Manages long-term memory for users across conversations. Automatically queries relevant memories when starting a new topic, and saves important personal information, habits, schedules, and user-requested memories. Use this when discussing user background, preferences, or plans; starting a new task or project; users mention personal details or ask to remember something.
Connect to the Pieces MCP server (SSE) and reliably query or write to Pieces Long‑Term Memory (LTM) using query/write tool patterns (e.g., ask_pieces_ltm + create_pieces_memory), with practical troubleshooting and request-shaping examples.
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).
Collaborates with OpenAI Codex as an external AI agent for second opinions on complex decisions. Provides guidelines for brainstorming, plan validation, and code review workflows. Use when making architectural decisions, validating implementation plans, reviewing code after significant changes, or consulting codex, codex-reply, or codex-review MCP tools.
Comprehensive development guides for advanced Kailash SDK features including custom node development, MCP development, async patterns, testing strategies, production deployment, RAG systems, security patterns, monitoring, and SDK internals. Use when asking about 'development guide', 'advanced features', 'custom node development', 'async node development', 'MCP development', 'production deployment', 'testing strategies', 'RAG implementation', 'security patterns', 'monitoring setup', 'circuit breaker', 'compliance', 'edge computing', or 'SDK internals'.
Programmatic browser automation using Playwright MCP server. Use when building Claude Code tools or applications that need web automation, testing, scraping, or browser interaction. Provides structured accessibility-based automation without screenshots or vision models.
Kailash MCP (Model Context Protocol) - production-ready MCP server implementation for AI agent integration. Use when asking about 'MCP', 'Model Context Protocol', 'MCP server', 'MCP client', 'MCP tools', 'MCP resources', 'MCP prompts', 'MCP authentication', 'MCP transports', 'stdio transport', 'SSE transport', 'HTTP transport', 'MCP testing', 'progress reporting', or 'structured tools'.
Token-efficient proxy for Naki's 47 MCP tools. Routes user intent to optimal MCP tool via agent isolation, saving 40-70% tokens. Use for any Naki game control, bot status, or UI operation.
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.
Obsidian vault notes (AILSS): search/summarize/edit (frontmatter, tags/keywords, typed links/backlinks, broken links; retrieval-first MCP; gated writes)
Auxilia desenvolvimento do chat NathIA no projeto Nossa Maternidade. Conhece a arquitetura de agentes IA (MaternalChatAgent, EmotionAnalysisAgent), MCP servers (Supabase, GoogleAI, OpenAI, Anthropic), e prompts. Use ao trabalhar com chat, agentes IA, ou integracao Gemini.
Guide for creating and managing Claude Code plugins. Use when creating a new plugin, adding plugin components (commands, agents, skills, hooks, MCP servers), or validating plugin structure and configuration.
Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.
Create integration test documents and evidence using aws-mcp-server script. Retrieve results with read-only commands and generate Markdown evidence. Job execution is performed by the user.
指南：创建高质量的 MCP（模型上下文协议）服务器，使 LLM 能够通过精心设计的工具与外部服务交互。在构建 MCP 服务器以集成外部 API 或服务时使用，无论是 Python（FastMCP）还是 Node/TypeScript（MCP SDK）。
Externalize detailed memory to Memory Bank before conversation summarization to prevent context loss. Triggers: CP, checkpoint, save, 存檔, 記一下, 保存, sync memory, dump, 先記著.
Get official Claude Code documentation. Use when the user asks about Claude Code features OR when you need to create/implement plugins, skills, hooks, subagents, slash commands, or MCP servers. Always retrieve documentation BEFORE implementing any Claude Code feature. Topics include configuration, settings, deployment, and troubleshooting.
Expert knowledge in creating and configuring Claude Code components (subagents, skills, slash commands, hooks, MCP integrations). Use when the user asks to create, modify, or extend .claude/ directory components. Follows official best practices and documentation standards.
