Nimblebraininc Skills

Build MCP servers end-to-end — scaffold a production-ready Python or TypeScript server from API docs, implement tools, validate the MCPB bundle, embed a skill resource, and release to the mpak registry. Covers the full lifecycle from API analysis to published bundle. Use when building a new MCP server, wrapping an API as MCP, or creating an integration. Triggers include "build an MCP server", "create a server for X", "/mcpb".

Build a Synapse UI for an MCP server — a React app built to one inlined HTML file, served as a `ui://` resource and rendered in the NimbleBrain host. Works with any MCP server (Python/FastMCP or TypeScript). Use when building a Synapse app or UI, adding a frontend to an MCP server, making a server "visual" or "interactive", or wiring a `ui://` resource.

Get started contributing to NimbleBrain open source — find an integration to build, set up your environment, propose a new idea, or check on your work. Use when onboarding as a contributor, picking something to build, filing an issue, or asking "what should I build". Triggers include "I'm a new contributor", "onboard me", "what should I build", "show me open issues", "file an issue".

Best practices for MCP servers — how to name, describe and schema a tool so a model actually calls it, how resources and prompts differ, and what the boundary must never trust. Applies while authoring a new surface or as an audit of an existing one, grounded in the MCP specification and the tool-authoring guidance from Anthropic and OpenAI. Triggers include "MCP best practices", "name this tool", "audit this MCP server", "why won't the model call my tool", "/mcp-best-practices".