Skill Builder

Generate Claude Code Skill units with YAML frontmatter and standardized directories.

Updated Jul 2, 2025
One-click install
npx skills add https://github.com/dug-21/neural-data-platform --skill skill-builder-dug-21
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Skill Builder
Source: https://github.com/dug-21/neural-data-platform/tree/main/.claude/skills/skill-builder
Command: npx skills add https://github.com/dug-21/neural-data-platform --skill skill-builder-dug-21

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Skill Builder provides a standardized path for creating production-ready Claude Code Skills by ensuring the mandatory YAML frontmatter, a progressive disclosure structure, and a complete top-level directory organization. It helps teams and individuals generate consistent skill templates and documentation to accelerate discovery and activation.

Core Features & Use Cases

  • Enforces a strict SKILL.md frontmatter with the required name and description to enable reliable discovery.
  • Guides the design of progressive disclosure across metadata, body, and referential content to scale skills without context bloat.
  • Recommends and demonstrates a full folder structure (skill-dir, scripts/, references/, assets/, docs/) to speed up skill creation and reuse.
  • Use Case: teams quickly bootstrap new Claude Skills for automation, data pipelines, documentation, or workflow orchestration.

Quick Start

Create a new skill directory under ~/.claude/skills/ and add an SKILL.md with valid frontmatter and a structured, navigable content layout as shown in the skill-builder example. Then optionally add scripts, references, and assets to extend functionality.

Frequently Asked Questions about Skill Builder

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a Claude Code Skill with the correct YAML frontmatter and directory structure?

To create a Claude Code Skill, you generate a SKILL.md file with mandatory YAML frontmatter and a standardized directory structure. This enforces the progressive disclosure model across metadata, body, and referential content.

What is the progressive disclosure model for structuring Claude Skills?

The progressive disclosure model structures Claude Skills across three tiers: metadata, body, and referential content. This design scales skill functionality without causing context bloat during discovery and activation.

How do I scaffold a new project for Claude Code workflows and documentation?

You scaffold a new project by creating a skill directory under ~/.claude/skills/ and adding an SKILL.md file. You then extend functionality by adding scripts, references, assets, and docs folders.

Does Claude Code require specific metadata in the SKILL.md frontmatter for skill discovery?

Claude Code skill discovery requires strict YAML frontmatter in the SKILL.md file. Mandatory metadata fields include the skill name and description to enable reliable activation and searchability.

What is the best way to document Claude Skills specification for team automation?

The best way to document Claude Skills is using standardized templates that organize content into a navigable layout. This accelerates team bootstrapping for automation, data pipelines, and workflow orchestration.