What problem does it solve? Writing an effective AI skill is hard to get right on the first try: descriptions fail to trigger, instructions are ambiguous, and there is no systematic way to know if a skill actually improves results. This Skill provides a structured draft-test-review-iterate workflow for building and refining skills with quantitative benchmarks and human feedback. ## 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. - Evaluation Harness: Runs test prompts with and without the skill in parallel subagents, grades outputs against assertions, and aggregates pass rates, timing, and token usage into benchmark reports. - Interactive Review Viewer: Generates an HTML viewer (via eval-viewer/generate_review.py) so users can inspect outputs side-by-side and leave feedback that drives the next iteration. - Description Optimization: Generates trigger/no-trigger eval queries and runs an automated loop (scripts/run_loop.py) to improve the skill's description for reliable triggering. - Use Case: You want to build a skill that formats weekly sales reports. This Skill helps you draft it, creates realistic test prompts, runs baseline comparisons, shows you the results in a browser, and iterates until the outputs are consistently correct. ## Quick Start Ask the assistant to help you create a new skill for your workflow, and it will interview you, draft the SKILL.md, and run test evaluations. ## Quick Start Tell the assistant: help me create a new skill for my workflow, and it will interview you, draft the SKILL.md, and run test evaluations.
