What problem does it solve? Writing effective skills for AI agents is hard: descriptions fail to trigger reliably, instructions overfit to a few examples, and there is no systematic way to know whether a change actually improved the skill. This Skill provides a complete workflow for drafting skills, running test prompts with and without the skill, collecting human feedback through a review viewer, benchmarking results quantitatively, and optimizing the trigger description. ## Core Features & Use Cases - Guided Skill Authoring: Interviews the user about intent, trigger conditions, and output formats, then drafts a SKILL.md following progressive-disclosure and writing-style best practices. - Evaluation & Benchmarking: Runs test prompts in parallel with-skill and baseline configurations, grades outputs against assertions, and aggregates pass rates, timing, and token usage into benchmark reports. - Interactive Review Viewer: Generates an HTML viewer (server or static file) so users can inspect outputs side by side, leave feedback per test case, and compare across iterations. - Description Optimization: Builds trigger/no-trigger eval query sets, runs an automated optimization loop with train/test splits, and applies the best-performing description. - Use Case: You want to turn a repeated workflow into a reusable skill. The Skill helps you draft it, creates realistic test prompts, runs blind baseline comparisons, shows you the results in a browser, and iterates until the skill generalizes. ## Quick Start Ask the agent to help you create a new skill for your workflow, or to evaluate and improve an existing skill using test prompts and benchmarks.
