forge-editor

---

Load a specific skill by name

Run tests on a virtual test environment

List all available skills with categories and descriptions

Suggest relevant skills based on your current task or prompt

Create virtual test environment for hooks, plugins, or agents

---

Validate plugin structure and run tests before deployment

Create skills, agents, or commands with smart routing

---

---

---

---

---

---

---

---

---

---

---

Designs new skills through iterative questioning. Determines skill type and creates structure.

Converts existing code into reusable skills. Identifies scriptable operations and extracts patterns.

Creates subagents that use skills with isolated context. Single-skill or multi-skill architecture.

---

---

---

---

Philosophical/meta project analysis - critical analysis framework that asks "why?"

---

Claude Code Hook system reference for capabilities, possibilities, and limitations. Use when you want to know what hooks can do.

LLM invocation patterns from hooks via SDK. Use when you need background agents, CLI calls, or cost optimization.

Claude Code Hook system entry point. Guides you to the right skill based on your needs.

Comprehensive Claude Code hook patterns for automation, state management, and external integration. Use when implementing hooks for validation, workflow gates, MCP integration, or state machines.

U-llm-sdk and claude-only-sdk patterns. Use when working on projects with LLM service, designing LLM integrations, or implementing AI-powered features.

---

---

Single-skill vs multi-skill subagent architectures. Use when designing subagents.

Virtual test environment for Claude Code hooks, plugins, and agents. Use when testing or validating plugin components without affecting production.

---

Categorize and display available skills. Use when listing or selecting skills.

Best practices for skill structure and types. Use when creating skills.

---

---

---

32 hooks across 5 events