Menu
Use Google Gemini for AI chat, research, image/video creation, and analysis. Use when user wants to use Gemini, ask complex questions, generate images or videos, do deep research, or use Gemini's thinking capabilities.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Create a GitHub pull request with proper issue linking and conventional commits. Use when user says "create pr", "submit pr", "open pull request", "push and create pr", or after pre-pr review passes.
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
Review code changes against spec for drift and principle violations before PR submission. Use when user says "pre-pr review", "check against spec", "review my changes", "spec drift", "am I following the spec", or before creating a pull request.
Design robust specs through principle-driven interviews, then create GitHub issues with sub-issue hierarchies. Use when starting a new feature, designing a solution, or when user says "let's spec this out", "design this feature", "create a spec".
Analyze coding agent session transcripts to improve existing skills or create new ones. Use when asked to improve a skill based on a session, or extract a new skill from session history.
Create new Claude Code skills. Use when user wants to create, update, or improve a skill that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
| name | gemini |
| description | Use Google Gemini for AI chat, research, image/video creation, and analysis. Use when user wants to use Gemini, ask complex questions, generate images or videos, do deep research, or use Gemini's thinking capabilities. |
| allowed-tools | mcp__claude-in-chrome__* |
Browser automation for Google Gemini AI assistant at gemini.google.com.
Access via model dropdown (bottom-right of input area):
| Model | Description | Best For |
|---|---|---|
| Fast | Quick responses | Simple questions, fast interactions |
| Thinking | Extended reasoning | Complex problem solving |
| Pro | Advanced capabilities | Math, code, detailed analysis |
Access via sliders icon (left of model selector):
| Tool | Description |
|---|---|
| Deep Research | In-depth research with sources |
| Deep Think | Extended reasoning (shows thinking process) |
| Create videos | Video generation with Veo 3.1 |
| Create images | AI image generation |
| Canvas | Collaborative document editing |
| Guided Learning | Educational/tutorial mode |
Access via "+" button (left of input area):
| Option | Description |
|---|---|
| Upload files | Attach local files |
| Add from Drive | Import Google Drive files |
| Photos | Access photo library |
| Import code | Add code snippets |
| NotebookLM | Direct NotebookLM integration |
Access via "Gems" in sidebar:
| Feature | Location | Description |
|---|---|---|
| Copy | Bottom of response | Copy full response text |
| Export to Sheets | In tables | Export data to Google Sheets |
| Sources | Below response | View cited sources |
| Like/Dislike | Bottom of response | Feedback buttons |
| Share | Response menu | Share conversation |
Sidebar:
Retrieving Previous Chats:
Best Practice: Use native "Copy response" button (two overlapping rectangles icon at bottom of response).
Avoid JavaScript clipboard API - can be overwritten by other processes. Paste immediately after copying.
1. Navigate to gemini.google.com
2. Click sliders icon → enable "Deep Think"
3. Select "Pro" model for best results
4. Enter research query
5. Wait for completion (may take minutes)
6. Click "Copy response" button
1. Navigate to gemini.google.com
2. Click sliders icon → enable "Create images"
3. Describe desired image in detail
4. Review generated options
5. Click to download or regenerate
1. Complete research in Gemini
2. Copy response using native button
3. Open NotebookLM (see notebooklm skill)
4. Create notebook → Copied text → Paste