What problem does it solve? Writing effective skills for AI agents is hard to get right on the first try, and there is no systematic way to know whether a skill actually improves agent behavior. This Skill provides a structured workflow for drafting skills, running test cases with and without the skill, grading results against assertions, and iterating based on quantitative benchmarks and user feedback. ## Core Features & Use Cases - Guided Skill Authoring: Walks through intent capture, interviewing, and writing SKILL.md files with proper frontmatter, progressive disclosure, and writing-style guidance. - Evaluation Harness: Spawns parallel with-skill and baseline runs, drafts verifiable assertions, captures timing and token data, and aggregates results into benchmark.json with pass rates and deltas. - Description Optimization: Generates trigger/no-trigger eval queries, runs an automated optimization loop with train/test splits, and applies the best-performing description for accurate skill triggering. - Use Case: You want to build a skill that formats weekly sales reports. Use this Skill to draft it, run three realistic test prompts against baseline runs, review outputs in the HTML viewer, and iterate until the benchmark shows consistent improvement. ## Quick Start Help me create a new skill that converts meeting transcripts into structured action-item lists, then test and improve it.
