What problem does it solve? Building effective AI Skills requires more than writing instructions — descriptions must trigger reliably, outputs must be validated against real test cases, and improvements need evidence rather than guesswork. This Skill provides a structured workflow for drafting Skills, running controlled evaluations with baselines, collecting human feedback, and optimizing trigger descriptions. ## 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. - Benchmark Evaluation Loop: Runs test prompts in parallel with and without the Skill, grades outputs against assertions, aggregates pass rates and timing into benchmark reports, and launches an HTML review viewer for human feedback. - Description Optimization: Generates realistic trigger/no-trigger query sets, runs an automated optimization loop with train/test splits, and applies the best-performing description to improve triggering accuracy. - Use Case: You want to build a Skill that formats weekly sales reports. This Skill helps you draft it, creates test prompts, runs evaluations comparing performance with and without the Skill, presents results in a browser viewer, and iterates until the output meets your standards. ## Quick Start Help me create a new Skill that converts meeting transcripts into structured action-item lists, then test and refine it.
