Skill Builder
If you're building custom Claude Code workflows, you'll eventually need to package your own skills, and this walks you through the whole setup. It covers the required YAML frontmatter (name and description fields), progressive disclosure structure, and directory organization that Claude expects. The source shows you exactly where files go (top-level only, no nesting), how to write descriptions that help Claude know when to invoke your skill, and what a complete skill package looks like with scripts and templates. Think of it as the spec and scaffolding tool in one. Most useful when you've hit the limits of existing skills and need something purpose-built for your team's workflow.
- GitHub stars
- 240
- last updated
- Jun 11, 2026
Install
$ npx -y skills add spencermarx/open-code-review --skill 'Skill Builder' --agent claude-codeInstalls into .claude/skills of the current project.
Files
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
📋 YAML Frontmatter (REQUIRED)
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/spencermarx/open-code-review
- Categories
- DevOps & CI/CD, Git & Pull Requests, Code Review & Quality
- License
- Apache-2.0
- First seen
- Jun 11, 2026
More from spencermarx/open-code-review
All 31- Sparc Methodology
- Stream Chain
- Swarm Advanced
- Swarm Orchestration
- V3 CLI Modernization
- V3 Core Implementation
- V3 DDD Architecture
- V3 Deep Integration
- V3 MCP Optimization
- V3 Memory Unification
- V3 Performance Optimization
- V3 Security Overhaul
- V3 Swarm Coordination
- Verification & Quality Assurance
- AgentDB Advanced Features
- AgentDB Learning Plugins
- AgentDB Memory Patterns
- AgentDB Performance Optimization
- AgentDB Vector Search
- Browser
- Github Code Review
- Github Multi Repo
- Github Project Management
- Github Release Management
Recommended
More DevOps & CI/CD
V3 MCP Optimizationspencermarx/open-code-reviewMCP server optimization and transport layer enhancement for claude-flow v3. Implements connection pooling, load balancing, tool registry optimization, and perfo0skills.sh installs
sponsiosponsiolabs/sponsioInstall, observe, tune, enforce, and periodically refresh Sponsio — a runtime contract layer for LLM agents that blocks unsafe tool calls and scores output qual0skills.sh installs
frontend-designsyahiidkamil/software-engineer-ai-agent-atlasCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, 0skills.sh installs
designing-hardware-productstelagod/code-abyssAI-automated hardware product pipeline: from requirements to manufacturable Gerber + compiled firmware + cross-platform app. Orchestrates system design, ESP-IDF0skills.sh installsorchestrating-adversarial-reviewstelagod/code-abyssMulti-agent adversarial-verification orchestration for high-confidence conclusions. Fan-out finders, then verify every finding through a three-prism panel (expl0skills.sh installsshipping-changestelagod/code-abyssEnd-to-end change-shipping closed loop for non-trivial work — research → proposal doc → phased guarded implementation → PR self-review → harden → merge. Use whe0skills.sh installs