skill-designer
tradermonty/claude-trading-skills
Generate Claude CLI prompts to auto-create complete skills from structured idea specifications.
What is skill-designer?
Skill Designer builds a comprehensive prompt for the Claude CLI that instructs it to create a new skill directory with SKILL.md, references, scripts, and tests following repository conventions. Use it in an auto-generation pipeline to bootstrap skills from JSON idea specifications.
- Accepts a JSON idea specification (title, description, category) and normalized skill name
- Reads reference files (structure guide, quality checklist, template) to embed best practices
- Lists existing skills to prevent duplication
- Outputs a complete Claude CLI prompt ready for piping to `claude -p`
- Validates that required reference files exist before generating the prompt
How to install skill-designer
npx skills add https://github.com/tradermonty/claude-trading-skills --skill skill-designer- Python 3.9 or later
- Reference files must exist under `references/` (skill-structure-guide.md, quality-checklist.md, skill-template.md)
- No external API keys required
How to use skill-designer
- 1.Prepare a JSON file with skill idea (title, description, category)
- 2.Run `python3 skills/skill-designer/scripts/build_design_prompt.py --idea-json <path> --skill-name <name> --project-root .`
- 3.Pipe the output prompt into `claude -p --allowedTools Read,Edit,Write,Glob,Grep`
- 4.Claude will create the skill directory with SKILL.md, references, scripts, and tests
- 5.Validate the output skill directory structure and run the dual-axis-skill-reviewer to check quality score
Use cases
- Auto-generation pipeline selects a skill idea and needs a design prompt for Claude CLI
- Developer wants to bootstrap a new skill from a JSON specification without manual scaffolding
- Quality review process requires awareness of the dual-axis scoring rubric embedded in the prompt
- Batch skill creation where multiple ideas are processed through the pipeline sequentially
- Skill pipeline maintainers and automation engineers
- Developers building skill repositories at scale
- Teams implementing skill auto-generation workflows
skill-designer FAQ
A JSON object with `title` (human-readable name), `description` (what the skill does), and `category` (e.g., trading-analysis, developer-tooling).
Yes. Run the build_design_prompt.py script directly with --idea-json, --skill-name, and --project-root arguments, then copy the output prompt into `claude -p` manually.
The script exits with code 1 and reports which reference files are missing. Ensure skill-structure-guide.md, quality-checklist.md, and skill-template.md exist in the references/ directory.
No. This skill generates a prompt for Claude CLI. Claude CLI then creates the directory, SKILL.md, and all supporting files based on the prompt.
The script lists up to 20 existing skills and includes them in the prompt so Claude is aware of what already exists and can avoid duplication.
Full instructions (SKILL.md)
Source of truth, from tradermonty/claude-trading-skills.
name: skill-designer description: Design new Claude skills from structured idea specifications. Use when the skill auto-generation pipeline needs to produce a Claude CLI prompt that creates a complete skill directory (SKILL.md, references, scripts, tests) following repository conventions.
Skill Designer
Overview
Generate a comprehensive Claude CLI prompt from a structured skill idea specification. The prompt instructs Claude to create a complete skill directory following repository conventions: SKILL.md with YAML frontmatter, reference documents, helper scripts, and test scaffolding.
When to Use
- The skill auto-generation pipeline selects an idea from the backlog and needs
a design prompt for
claude -p - A developer wants to bootstrap a new skill from a JSON idea specification
- Quality review of generated skills requires awareness of the scoring rubric
Prerequisites
- Python 3.9+
- No external API keys required
- Reference files must exist under
references/
Workflow
Step 1: Prepare Idea Specification
Accept a JSON file (--idea-json) containing:
title: Human-readable idea namedescription: What the skill doescategory: Skill category (e.g., trading-analysis, developer-tooling)
Accept a normalized skill name (--skill-name) that will be used as the
directory name and YAML frontmatter name: field.
Step 2: Build Design Prompt
Run the prompt builder:
python3 skills/skill-designer/scripts/build_design_prompt.py \
--idea-json /tmp/idea.json \
--skill-name "my-new-skill" \
--project-root .
The script:
- Loads the idea JSON
- Reads all three reference files (structure guide, quality checklist, template)
- Lists existing skills (up to 20) to prevent duplication
- Outputs a complete prompt to stdout
Step 3: Feed Prompt to Claude CLI
The calling pipeline pipes the prompt into claude -p:
python3 skills/skill-designer/scripts/build_design_prompt.py \
--idea-json /tmp/idea.json \
--skill-name "my-new-skill" \
--project-root . \
| claude -p --allowedTools Read,Edit,Write,Glob,Grep
Step 4: Validate Output
After Claude creates the skill, verify:
skills/<skill-name>/SKILL.mdexists with correct frontmatter- Directory structure follows conventions
- Score with dual-axis-skill-reviewer meets threshold
Output Format
The script outputs a plain-text prompt to stdout. Exit code 0 on success, 1 if required reference files are missing.
Resources
references/skill-structure-guide.md-- Directory structure, SKILL.md format, naming conventionsreferences/quality-checklist.md-- Dual-axis reviewer 5-category checklist (100 points)references/skill-template.md-- SKILL.md template with YAML frontmatter and standard sectionsscripts/build_design_prompt.py-- Prompt builder script (CLI interface)
Related skills
More from tradermonty/claude-trading-skills and the wider catalog.

skill-idea-miner
Mine Claude Code session logs to extract and score skill idea candidates for your weekly pipeline.

skill-integration-tester
Validate multi-skill workflows and inter-skill data contracts before release.

stanley-druckenmiller-investment
Synthesize 8 upstream market analysis skills into a unified conviction score and Druckenmiller-style allocation recommendation.

stockbee-20pct-study
Build a daily 20% mover study for US equities to identify catalysts, patterns, and edge hints from explosive price moves.

stockbee-episodic-pivot-analyzer
Identify and score Stockbee-style Day 1 Episodic Pivot candidates from earnings, M&A, FDA, and catalyst events.

stockbee-exhaustion-hammer-screener
Screen US stocks for Stockbee-style selling-exhaustion hammer setups with momentum, pullback, and geometry scoring.