What problem does it solve? Writing effective agent skills 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 controlled 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: Interview-driven process to capture intent, write SKILL.md files with proper frontmatter, and structure scripts, references, and assets following progressive disclosure principles. - Evaluation & Benchmarking: Run test prompts with and without the skill in parallel, grade outputs against assertions, and aggregate pass rates, timing, and token usage into benchmark reports with variance analysis. - Description Optimization: Generate trigger/no-trigger eval queries and run an automated optimization loop to improve the skill description's triggering accuracy. - Use Case: You want to build a skill that formats weekly sales reports. Use this Skill to draft it, run three realistic test prompts, review outputs side-by-side in an HTML viewer, and iterate until the benchmark shows consistent improvement over the baseline. ## Quick Start Help me create a new skill that converts meeting transcripts into structured action-item lists, then test it with a few realistic prompts.
