Skill Designer turns a structured idea (title, description, category) and a skill name into one long prompt. The prompt carries the repository’s structure guide, a quality checklist, a SKILL.md template and a list of up to 20 existing skills so the new one does not duplicate them.
The prompt is printed to stdout and meant to be piped into claude -p, which then writes the skill directory. It is a development tool for the skills in this repository and fetches no market data.
What You Get
- A design prompt printed as text on stdout
- The structure guide, the 100-point quality checklist and the SKILL.md template folded into that prompt
- A list of existing skills in the prompt to prevent duplicates
- A command line that pipes the prompt into claude -p with read, edit, write, glob and grep tools
Common Use Cases
- Bootstrapping a new skill from a backlog idea in an automated pipeline
- Giving a contributor a consistent starting prompt for a new skill
- Preparing a skill so it meets the scoring rubric of the dual-axis reviewer
What Makes It Unique
It encodes the repository’s own conventions and review rubric into the prompt, so a generated skill is built against the same checklist later used to score it. It needs no API keys.
Under The Hood
A Python script reads local files only: the idea JSON, three reference documents and the skill folders under the project root. It prints the prompt to stdout. The documented pipeline then pipes that prompt into the Claude CLI with permission to read, edit and write files, so the model creates the new skill directory on disk.