What problem does it solve? Writing an effective agent skill is hard to get right on the first try: descriptions undertrigger, instructions overfit to examples, and there is no systematic way to know whether a change actually improved the skill. This Skill provides a structured draft-test-review-iterate workflow with quantitative benchmarks so skill quality is measured rather than guessed. ## Core Features & Use Cases - Guided skill authoring: Interviews the user about intent, trigger contexts, and output formats, then drafts a SKILL.md following progressive-disclosure and writing-style best practices. - Parallel evaluation harness: Runs test prompts with and without the skill via subagents, grades outputs against assertions, and aggregates pass rates, timing, and token usage into benchmark.json with mean and standard deviation. - Description optimization loop: Generates realistic should-trigger and should-not-trigger queries, then iteratively rewrites the skill description and scores it on train and held-out test splits to improve triggering accuracy. - Use Case: You want a skill that converts meeting notes into Jira tickets. This Skill helps you draft it, runs three realistic test prompts with and without the skill, shows results in a browser-based review viewer, collects your feedback, and iterates until the outputs pass your assertions. ## Quick Start Help me create a new skill that turns my weekly meeting notes into structured Jira tickets, then test it with a few realistic prompts.
