What problem does it solve? Building effective agent skills requires more than writing instructions — you need test cases, quantitative benchmarks, and structured iteration to know whether a skill actually improves results. This Skill guides the full lifecycle of creating, testing, evaluating, and refining skills so changes are grounded in evidence rather than guesswork. ## Core Features & Use Cases - Skill Authoring: Interview-driven drafting of SKILL.md files with proper frontmatter, progressive disclosure structure, and writing-style guidance. - Evaluation & Benchmarking: Run with-skill and baseline test cases in parallel, grade outputs against assertions, and aggregate pass rates, timing, and token usage into benchmark reports. - Description Optimization: Generate trigger/no-trigger eval queries and run an automated optimization loop to improve skill triggering accuracy with train/test splits. - Use Case: You want to build a skill that formats weekly sales reports. This Skill helps you draft it, create realistic test prompts, compare outputs with and without the skill, review results in an HTML viewer, and iterate until the outputs are consistently correct. ## Quick Start Help me create a new skill that converts meeting transcripts into structured action-item lists, then test and improve it.
