Skip to content
Development
Skill

/skill-builder

Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build custom skills for specific workflows, generate skill templates, or understand the Claude Skills specification.

From plugin
claude-flow
67k200 skills157 agents194 commands1 MCP
Install
$ npx -y skills add ruvnet/claude-flow --skill skill-builder --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition โ†’
  • You can call itInvoke it directly when you want it.
  • Slash command/skill-builder

Context preview

The summary Claude sees to decide when to auto-load this skill.

Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build custom skills for specific workflows, generate skill templates, or understand the Claude Skills specification.

SKILL.md

skill-builder.SKILL.md
name: "Skill Builder"
description: "Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build custom skills for specific workflows, generate skill templates, or understand the Claude Skills specification."

Skill Builder

What This Skill Does

Creates production-ready Claude Code Skills with proper YAML frontmatter, progressive disclosure architecture, and complete file/folder structure. This skill guides you through building skills that Claude can autonomously discover and use across all surfaces (Claude.ai, Claude Code, SDK, API).

Prerequisites

  • Claude Code 2.0+ or Claude.ai with Skills support
  • Basic understanding of Markdown and YAML
  • Text editor or IDE

Quick Start

Creating Your First Skill

# 1. Create skill directory (MUST be at top level, NOT in subdirectories!)
mkdir -p ~/.claude/skills/my-first-skill

# 2. Create SKILL.md with proper format
cat > ~/.claude/skills/my-first-skill/SKILL.md << 'EOF'
---
name: "My First Skill"
description: "Brief description of what this skill does and when Claude should use it. Maximum 1024 characters."
---

# My First Skill

## What This Skill Does
[Your instructions here]

## Quick Start
[Basic usage]
EOF

# 3. Verify skill is detected
# Restart Claude Code or refresh Claude.ai

---

Complete Specification

๐Ÿ“‹ YAML Frontmatter (REQUIRED)

Every SKILL.md **must** start with YAML frontmatter containing exactly two required fields:

---
name: "Skill Name"                    # REQUIRED: Max 64 chars
description: "What this skill does    # REQUIRED: Max 1024 chars
and when Claude should use it."       # Include BOTH what & when
---

Field Requirements

**`name`** (REQUIRED):

  • **Type**: String
  • **Max Length**: 64 characters
  • **Format**: Human-friendly display name
  • **Usage**: Shown in skill lists, UI, and loaded into Claude's system prompt
  • **Best Practice**: Use Title Case, be concise and descriptive
  • **Examples**:
  • โœ… "API Documentation Generator"
  • โœ… "React Component Builder"
  • โœ… "Database Schema Designer"
  • โŒ "skill-1" (not descriptive)
  • โŒ "This is a very long skill name that exceeds sixty-four characters" (too long)

**`description`** (REQUIRED):

  • **Type**: String
  • **Max Length**: 1024 characters
  • **Format**: Plain text or minimal markdown
  • **Content**: MUST include:

1. **What** the skill does (functionality) 2. **When** Claude should invoke it (trigger conditions)

  • **Usage**: Loaded into Claude's system prompt for autonomous matching
  • **Best Practice**: Front-load key trigger words, be specific about use cases
  • **Examples**:
  • โœ… "Generate OpenAPI 3.0 documentation from Express.js routes. Use when creating API docs, documenting endpoints, or building API specifications."
  • โœ… "Create React functional components with TypeScript, hooks, and tests. Use when scaffolding new components or converting class components."
  • โŒ "A comprehensive guide to API documentation" (no "when" clause)
  • โŒ "Documentation tool" (too vague)

YAML Formatting Rules

---
# โœ… CORRECT: Simple string
name: "API Builder"
description: "Creates REST APIs with Express and TypeScript."

# โœ… CORRECT: Multi-line description
name: "Full-Stack Generator"
description: "Generates full-stack applications with React frontend and Node.js backend. Use when starting new projects or scaffolding applications."

# โœ… CORRECT: Special characters quoted
name: "JSON:API Builder"
description: "Creates JSON:API compliant endpoints: pagination, filtering, relationships."

# โŒ WRONG: Missing quotes with special chars
name: API:Builder  # YAML parse error!

# โŒ WRONG: Extra fields (ignored but discouraged)
name: "My Skill"
description: "My description"
version: "1.0.0"       # NOT part of spec
author: "Me"           # NOT part of spec
tags: ["dev", "api"]   # NOT part of spec
---

**Critical**: Only `name` and `description` are used by Claude. Additional fields are ignored.

---

๐Ÿ“‚ Directory Structure

Minimal Skill (Required)

~/.claude/skills/                    # Personal skills location
โ””โ”€โ”€ my-skill/                        # Skill directory (MUST be at top level!)
    โ””โ”€โ”€ SKILL.md                     # REQUIRED: Main skill file

**IMPORTANT**: Skills MUST be directly under `~/.claude/skills/[skill-name]/`. Claude Code does NOT support nested subdirectories or namespaces!

Full-Featured Skill (Recommended)

~/.claude/skills/
โ””โ”€โ”€ my-skill/                        # Top-level skill directory
        โ”œโ”€โ”€ SKILL.md                 # REQUIRED: Main skill file
        โ”œโ”€โ”€ README.md                # Optional: Human-readable docs
        โ”œโ”€โ”€ scripts/                 # Optional: Executable scripts
        โ”‚   โ”œโ”€โ”€ setup.sh
        โ”‚   โ”œโ”€โ”€ validate.js
        โ”‚   โ””โ”€โ”€ deploy.py
        โ”œโ”€โ”€ resources/               # Optional: Supporting files
        โ”‚   โ”œโ”€โ”€ templates/
        โ”‚   โ”‚   โ”œโ”€โ”€ api-template.js
        โ”‚   โ”‚   โ””โ”€โ”€ component.tsx
        โ”‚   โ”œโ”€โ”€ examples/
        โ”‚   โ”‚   โ””โ”€โ”€ sample-output.json
        โ”‚   โ””โ”€โ”€ schemas/
        โ”‚       โ””โ”€โ”€ config-schema.json
        โ””โ”€โ”€ docs/                    # Optional: Additional documentation
            โ”œโ”€โ”€ ADVANCED.md
            โ”œโ”€โ”€ TROUBLESHOOTING.md
            โ””โ”€โ”€ API_REFERENCE.md

Skills Locations

**Personal Skills** (available across all projects):

~/.claude/skills/
โ””โ”€โ”€ [your-skills]/
  • **Path**: `~/.claude/skills/` or `$HOME/.claude/skills/`
  • **Scope**: Available in all projects for this user
  • **Version Control**: NOT committed to git (outside repo)
  • **Use Case**: Personal productivity tools, custom workflows

**Project Skills** (team-shared, version controlled):

<project-root>/.claude/skills/
โ””โ”€โ”€ [team-skills]/
  • **Path**: `.claude/skills/` in project root
  • **Scope**: Available only in this project
  • **Version Control**: SHOULD be committed to git
  • **Use Case**: Team workflows, project-specific
Read more
Ships withclaude-flow

An agent meta-harness for Claude Code and Codex. Agent = Model + Harness. The model writes; the harness gives it tools, memory, loops, sandboxes, and controls so it can actually work.

Get the whole plugin

Other skills on claude-flow.