What problem does it solve? Building effective AI agent skills requires more than writing instructions — descriptions must trigger reliably, outputs must be verified, and improvements must be measured. This Skill provides a structured draft-test-review-iterate loop with quantitative benchmarking so skill quality is validated rather than assumed. ## Core Features & Use Cases - Guided Skill Authoring: Captures intent through interview questions, then drafts SKILL.md files following progressive disclosure and anatomy best practices. - Evaluation Harness: Runs test prompts with and without the skill in parallel, grades assertions, aggregates pass rates, timing, and token usage into benchmark reports, and renders results in an HTML review viewer. - Description Optimization: Generates realistic trigger/no-trigger query sets and runs an automated train/test optimization loop to improve skill triggering accuracy. - Use Case: A user wants a skill that converts meeting notes into Jira tickets. This Skill drafts the SKILL.md, creates test prompts, runs baseline comparisons, presents results for review, and iterates until the outputs pass. ## Quick Start Help me create a new skill that extracts action items from meeting transcripts and test it with a few realistic prompts.
