
Skill Builder
Author production-ready Claude Code Skills with valid YAML frontmatter and progressive disclosure whenever you need reusable agent workflows.
Overview
Skill Builder is a journey-wide agent skill that creates production-ready Claude Code Skills with YAML frontmatter and progressive disclosure—usable whenever a solo builder needs to package reusable agent workflows befor
Install
npx skills add https://github.com/ruvnet/ruflo --skill skill-builderWhat is this skill?
- Enforces required YAML frontmatter (name, description up to 1024 characters) on every SKILL.md
- Progressive disclosure structure with What This Skill Does, Quick Start, and Complete Specification sections
- Insists skills live at top-level `~/.claude/skills/<skill-name>`—not nested subdirectories that break discovery
- Step-by-step mkdir and heredoc quick start for first-skill bootstrap and detection refresh
- Documents full Claude Skills specification for Claude.ai, Claude Code, SDK, and API surfaces
- Description field maximum 1024 characters in frontmatter
Adoption & trust: 637 installs on skills.sh; 58.5k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You keep repeating the same multi-step agent instructions in chat because you lack a valid SKILL.md, frontmatter, and top-level skills directory Claude can discover.
Who is it for?
Indie builders formalizing recurring workflows into installable skills with correct metadata and documentation depth.
Skip if: One-off questions with no intent to reuse instructions, or teams that only consume third-party skills and never author their own.
When should I use this skill?
You need to build custom skills for specific workflows, generate skill templates, or understand the Claude Skills specification.
What do I get? / Deliverables
You finish a properly named skill folder with specification-compliant SKILL.md and structure Claude can autonomously load on Code, web, SDK, or API.
- Skill directory at top-level `~/.claude/skills/<skill-name>`
- SKILL.md with valid YAML frontmatter and progressive disclosure sections
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
Package a competitor-research ritual into a skill so every new idea session triggers the same steps.
Author a scoping skill that turns rough requirements into checklists before you greenlight Build.
Encode a third-party API workflow as a skill with frontmatter triggers instead of brittle prompt paste.
Create a code-review skill with progressive disclosure so pre-merge review stays consistent.
Ship an incident triage skill you refine after each production fire without rewriting base instructions.
How it compares
Meta authoring guide for SKILL.md packages, not an MCP server installer or runtime integration like hive-mind.
Common Questions / FAQ
Who is skill-builder for?
Solo builders and small teams on Claude Code 2.0+ who want custom, autodiscoverable skills instead of pasting long system prompts every session.
When should I use skill-builder?
Use it journey-wide when scoping repeatable rituals in Validate, encoding Build integrations, drafting Ship checklists, or Operate runbooks—anytime you need a new skill template or spec refresher.
Is skill-builder safe to install?
Review the Security Audits panel on this Prism page; the skill teaches filesystem layout and markdown authoring—avoid embedding secrets in SKILL.md or bundled scripts.
SKILL.md
READMESKILL.md - Skill Builder
# Skill Builder ## What This Skill Does Creates production-ready Claude Code Skills with proper YAML frontmatter, progressive disclosure architecture, and complete file$folder structure. This skill guides you through building skills that Claude can autonomously discover and use across all surfaces (Claude.ai, Claude Code, SDK, API). ## Prerequisites - Claude Code 2.0+ or Claude.ai with Skills support - Basic understanding of Markdown and YAML - Text editor or IDE ## Quick Start ### Creating Your First Skill ```bash # 1. Create skill directory (MUST be at top level, NOT in subdirectories!) mkdir -p ~/.claude$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 ### 📋 YAML Frontmatter (REQUIRED) Every SKILL.md **must** start with YAML frontmatter containing exactly two required fields: ```yaml --- 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**: - ✅ "API Documentation Generator" - ✅ "React Component Builder" - ✅ "Database Schema Designer" - ❌ "skill-1" (not descriptive) - ❌ "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**: - ✅ "Generate OpenAPI 3.0 documentation from Express.js routes. Use when creating API docs, documenting endpoints, or building API specifications." - ✅ "Create React functional components with TypeScript, hooks, and tests. Use when scaffolding new components or converting class components." - ❌ "A comprehensive guide to API documentation" (no "when" clause) - ❌ "Documentation tool" (too vague) #### YAML Formatting Rules ```yaml --- # ✅ CORRECT: Simple string name: "API Builder" description: "Creates REST APIs with Express and TypeScript." # ✅ 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." # ✅ CORRECT: Special characters quoted name: "JSON:API Builder" description: "Creates JSON:API compliant endpoints: pagination, filtering, relationships." # ❌ WRONG: Missing quotes with special chars name: API:Builder # YAML parse error! # ❌ 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 use