Skip to content

Docs: Add Google Antigravity installation instructions #13

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
codeF1x wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Docs: Add Google Antigravity installation instructions #13

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0a096c0
docs: add Google Antigravity installation instructions
codeF1x Jan 17, 2026
af89718
docs: add prerequisite note for Antigravity users
codeF1x Jan 17, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
95 changes: 72 additions & 23 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,7 @@ The web UI runs skills in a sandbox without network access, which this skill req
## The Problem

When you tell [Claude Code](https://github.com/anthropics/claude-code) to "search through my local documentation", here's what happens:

- **Massive token consumption**: Searching through documentation means reading multiple files repeatedly
- **Inaccurate retrieval**: Searches for keywords, misses context and connections between docs
- **Hallucinations**: When it can't find something, it invents plausible-sounding APIs
Expand All @@ -47,12 +48,12 @@ Your Task → Claude asks NotebookLM → Gemini synthesizes answer → Claude wr

## Why NotebookLM, Not Local RAG?

| Approach | Token Cost | Setup Time | Hallucinations | Answer Quality |
|----------|------------|------------|----------------|----------------|
| **Feed docs to Claude** | 🔴 Very high (multiple file reads) | Instant | Yes - fills gaps | Variable retrieval |
| **Web search** | 🟡 Medium | Instant | High - unreliable sources | Hit or miss |
| **Local RAG** | 🟡 Medium-High | Hours (embeddings, chunking) | Medium - retrieval gaps | Depends on setup |
| **NotebookLM Skill** | 🟢 Minimal | 5 minutes | **Minimal** - source-grounded only | Expert synthesis |
| Approach | Token Cost | Setup Time | Hallucinations | Answer Quality |
| ----------------------- | ---------------------------------- | ---------------------------- | ---------------------------------- | ------------------ |
| **Feed docs to Claude** | 🔴 Very high (multiple file reads) | Instant | Yes - fills gaps | Variable retrieval |
| **Web search** | 🟡 Medium | Instant | High - unreliable sources | Hit or miss |
| **Local RAG** | 🟡 Medium-High | Hours (embeddings, chunking) | Medium - retrieval gaps | Depends on setup |
| **NotebookLM Skill** | 🟢 Minimal | 5 minutes | **Minimal** - source-grounded only | Expert synthesis |

### What Makes NotebookLM Superior?

Expand Down Expand Up @@ -80,7 +81,25 @@ git clone https://github.com/PleasePrompto/notebooklm-skill notebooklm
"What are my skills?"
```

### Google Antigravity Installation

> **Prerequisite**: Please ensure you have read the [official documentation](https://antigravity.google/docs/skills) to understand how to install and manage skills in Google Antigravity.

1. Clone this repository:

```bash
git clone https://github.com/PleasePrompto/notebooklm-skill temp_notebooklm
```

2. Copy the skill to your global skills directory:

- **Windows**: `%USERPROFILE%\.gemini\antigravity\skills\notebooklm-skill`
- **Mac/Linux**: `~/.gemini/antigravity/skills/notebooklm-skill`

3. (Optional) Clean up the temporary directory.

When you first use the skill, it automatically:

- Creates an isolated Python environment (`.venv`)
- Installs all dependencies including **Google Chrome**
- Sets up browser automation with Chrome (not Chromium) for maximum reliability
Expand All @@ -95,6 +114,7 @@ When you first use the skill, it automatically:
### 1. Check your skills

Say in Claude Code:

```
"What skills do I have?"
```
Expand All @@ -106,11 +126,13 @@ Claude will list your available skills including NotebookLM.
```
"Set up NotebookLM authentication"
```
*A Chrome window opens → log in with your Google account*

_A Chrome window opens → log in with your Google account_

### 3. Create your knowledge base

Go to [notebooklm.google.com](https://notebooklm.google.com) → Create notebook → Upload your docs:

- 📄 PDFs, Google Docs, markdown files
- 🔗 Websites, GitHub repos
- 🎥 YouTube videos
Expand All @@ -121,15 +143,19 @@ Share: **⚙️ Share → Anyone with link → Copy**
### 4. Add to your library

**Option A: Let Claude figure it out (Smart Add)**

