Skip to content
SkillMixed592 tokens in use

skill-designer

Builds a prompt from a JSON skill idea that tells Claude CLI to create a full skill folder with SKILL.md, references, scripts and tests.

7,430 stars on the repository MIT Licensetradermonty/claude-trading-skills · skills/skill-designer

Skill label

measured from its files

What installing skill-designer costs

48tokens idle
592tokens in use
2,174tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Mixed

Script-ledMixedModel-led

Scripts do part of the work and the model's judgement does the rest.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/build_design_prompt.py.

Touches

shelldetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter12/15
  • Structure22/25
  • Examples9/15
  • Output12/15
  • Size15/15
  • Resources12/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 45

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity100
  • Maintenance52
  • Community68
  • Maturity36
  • Momentum40

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.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers