Menu
Categorize and display available skills. Use when listing or selecting skills.
Patterns for configuring agent tools correctly
Philosophical/meta project analysis - critical analysis framework that asks "why?"
Smart routing wizard for creating skills, agents, commands with complexity-based skill loading
Language, style, and comment quality guidelines for plugin content
Protocol-based workflow enforcement with validation dependencies and anti-bypass protection
Analyze vague user ideas and recommend architecture based on actual needs, not predefined categories. Front-end for clarifying ambiguous requests before routing to appropriate skillmaker tools.
| name | skill-catalog |
| description | Categorize and display available skills. Use when listing or selecting skills. |
| allowed-tools | ["Read"] |
Claude Code maintains a global skill registry. All installed skills are automatically available.
System Prompt (자동 포함):
<available_skills>
<skill><name>skill-name</name><description>...</description></skill>
...
</available_skills>
No discovery needed - Claude already knows all skills.
| Source | Location | Registration |
|---|---|---|
| Plugin Skills | ~/.claude/plugins/*/skills/ | marketplace.json skills array |
| User Skills | ~/.claude/skills/ | Automatic |
| Project Skills | .claude/skills/ | Automatic |
All sources merge into a single global registry accessible via Skill tool.
| Icon | Category | Keywords |
|---|---|---|
| 📊 | Data & Analysis | data, sql, database, query |
| 🎨 | Design & Frontend | ui, frontend, component, design |
| 📝 | Documentation | doc, writing, content |
| 🔧 | Development Tools | build, deploy, test, ci |
| 🔒 | Security | security, auth, validation |
| 🤖 | AI & Orchestration | ai, workflow, orchestration, agent |
| 📦 | Code Generation | generate, scaffold, template |
| 🔍 | Code Analysis | analyze, review, refactor |
Claude can reference <available_skills> from system prompt directly.
Skill("skill-name") # Load skill into context
Skill("plugin:skill-name") # Fully qualified name
skills: skill1, skill2 # Auto-loaded at agent start
For orchestrator agents, help users select skills:
## Available Skills by Category
### 🔍 Code Analysis
- **serena-refactor:analyze** - SOLID violation detection
- **pr-review-toolkit:code-reviewer** - PR code review
### 🤖 AI & Orchestration
- **forge-editor:orchestration-patterns** - Agent architecture
- **forge-editor:mcp-gateway-patterns** - MCP isolation
Which skills does your agent need?