stack/packages/skills/brain/SKILL.md

---
name: mosaic-brain
description: Capture ideas, brain dumps, and semantic search across your Mosaic Stack knowledge base.
homepage: https://mosaicstack.dev
metadata: { "clawdbot": { "emoji": "🧠", "requires": { "bins": ["curl", "jq"] } } }
---

# Mosaic Brain

Capture and search ideas, brain dumps, and notes in your Mosaic Stack workspace. Provides quick capture, semantic search, and tag management.

## Setup

1. Ensure Mosaic Stack API is running (default: `http://localhost:3001`)
2. Set environment variables:

   ```bash
   export MOSAIC_API_URL="http://localhost:3001"
   export MOSAIC_WORKSPACE_ID="your-workspace-uuid"
   export MOSAIC_API_TOKEN="your-auth-token"
   ```

3. Optionally create `~/.config/mosaic/brain.conf`:
   ```bash
   MOSAIC_API_URL=http://localhost:3001
   MOSAIC_WORKSPACE_ID=your-workspace-uuid
   MOSAIC_API_TOKEN=your-auth-token
   ```

## Common Commands

### Quick Brain Dump

Capture an idea quickly without thinking about categorization:

```bash
# Quick capture
./brain.sh capture "Had a great idea about using AI for code reviews"

# Capture with title
./brain.sh capture "Remember to follow up with the team about the new feature" --title "Team Follow-up"
```

### Create Detailed Idea

Create an idea with full metadata:

```bash
./brain.sh create \
  --title "New Feature Idea" \
  --content "Implement semantic search across all documents..." \
  --tags "feature,ai,search" \
  --category "product"
```

### Semantic Search

Search your brain using natural language:

```bash
# Query your knowledge base
./brain.sh query "What did I say about AI and code reviews?"

# Search with limit
./brain.sh search "project ideas" --limit 10
```

### List Ideas

```bash
# List recent ideas
./brain.sh list

# List with filters
./brain.sh list --limit 20 --tags "work,urgent"
```

### Get Specific Idea

```bash
./brain.sh get <idea-id>
```

### Update Idea

```bash
./brain.sh update <idea-id> \
  --title "Updated Title" \
  --tags "new,tags" \
  --status "IN_PROGRESS"
```

### Delete Idea

```bash
./brain.sh delete <idea-id>
```

### Tag Management

```bash
# List all tags
./brain.sh tags

# Add tags to an idea
./brain.sh update <idea-id> --add-tags "urgent,review"

# Remove tags from an idea
./brain.sh update <idea-id> --remove-tags "old-tag"
```

## API Endpoints

The skill uses these Mosaic Stack API endpoints:

- **POST /api/ideas/capture** - Quick brain dump (minimal fields)
- **POST /api/ideas** - Create full idea with metadata
- **GET /api/ideas** - List ideas with filters
- **GET /api/ideas/:id** - Get specific idea
- **PATCH /api/ideas/:id** - Update idea
- **DELETE /api/ideas/:id** - Delete idea
- **POST /api/brain/query** - Semantic search/query
- **GET /api/brain/search** - Search ideas

## Configuration

Config file priority:

1. Environment variables
2. `~/.config/mosaic/brain.conf`
3. Default values

Required settings:

- `MOSAIC_API_URL` - API base URL (default: http://localhost:3001)
- `MOSAIC_WORKSPACE_ID` - Your workspace UUID
- `MOSAIC_API_TOKEN` - Authentication token

## Usage from Clawdbot

Natural language examples:

- "Remember this..." / "Note to self..." → Quick capture
- "What did I say about..." → Semantic search
- "Show me my recent ideas" → List ideas
- "Brain dump: [content]" → Quick capture

## Notes

- Quick capture (`capture`) is fastest - just dump your thought
- Semantic search (`query`) uses AI to find relevant ideas
- Regular search is keyword-based, faster but less intelligent
- Tags are automatically indexed for quick filtering
- Ideas support markdown formatting in content