What problem does it solve? Writing an effective skill is hard to get right on the first try, and without structured evaluation there is no way to know whether a skill actually improves the model's output or triggers when it should. This Skill provides a complete draft-test-review-improve loop with quantitative benchmarking and description optimization. ## Core Features & Use Cases - Guided Skill Authoring: Interviews the user to capture intent, then drafts a SKILL.md with proper frontmatter, progressive disclosure structure, and writing-style guidance. - Parallel Evaluation Runs: Spawns with-skill and baseline subagent runs for each test prompt, grades outputs against assertions, and aggregates pass rates, timing, and token usage into benchmark.json. - Interactive Review Viewer: Generates an HTML viewer (via eval-viewer/generate_review.py) so users can inspect outputs side-by-side and leave feedback per test case. - Description Optimization: Runs an automated train/test loop (scripts/run_loop) that rewrites the skill's description to improve triggering accuracy on realistic queries. - Use Case: A user says "I want a skill that formats my lab notebooks." This Skill drafts it, creates test prompts, runs benchmarked evaluations, presents results for review, and iterates until the user is satisfied. ## Quick Start Help me create a new skill that converts my meeting notes into structured action items, then test and refine it with me.
