What problem does it solve? Writing a skill that triggers reliably and performs well is hard to do by intuition alone. This Skill guides the full lifecycle of skill development: drafting SKILL.md files, running test prompts with and without the skill, grading outputs against assertions, benchmarking pass rates and token usage, and optimizing the description field for accurate triggering. ## Core Features & Use Cases - Guided Skill Authoring: Interviews the user about intent, trigger contexts, and output formats, then drafts a SKILL.md following progressive disclosure and writing-style best practices. - Evaluation & Benchmarking: Spawns parallel with-skill and baseline runs, grades outputs against assertions, aggregates pass rate, timing, and token statistics, and renders results in an interactive HTML review viewer. - Description Optimization: Generates realistic trigger/no-trigger eval queries, runs an automated train/test optimization loop, and applies the best-performing description to improve skill triggering accuracy. - Use Case: A user says "turn this workflow into a skill." The Skill captures the intent, writes a draft, runs three test prompts against baselines, opens a browser viewer for feedback, iterates on the skill, and finally tunes the description so the skill triggers on the right prompts. ## Quick Start Ask Claude to create a new skill for your workflow and let it draft, test, and refine the skill through an evaluation loop.
