Agent Building skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
model-switcher
タスクの複雑さに応じて Claude のモデルを自動的に切り替える。複雑なタスク（アーキテクチャ設計、大規模リファクタリング、難解なバグ修正）では opus を、単純なタスク（小さな修正、フォーマット、簡単な質問）では sonnet を自動選択。コストと品質のバランスを最適化。
multi-agent-orch
Plans and orchestrates multi-agent swarms, defining roles, topologies, and handoffs.
multi-modal
Multi-modal prompting with vision, audio, and document understanding
neuroscience-foundations
Apply biological brain patterns to agent design
oh-my-ccg-init
初始化 oh-my-ccg 环境 — 验证 MCP 服务器、Codex、Gemini
open-commerce
Open Commerce MCP and AI operations context
openai-agents
Use when integrating OpenAI GPT models for conversational AI. Covers chat completions, streaming responses, function calling, system prompts, token management, cost optimization, error handling, and building specialized agent personas for Physical AI tutoring.
opence-compound
Document learnings, capture repeatable workflows as skills, and prepare to compound an opence change.
orca-architecture
This skill should be used when the user asks about "Orca architecture", "knowledge graph design", "MCP server structure", "nugget storage", "telemetry design", "Orca refactoring", or is planning changes to Orca components. Provides decision capture workflows, bounded exploration patterns, and architecture discussion guidance.