dall-e

---
name: dall-e
description: Generate an image using DALL-E via ChatGPT in Chrome browser automation. Use when the user says "generate an image with DALL-E", "use DALL-E", "ChatGPT image", "make an image in ChatGPT", "create with DALL-E", "dall-e", or wants to use ChatGPT's image generation. Takes an image prompt as the argument.
user-invocable: true
allowed-tools:
  - mcp__claude-in-chrome__tabs_context_mcp
  - mcp__claude-in-chrome__tabs_create_mcp
  - mcp__claude-in-chrome__navigate
  - mcp__claude-in-chrome__read_page
  - mcp__claude-in-chrome__find
  - mcp__claude-in-chrome__form_input
  - mcp__claude-in-chrome__computer
  - mcp__claude-in-chrome__get_page_text
  - mcp__claude-in-chrome__javascript_tool
  - Bash
  - Read
---

# DALL-E — Generate Images via ChatGPT in Chrome

Arguments passed: `$ARGUMENTS`

## Argument Handling

- `$ARGUMENTS` is the image prompt (e.g., "a watercolor painting of a sunset over mountains")
- If no arguments provided, ASK the user what image they want to generate

## Workflow

### Step 1: Get Browser Context

Call `mcp__claude-in-chrome__tabs_context_mcp` to see current tabs.

- If ChatGPT is already open in a tab, reuse it
- Otherwise, create a new tab

### Step 2: Navigate to ChatGPT

Navigate to `https://chatgpt.com/`

- Wait for the page to load
- If the user is not signed in, tell them: "You need to be signed into your OpenAI account in Chrome. Please sign in and try again."

### Step 3: Enter the Prompt

1. Read the page to find the message input textarea
2. Type the prompt. Prefix with "Generate an image of: " to ensure ChatGPT uses DALL-E for image generation
3. Submit the prompt (press Enter or click the send button)

### Step 4: Wait for the Image

1. Wait for ChatGPT/DALL-E to process — this can take 15-45 seconds
2. Read the page periodically to check if the image has been generated
3. Look for the generated image in the response area

### Step 5: Download the Image

1. Look for a download button on the generated image and click it
2. If no download button is visible, try hovering over the image to reveal download options, or right-click and save
3. Check the default downloads directory (`~/Downloads/`) for the newly downloaded file
4. Report the downloaded file path to the user:
   ```
   Image downloaded: ~/Downloads/<filename>
   ```

## Rules

- **Don't trigger alerts or dialogs** in the browser
- **If the page structure is unexpected**, describe what you see and ask the user for guidance rather than clicking blindly
- **If ChatGPT shows an error** (content policy, rate limit, etc.), report it clearly to the user
- **Keep it simple** — navigate, type, submit, download. Don't over-automate.