Skill Creator

A skill for creating new skills and iteratively improving them.

⚠️ Completeness Contract: This workflow has 6 phases: Intent → Draft → Test & Evaluate → Iterate → Optimize Description → Package. The workflow is NOT complete until Description Optimization has been offered to the user. If you haven't reached that step, you still have work to do.

Before jumping in, identify where the user is in this process and what phases remain — including the ones at the end of this file. Do not start executing until you can name every remaining phase.

At a high level, the process of creating a skill goes like this:

• Decide what you want the skill to do and roughly how it should do it
• Write a draft of the skill
• Create a few test prompts and run claude-with-access-to-the-skill on them
• Help the user evaluate the results both qualitatively and quantitatively
  • While the runs happen in the background, draft some quantitative evals if there aren't any (if there are some, you can either use as is or modify if you feel something needs to change about them). Then explain them to the user (or if they already existed, explain the ones that already exist)
  • Use the eval-viewer/generate_review.py script to show the user the results for them to look at, and also let them look at the quantitative metrics
• Rewrite the skill based on feedback from the user's evaluation of the results (and also if there are any glaring flaws that become apparent from the quantitative benchmarks)
• Repeat until you're satisfied
• Expand the test set and try again at larger scale