// Generate images via DALL-E and videos via Sora using browser automation. Use when a project needs visual assets like hero images, team photos, feature icons, or product demo videos.
Control Chrome browser via 71 MCP tools - screenshots, clicks, forms, downloads, network capture, TTS, history, cookies, emulation. Use when working with browser automation.
TODO: Add description
Claude Code CLI configuration guide for Codex. Use when users ask about: claude code config, ~/.claude/settings.json, claude plugins, claude agents, claude skills, claude hooks, claude mcp servers, or integrating tools with Claude Code.
| name | tabz-artist |
| description | Generate images via DALL-E and videos via Sora using browser automation. Use when a project needs visual assets like hero images, team photos, feature icons, or product demo videos. |
| agent | conductor:tabz-manager |
| context | fork |
Generate images (DALL-E) and videos (Sora) for projects using TabzChrome MCP tools.
Runs in tabz-manager context - This skill automatically spawns as a tabz-manager subagent with isolated tab group.
/conductor:tabz-artist Generate assets for a [industry] landing page:
- Hero image: [description]
- Feature icons: [description]
- Product video: [description]
tabz-manager automatically creates an isolated tab group before browser work:
SESSION_ID="Artist-$(shuf -i 100-999 -n 1)"
mcp-cli call tabz/tabz_create_group "{\"title\": \"$SESSION_ID\", \"color\": \"purple\"}"
# All subsequent URLs opened into this group with explicit groupId
| Page | URL |
|---|---|
| DALL-E 3 GPT | https://chatgpt.com/g/g-iLoR8U3iA-dall-e3 |
| Images Gallery | https://chatgpt.com/images |
# 1. Open DALL-E (into your tab group)
mcp-cli call tabz/tabz_open_url '{"url": "https://chatgpt.com/g/g-iLoR8U3iA-dall-e3", "groupId": <your_groupId>}'
# 2. Fill prompt (wait 2-3s for page load)
mcp-cli call tabz/tabz_fill '{"selector": "#prompt-textarea", "value": "PROMPT_HERE", "tabId": <your_tabId>}'
# 3. Submit
mcp-cli call tabz/tabz_click '{"selector": "#composer-submit-button", "tabId": <your_tabId>}'
# 4. Wait 15-30s, poll with screenshots until image appears
mcp-cli call tabz/tabz_screenshot '{"tabId": <your_tabId>}'
# 5. Extract image URL
mcp-cli call tabz/tabz_get_element '{"selector": "img[alt=\"Generated image\"]", "tabId": <your_tabId>}'
# Look for: attributes.src
# 6. Download
mcp-cli call tabz/tabz_download_file '{"url": "IMAGE_SRC_URL", "filename": "public/images/hero.png"}'
# Go to gallery
mcp-cli call tabz/tabz_open_url '{"url": "https://chatgpt.com/images"}'
# Click download button (hover bottom-left of each image)
# nth-of-type(1) = first in grid, nth-of-type(2) = second, etc.
mcp-cli call tabz/tabz_click '{"selector": "div.flex.w-full > div.flex:nth-of-type(1) > span > button.flex.items-center"}'
| Element | Selector |
|---|---|
| Prompt input | #prompt-textarea |
| Submit button | #composer-submit-button |
| Generated image | img[alt="Generated image"] |
| Download btn (/images) | div.flex.w-full > div.flex:nth-of-type(n) > span > button.flex.items-center |
| Page | URL |
|---|---|
| Drafts | https://sora.chatgpt.com/drafts |
# 1. Open Sora drafts (into your tab group)
mcp-cli call tabz/tabz_open_url '{"url": "https://sora.chatgpt.com/drafts", "groupId": <your_groupId>}'
# 2. Fill prompt (wait 2-3s for page load)
mcp-cli call tabz/tabz_fill '{"selector": "textarea", "value": "PROMPT_HERE", "tabId": <your_tabId>}'
# 3. Submit
mcp-cli call tabz/tabz_click '{"selector": "div.flex.items-center.justify-between > div:last-child > button:last-child", "tabId": <your_tabId>}'
# 4. Wait 60-120s, poll with screenshots until video thumbnail appears
mcp-cli call tabz/tabz_screenshot '{"tabId": <your_tabId>}'
# 5. Click video to open detail view
mcp-cli call tabz/tabz_click '{"selector": "video", "tabId": <your_tabId>}'
# 6. Extract video URL
mcp-cli call tabz/tabz_get_element '{"selector": "video", "tabId": <your_tabId>}'
# Look for: attributes.src
# 7. Download
mcp-cli call tabz/tabz_download_file '{"url": "VIDEO_SRC_URL", "filename": "public/videos/demo.mp4"}'
| Element | Selector |
|---|---|
| Prompt textarea | textarea |
| Create video button | div.flex.items-center.justify-between > div:last-child > button:last-child |
| Video thumbnail | video |
| Video src | attributes.src via tabz_get_element |
When given a project description, plan assets like:
| Asset Type | DALL-E Prompt Structure |
|---|---|
| Hero image | "[Subject] in [setting], [style], [mood lighting], [composition]" |
| Team photos | "Professional headshot grid, [n] diverse people, modern office, candid warm lighting" |
| Feature icons | "Minimal line icon set, [n] icons for: [list], consistent stroke weight, [color]" |
| Product shot | "[Product] on [surface], [lighting setup], commercial photography style" |
| Asset Type | Sora Prompt Structure |
|---|---|
| Product demo | "[Style]. [Device/screen] showing [UI]. [Camera movement]. [Specific actions with timing]. [Lighting + palette]." |
| Background | "[Aesthetic]. [Scene description]. [Camera movement]. [Duration]. [Palette]." |
Save assets to project directories:
public/
├── images/
│ ├── hero.png
│ ├── team.png
│ └── icons/
│ ├── feature-1.png
│ └── feature-2.png
└── videos/
└── demo.mp4
Return a summary of generated assets:
## Generated Assets
### Images (DALL-E)
- public/images/hero.png - Hero image for landing page
- public/images/team.png - Team photo grid
### Videos (Sora)
- public/videos/demo.mp4 - Product demo video (10s)
All assets downloaded and ready for use.
For detailed prompt guidance, see:
.prompts/images/dalle3.prompty - DALL-E prompt structure and examples.prompts/video/sora.prompty - Sora prompt structure and examplesFor non-AI-generated visuals, consider:
/canvas-design - Programmatic poster/document design (canvas-based PDFs, posters)/mermaidjs-v11 - Diagrams, flowcharts, architecture visualizations