developing-openai-agents-sdk-agents
Build, create, debug, review, implement, and optimize agentic AI applications using the OpenAI Agents SDK for TypeScript. Use when creating new agents, defining tools, implementing handoffs between agents, adding guardrails, debugging agent behavior, reviewing agent code, or orchestrating multi-agent systems with the @openai/agents package.
tool-design
Design effective tools for AI agents - tool descriptions, consolidation principles, architectural reduction, MCP naming conventions, and error handling
design-system-context
Automatic design system context injection for UI consistency
voice-interaction
Enable voice conversations with Claude Code - speak commands and hear responses
embassy-rp
Embassy HAL for Raspberry Pi RP2040 and RP2350 microcontrollers. Use when working with Pico/Pico 2 peripherals, GPIO, SPI, I2C, UART, PIO, or flashing with picotool.
agent-tuning
Configure and optimize AI coding agents (OpenCode/Claude). Use when setting up or improving agent behavior.
model-deployment
Export and deploy fine-tuned models to production. Covers GGUF/Ollama, vLLM, HuggingFace Hub, Docker, quantization, and platform selection. Use after fine-tuning when you need to deploy models efficiently.
adversarial-examples
Generate adversarial inputs, edge cases, and boundary test payloads for stress-testing LLM robustness
docs-updater
プロジェクトの CLAUDE.md を更新する。「CLAUDE.md を更新して」「ルールを追加」「プロジェクトルールを変更」「Claude のルール」「AI ドキュメント更新」「CLAUDE.md に追記」「ルールを編集」などで起動。プロジェクト固有のルールやガイドラインを管理。
spawning-agents-on-the-command-line
Use when subagents need to delegate work but can't use Task tool, or when needing to test skills in isolated context - spawns Claude instances via CLI backgrounding with JSON responses
context-llm-pipeline
RAG pipeline, embeddings, LLM interactions, and flow orchestration.
rag-architecture
Use when building retrieval-augmented generation systems. Covers chunking strategies, embedding models, vector databases, retrieval patterns, and hybrid search. Apply when adding knowledge bases, document Q&A, or semantic search to applications.
llm-mcp-builder-dev
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
testing-claude-plugins-with-python-sdk
Use when testing Claude Code plugins programmatically, building SDK applications, encountering plugin loading failures (plugins array empty), getting AttributeError on message.type, or needing verified Claude Agents SDK Python patterns - provides complete reference for correct message handling (isinstance not .type), plugin loading (setting_sources required), content block iteration, and all working patterns from official documentation
product-planner
AI产品经理,整套"0基础 AI 协同开发系统"的源头角色与项目总导演。将自然语言需求转换为可执行的产品规划与标准化任务卡,协调 Backend/Frontend/SCF/QA/Reviewer/Deploy/Billing Guard 多部门有序并行交付。遵循易用性优先、契约优先、门禁治理、MVP-first 的工程基线。适用于收到自然语言需求时使用。
context-compression
Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need to summarize conversation history, or when optimizing tokens-per-task rather than tokens-per-request.
faf-init
Initialize project.faf files when starting new projects, when user asks to set up AI context, create project DNA, or needs persistent context. Automatically detects project type (React, TypeScript, Next.js, Svelte, etc.), generates appropriate IANA-registered format (application/vnd.faf+yaml), and creates project.faf in repository root. Use when user mentions "context", "project setup", "AI-readiness", or "FAF".
llm-sdk-guide
U-llm-sdk and claude-only-sdk patterns. Use when working on projects with LLM service, designing LLM integrations, or implementing AI-powered features.
isaac-patterns
NVIDIA Isaac Sim and Isaac ROS integration patterns for Physical AI applications.
dispatching-parallel-agents
Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently
claude-agent-sdk
Comprehensive guide for building production-ready agents with the Claude Agent SDK. Use when creating agents, designing tools, implementing subagents, managing sessions, integrating MCP servers, or understanding SDK-native features. Emphasizes documentation-first approach and using only SDK native capabilities.
