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 built-in way to measure whether a skill actually improves agent output. This Skill provides a structured draft-test-review-iterate workflow with quantitative benchmarks and description optimization. ## Core Features & Use Cases - Skill authoring workflow: Capture intent, interview the user, and write a well-structured SKILL.md following progressive disclosure and anatomy best practices. - Evaluation harness: Run test prompts with and without the skill via subagents, grade assertions, aggregate benchmark statistics (pass rate, time, tokens), and review results in an HTML viewer. - Description optimization: Generate trigger/no-trigger eval queries, review them in an HTML template, and run an automated loop that rewrites the frontmatter description to improve triggering accuracy. - Use Case: You want a skill that formats weekly sales spreadsheets. This Skill helps you draft it, run three realistic test prompts against a baseline, review outputs side by side, refine the instructions, and optimize the description so it triggers reliably. ## Quick Start Ask the agent to create a new skill for your workflow and iterate on it with test cases until the outputs look right.
