Back to directory

Claude Code — Team Onboarding Kit

This kit is a pre-configured starter repository of agents, skills, slash commands and MCP integrations meant to bring a team onto Claude Code within about thirty minutes for a specific technology stack.

Claude Code — Team Onboarding Kit

The onboarding kit targets one concrete stack: Java 21 with Spring Boot WebFlux, Node.js with NestJS, Python with LangChain, LangGraph and FastAPI, Angular with an Agent-to-User Interface renderer and Three.js, Flutter with Dart, and PostgreSQL with pgvector, Weaviate and Firebase. Cloning it and installing Claude Code is meant to give a team the same working configuration on day one.

It walks a new team member through installing an editor and Claude Code, explains what CLAUDE.md files, slash commands, subagents, skills, MCP servers, settings.json and hooks are for and when to use each, and includes an optional persistent-memory add-on and an optional voice mode. It also documents a cheaper local-model alternative and how to run multiple coordinated subagents as an agent team.

It is a Python-based repository under the MIT license.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.