, then test it and improve it based on my feedback.
