skill-creator
Skill Creator
A skill for creating new skills and iteratively improving them.
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.pyscript 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
Your job when using this skill is to figure out where the user is in this process and then jump in and help them progress through these stages. So for instance, maybe they're like "I want to make a skill for X". You can help narrow down what they mean, write a draft, write the test cases, figure out how they want to evaluate, run all the prompts, and repeat.
On the other hand, maybe they already have a draft of the skill. In this case you can go straight to the eval/iterate part of the loop.
More from jvgomg/skills
grill-me
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
10team-lead
Orchestrates large bodies of work (features, refactors, milestones, backlog tasks) using sub-agents as a team. Use this skill when the user explicitly asks you to "take responsibility", "orchestrate", "lead", or "team-lead" a set of tasks or a milestone. This is a manual-trigger skill — only activate when the user clearly invokes it.
5prd-to-tasks
Break a PRD into independently-grabbable Backlog tasks using tracer-bullet vertical slices. Use when user wants to convert a PRD to tasks, create implementation tickets, or break down a PRD into work items.
4write-a-prd
Create a PRD through user interview, codebase exploration, and module design, then store as a Backlog document. Use when user wants to write a PRD, create a product requirements document, or plan a new feature.
4dependabot-pnpm
Resolve Dependabot security alerts in pnpm projects. Use when asked to fix, resolve, or work through Dependabot alerts, security vulnerabilities, or dependency security issues. Handles fetching alerts via gh api, analyzing dependency chains, applying fixes (direct updates or pnpm overrides), and maintaining a decision log. Works autonomously through batches of alerts, asking for input only when necessary.
1split-expenses
>
1