```
"Query this notebook about its content and add it to my library: [your-link]"
```

Claude will automatically query the notebook to discover its content, then add it with appropriate metadata.

**Option B: Manual add**

```
"Add this NotebookLM to my library: [your-link]"
```

Claude will ask for a name and topics, then save it for future use.

### 5. Start researching
Expand All @@ -148,14 +174,14 @@ This is a **Claude Code Skill** - a local folder containing instructions and scr

### Key Differences from MCP Server

| Feature | This Skill | MCP Server |
|---------|------------|------------|
| **Protocol** | Claude Skills | Model Context Protocol |
| **Installation** | Clone to `~/.claude/skills` | `claude mcp add ...` |
| **Sessions** | Fresh browser each question | Persistent chat sessions |
| **Compatibility** | Claude Code only (local) | Claude Code, Codex, Cursor, etc. |
| **Language** | Python | TypeScript |
| **Distribution** | Git clone | npm package |
| Feature | This Skill | MCP Server |
| ----------------- | --------------------------- | -------------------------------- |
| **Protocol** | Claude Skills | Model Context Protocol |
| **Installation** | Clone to `~/.claude/skills` | `claude mcp add ...` |
| **Sessions** | Fresh browser each question | Persistent chat sessions |
| **Compatibility** | Claude Code only (local) | Claude Code, Codex, Cursor, etc. |
| **Language** | Python | TypeScript |
| **Distribution** | Git clone | npm package |

### Architecture

Expand All @@ -171,6 +197,7 @@ This is a **Claude Code Skill** - a local folder containing instructions and scr
```

When you mention NotebookLM or send a notebook URL, Claude:

1. Loads the skill instructions
2. Runs the appropriate Python script
3. Opens a browser, asks your question
Expand All @@ -182,35 +209,41 @@ When you mention NotebookLM or send a notebook URL, Claude:
## Core Features

### **Source-Grounded Responses**

NotebookLM significantly reduces hallucinations by answering exclusively from your uploaded documents. If information isn't available, it indicates uncertainty rather than inventing content.

### **Direct Integration**

No copy-paste between browser and editor. Claude asks and receives answers programmatically.

### **Smart Library Management**

Save NotebookLM links with tags and descriptions. Claude auto-selects the right notebook for your task.

### **Automatic Authentication**

One-time Google login, then authentication persists across sessions.

### **Self-Contained**

Everything runs in the skill folder with an isolated Python environment. No global installations.

### **Human-Like Automation**

Uses realistic typing speeds and interaction patterns to avoid detection.

---

## Common Commands

| What you say | What happens |
|--------------|--------------|
| *"Set up NotebookLM authentication"* | Opens Chrome for Google login |
| *"Add [link] to my NotebookLM library"* | Saves notebook with metadata |
| *"Show my NotebookLM notebooks"* | Lists all saved notebooks |
| *"Ask my API docs about [topic]"* | Queries the relevant notebook |
| *"Use the React notebook"* | Sets active notebook |
| *"Clear NotebookLM data"* | Fresh start (keeps library) |
| What you say | What happens |
| --------------------------------------- | ----------------------------- |
| _"Set up NotebookLM authentication"_ | Opens Chrome for Google login |
| _"Add [link] to my NotebookLM library"_ | Saves notebook with metadata |
| _"Show my NotebookLM notebooks"_ | Lists all saved notebooks |
| _"Ask my API docs about [topic]"_ | Queries the relevant notebook |
| _"Use the React notebook"_ | Sets active notebook |
| _"Clear NotebookLM data"_ | Fresh start (keeps library) |

---

Expand All @@ -221,6 +254,7 @@ Uses realistic typing speeds and interaction patterns to avoid detection.
**User asks**: "Check my Suzuki GSR 600 workshop manual for brake fluid type, engine oil specs, and rear axle torque."

