agent▌

作为 Agent Teams 协调器，你的职责包括：明确每个角色的职责边界、把控执行过程、对最终产品质量负责。

You are an expert LangChain agent developer specializing in production-grade AI systems using LangChain 0.1+ and LangGraph.

Scaffold a declarative agent for Microsoft 365 Copilot integrated with an MCP server. \n \n Generates complete project structure including manifest.json, declarativeAgent.json, and ai-plugin.json with tool definitions auto-imported from MCP servers \n Supports OAuth 2.0 and SSO authentication with environment variable configuration and secure credential storage \n Provides response semantics mapping to extract and format API response data for Copilot consumption \n Includes MCP server integratio

Terminal-based disposable email inbox management for agent automation workflows. \n \n Create temporary mailboxes, poll for new messages with configurable wait/interval, and retrieve full message details including body and source \n JSON-native output with key fields ( email , messageId , subject , from.address , createdAt ) designed for agent parsing and summarization \n Manage multiple mailbox profiles locally with accounts list , use , and remove commands; supports default alias for simplifie

Bootstrap a modular AI agent with OpenRouter SDK, extensible hooks, and optional terminal UI. \n \n Standalone agent core runs independently of any UI, with event-based hooks for streaming responses, tool calls, reasoning, and errors \n Items-based streaming model emits complete, progressively updated items by ID rather than accumulating chunks, enabling efficient React state management and concurrent output handling \n Supports 300+ language models via OpenRouter with dynamic model discovery; u

AI agent architecture for anticipating needs, surviving context loss, and continuous self-improvement. \n \n Implements Write-Ahead Logging (WAL) Protocol to capture corrections, decisions, and preferences before responding, ensuring critical details persist across sessions \n Three-tier memory system (SESSION-STATE.md, daily logs, curated MEMORY.md) with Working Buffer for context survival during compaction and Compaction Recovery for seamless resumption \n Proactive behavior patterns including

Playwright-based browser automation with element refs for AI agents, supporting navigation, interaction, screenshots, and video recording. \n \n Provides 6 core functions: open (navigate with config), snapshot (refresh element refs), interact (click/fill/drag/upload/scroll), screenshot, execute (JavaScript), and close \n Element interaction uses simple @e ref system that invalidates after navigation, requiring re-snapshot calls to maintain accurate selectors \n Supports video recording with opti

Universal self-improving agent that learns from all skill experiences using multi-memory architecture. \n \n Implements semantic, episodic, and working memory to extract patterns, abstract insights, and continuously evolve skill guidance across the codebase \n Auto-triggers on skill completion, errors, and session events via hooks-based integration; detects and corrects inaccurate guidance with traceable evolution markers \n Prioritizes updates across 10+ skill categories (PRD planning, architec

Drop-in React/Next.js agent component with runtime, tools, streaming, and human-in-the-loop approvals built in. \n \n Single component handles agent execution, tool lifecycle management, real-time token streaming, and approval flows without backend logic \n Supports client-side tools that run in the browser, file and image uploads, and declarative JSON widgets for agent-generated UI \n Includes API proxy route setup for Next.js and configurable agent parameters like model selection, system promp

AI-powered autonomous extraction of structured data from complex multi-page websites. \n \n Navigates sites intelligently to locate and extract data, returning results as JSON with optional schema validation \n Supports custom JSON schemas for predictable structured output, or freeform extraction when schema is not provided \n Offers two model tiers (spark-1-mini and spark-1-pro) with credit limits and optional waiting for inline results \n Best suited for multi-page extraction tasks; use simple