onboard

Scan a project's structure and generate a .md file of its AI-context.

Updated Jan 19, 2026
One-click install
npx skills add https://github.com/howdycarter/Mothership --skill onboard-howdycarter
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: onboard
Source: https://github.com/howdycarter/Mothership/tree/main/.claude/skills/onboard
Command: npx skills add https://github.com/howdycarter/Mothership --skill onboard-howdycarter

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Scans a project to generate a concise, AI-friendly codebase document that captures stack, structure, conventions, and dependencies for context.

Core Features & Use Cases

  • Automatically detects project structure (package.json, tsconfig.json, directories) and identifies the tech stack, framework, language, and deployment hints.
  • Produces a readable .mothership/codebase.md that can be consumed by AI agents to understand codebases and context.
  • Use Case: Onboard a new AI agent to a repository by generating a ready-to-consume codebase snapshot.

Quick Start

Run onboard with your project path to generate .mothership/codebase.md.

Frequently Asked Questions about onboard

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate AI-ready documentation from my codebase?

To generate AI-ready documentation, you scan your project structure to produce a codebase.md file. This file captures your stack, conventions, and dependencies into a concise markdown snapshot for AI agents to consume.

What is the best way to onboard an AI agent to a Node.js and TypeScript repository?

Onboarding an AI agent involves generating a structured markdown snapshot of your codebase. By scanning package.json and tsconfig.json, you can map routing and component patterns into a readable document for AI context.

Can I use this to document project structure and tech stack conventions automatically?

Yes, you can automatically document project structure and conventions. The scanning process detects directories, identifies your framework and language, and extracts deployment hints to output a comprehensive codebase document.

Does the generated codebase documentation work with diverse project layouts?

The generated codebase documentation applies to diverse stacks and project layouts. It maps your specific routing and component patterns to produce a structured markdown file that accurately reflects your unique project structure.

How do I create a codebase.md file for AI context consumption?

You create a codebase.md file by running a project scan with your designated path. The scan reads your configuration files and outputs the structured markdown document into a .mothership directory for AI consumption.

What limitations exist when scanning a codebase to identify tech stack and dependencies?

A limitation of scanning a codebase to identify dependencies is that the generated markdown snapshot is a static representation. It captures the project state at the time of the scan and requires re-running to reflect subsequent codebase changes.