**Claude automatically**:

- Authenticates with NotebookLM
- Asks comprehensive questions about each specification
- Follows up when prompted "Is that ALL you need to know?"
Expand All @@ -233,6 +267,7 @@ Uses realistic typing speeds and interaction patterns to avoid detection.
**You**: "I need to build an n8n workflow for Gmail spam filtering. Use my n8n notebook."

**Claude's internal process:**

```
→ Loads NotebookLM skill
→ Activates n8n notebook
Expand All @@ -247,13 +282,15 @@ Uses realistic typing speeds and interaction patterns to avoid detection.
## Technical Details

### Core Technology

- **Patchright**: Browser automation library (Playwright-based)
- **Python**: Implementation language for this skill
- **Stealth techniques**: Human-like typing and interaction patterns

Note: The MCP server uses the same Patchright library but via TypeScript/npm ecosystem.

### Dependencies

- **patchright==1.55.2**: Browser automation
- **python-dotenv==1.0.0**: Environment configuration
- Automatically installed in `.venv` on first use
Expand All @@ -270,19 +307,22 @@ All data is stored locally within the skill directory:
```

**Important Security Note:**

- The `data/` directory contains sensitive authentication data and personal notebooks
- It's automatically excluded from git via `.gitignore`
- NEVER manually commit or share the contents of the `data/` directory

### Session Model

Unlike the MCP server, this skill uses a **stateless model**:

- Each question opens a fresh browser
- Asks the question, gets the answer
- Adds a follow-up prompt to encourage Claude to ask more questions
- Closes the browser immediately

This means:

- No persistent chat context
- Each question is independent
- But your notebook library persists
Expand All @@ -295,11 +335,13 @@ For multi-step research, Claude automatically asks follow-up questions when need
## Limitations

### Skill-Specific

- **Local Claude Code only** - Does not work in web UI (sandbox restrictions)
- **No session persistence** - Each question is independent
- **No follow-up context** - Can't reference "the previous answer"

### NotebookLM

- **Rate limits** - Free tier has daily query limits
- **Manual upload** - You must upload docs to NotebookLM first
- **Share requirement** - Notebooks must be shared publicly
Expand Down Expand Up @@ -328,19 +370,23 @@ Chrome runs locally on your machine. Your credentials never leave your computer.
## Troubleshooting

### Skill not found

```bash
# Make sure it's in the right location
ls ~/.claude/skills/notebooklm/
# Should show: SKILL.md, scripts/, etc.
```

### Authentication issues

Say: `"Reset NotebookLM authentication"`

### Browser crashes

Say: `"Clear NotebookLM browser data"`

### Dependencies issues

```bash
# Manual reinstall if needed
cd ~/.claude/skills/notebooklm
Expand All @@ -361,6 +407,7 @@ While I've built in humanization features (realistic typing speeds, natural dela

**About CLI tools and AI agents:**
CLI tools like Claude Code, Codex, and similar AI-powered assistants are incredibly powerful, but they can make mistakes. Please use them with care and awareness:

- Always review changes before committing or deploying
- Test in safe environments first
- Keep backups of important work
Expand All @@ -375,11 +422,13 @@ That said, if you run into problems or have questions, feel free to open an issu
## Credits

This skill is inspired by my [**NotebookLM MCP Server**](https://github.com/PleasePrompto/notebooklm-mcp) and provides an alternative implementation as a Claude Code Skill:

- Both use Patchright for browser automation (TypeScript for MCP, Python for Skill)
- Skill version runs directly in Claude Code without MCP protocol
- Stateless design optimized for skill architecture

If you need:

- **Persistent sessions** → Use the [MCP Server](https://github.com/PleasePrompto/notebooklm-mcp)
- **Multiple tool support** (Codex, Cursor) → Use the [MCP Server](https://github.com/PleasePrompto/notebooklm-mcp)
- **Quick Claude Code integration** → Use this skill
Expand Down