菜单
Develop and maintain the standalone Lumina MCP server. Use when editing files under mcp_server/, adding or modifying tools, resources, prompts, middleware, configuration, or transport behavior for the Model Context Protocol server.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Work on Lumina deployment and infrastructure assets. Use when editing terraform/, aws/, docker-compose.yml, DEPLOYMENT.md, ADVANCED_DEPLOYMENTS.md, agentic_ai/deployments/, or other files related to Docker, Terraform, AWS or Azure rollout behavior, environment wiring, and release automation.
Work on the Python multi-agent pipeline and MCP client in agentic_ai. Use when editing files under agentic_ai/, changing agent orchestration, configuration loading, MCP client connectivity, async execution flow, pipeline startup commands, or cloud deployment wrappers for the Python service.
Implement and debug the Express and TypeScript backend for Lumina. Use when editing files under server/src or server/package.json, changing authentication, conversations, guest flows, chat routes, models, middleware, API contracts, or Gemini and Pinecone service wiring outside the dedicated knowledge-ingestion workflow.
Build, refine, and debug the React/Vite frontend for Lumina. Use when editing files under client/src or client/package.json, changing chat UX, landing page content, auth flows, routing, theme behavior, markdown rendering, animations, responsive layout, or frontend API wiring.
Manage Lumina's retrieval-augmented generation and knowledge ingestion workflow. Use when editing server/src/services/knowledgeBase.ts, server/src/services/pineconeClient.ts, server/src/scripts/knowledgeCli.ts, server/src/models/KnowledgeSource.ts, files under server/knowledge, manifest-based sync inputs, or debugging grounded answers, retrieval relevance, source lifecycle, and inline citations.
| name | lumina-mcp-server |
| description | Develop and maintain the standalone Lumina MCP server. Use when editing files under mcp_server/, adding or modifying tools, resources, prompts, middleware, configuration, or transport behavior for the Model Context Protocol server. |
Use this skill for the standalone MCP server at mcp_server/. The server implements the Model Context Protocol with 32 tools across 8 categories, 7 resources, and 6 prompts.
references/file-map.md to locate the tool, resource, prompt, or middleware that owns a behavior.references/tool-development.md when adding or modifying MCP tools.input_schema definitions are external contracts — MCP clients depend on them.tools/.ToolHandler(ABC) with name, description, input_schema, and handle().register(cfg) function._ToolRegistry entry in tools/__init__.py.MiddlewareChain.MCP_API_KEY, MCP_RATE_LIMIT, MCP_LOG_LEVEL).python -m compileall mcp_server for compile-time validation.python -m mcp_server --log-level DEBUG for startup smoke testing when dependencies are installed.