my-vault/.claude/commands/init-bootstrap.md

name, description, allowed-tools, argument-hint

name	description	allowed-tools	argument-hint
init-bootstrap	Interactive setup wizard that helps new users create a personalized CLAUDE.md file based on their Obsidian workflow preferences	Read Write MultiEdit Bash Task	(optional) path to existing vault or 'new' for fresh setup

Initialize Bootstrap Configuration

This command helps you create a personalized CLAUDE.md configuration file by asking questions about your Obsidian workflow and preferences.

Task

Read the CLAUDE-BOOTSTRAP.md template and interactively gather information about the user's:

• Existing vault structure (if any)
• Workflow preferences
• Note-taking style
• Organization methods
• Specific requirements

Then generate a customized CLAUDE.md file tailored to their needs.

Process

1. Initial Environment Setup

   • Check for package.json and run pnpm install if needed
   • Verify core dependencies are installed
   • Check git status and initialize if needed
   • Create base folder structure (00_Inbox through 06_Metadata)

2. Check Existing Configuration

   • Look for existing CLAUDE.md
   • If exists, ask if they want to update or start fresh
   • Check for CLAUDE-BOOTSTRAP.md template

3. Gather Vault Information

   • Ask if they have an existing vault or starting new
   • If existing, explore current folder structure
   • Document any custom organization patterns

4. Ask Configuration Questions

   • "Do you follow the PARA method or have a different organization system?"
   • "What are your main use cases? (research, writing, project management, knowledge base, daily notes)"
   • "Do you use any specific plugins or tools with Obsidian?"
   • "What's your preferred naming convention for files?"
   • "Do you work with attachments frequently? (images, PDFs, etc.)"
   • "Do you use git for version control?"
   • "Any specific websites or resources you reference often?"
   • "Do you have any specific writing style preferences?"
   • "Are there any workflows or patterns you want Claude to follow?"

5. Optional MCP Server Setup

   • Ask: "Would you like to set up Gemini Vision for analyzing images and PDFs?"
   • If yes:
     • Guide to get API key from https://aistudio.google.com/apikey
     • Help add to shell profile (.zshrc, .bashrc, etc.)
     • Run claude mcp add --scope project gemini-vision node .claude/mcp-servers/gemini-vision.mjs
     • Configure .mcp.json with API key
     • Test the connection with a sample command

6. Generate Custom Configuration

   • Start with CLAUDE-BOOTSTRAP.md as base
   • Add user-specific sections:
     • Custom folder structure
     • Personal workflows
     • Preferred tools and scripts
     • Specific guidelines
     • MCP configuration if set up
   • Include their websites/resources if provided
   • Add any custom naming conventions

7. Create Supporting Files

   • Generate initial folder structure if new vault
   • Create README files for main folders
   • Create 05_Attachments/Organized/ directory
   • Set up .gitignore if using git (include .mcp.json, node_modules)
   • Create initial templates if requested
   • Make initial git commit if repository was initialized

8. Run Test Commands

   • Execute pnpm vault:stats to verify scripts work
   • Test attachment commands if folders exist
   • Test MCP tools if configured
   • Verify git is tracking files correctly

9. Provide Next Steps

   • Summary of what was created and configured
   • Quick start guide specific to their setup
   • List of available commands they can use
   • Test commands to verify everything works
   • Suggestions for first tasks based on their use cases
   • How to modify configuration later

Example Output

# Your Obsidian Vault Configuration

Generated on: [Date]
Based on your preferences for: [main use cases]
Setup completed with: ✅ Dependencies ✅ Folder structure ✅ Git initialized

## Your Custom Folder Structure

[Their specific structure with explanations]

## Your Workflows

### Daily Routine
[Based on their answers]

### Project Management
[Their specific approach]

## Your Preferences

### File Naming
- Pattern: [their convention]
- Examples: [specific examples]

### Tools & Scripts
[Relevant scripts for their workflow]

## MCP Servers (if configured)

### Gemini Vision
- Status: ✅ Configured and tested
- API Key: Set in .mcp.json
- Test with: `Use gemini-vision to analyze [image path]`

## Available Commands

### Vault Management
- `pnpm vault:stats` - Show vault statistics
- `pnpm attachments:list` - List unprocessed attachments
- `pnpm attachments:organized` - Count organized files

### Claude Commands
- `claude run thinking-partner` - Collaborative thinking mode
- `claude run daily-review` - Review your day
- `claude run init-bootstrap` - Re-run this setup

## Quick Start

1. [Personalized first step]
2. [Next action based on their goals]
3. [Specific to their workflow]

## Setup Summary

✅ Dependencies installed (pnpm install)
✅ Folder structure created
✅ Git repository initialized
✅ CLAUDE.md personalized
[✅ MCP Gemini Vision configured - if set up]
[✅ First commit made - if git was initialized]

Interactive Example

User: claude run init-bootstrap
Assistant: Welcome! I'll help you set up your personalized Obsidian + Claude configuration.

First, let me set up your environment...
[Runs pnpm install to install dependencies]
[Creates folder structure if missing]
[Checks git status]

✅ Dependencies installed
✅ Core folders created
✅ Git repository ready

Now let me ask you a few questions to customize your setup:

1. **What will you primarily use this vault for?**
   (research, writing, project management, daily notes, knowledge base, or combination?)

User: I'll use it for research and writing, plus managing client projects

Assistant: Great! I'll configure your vault for research, writing, and client project management.

[Continues with questions...]

Would you like to set up Gemini Vision for analyzing images and PDFs? This requires a Google API key.

User: Yes, that sounds useful

Assistant: Excellent! Here's how to get your API key:
1. Go to https://aistudio.google.com/apikey
2. Click "Create API Key"
3. Copy the key (starts with AIzaSy...)

Once you have it, paste it here and I'll configure everything for you.