Back to Skills

generating-assets

verified

Generates 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.

View on GitHub

Marketplace

tabz-chrome

GGPrompts/TabzChrome

Plugin

tabz

agents

Repository

GGPrompts/TabzChrome
122stars

plugins/tabz/skills/generating-assets/SKILL.md

Last Verified

January 16, 2026

Install Skill

Select agents to install to:

Scope:
npx add-skill https://github.com/GGPrompts/TabzChrome/blob/main/plugins/tabz/skills/generating-assets/SKILL.md -a claude-code --skill generating-assets

Installation paths:

Claude
.claude/skills/generating-assets/
Powered by add-skill CLI

Instructions

# TabzArtist - AI Asset Generation via Browser Automation

Generate images (DALL-E) and videos (Sora) for projects using TabzChrome MCP tools.

> **Runs in tabz-expert context** - This skill automatically spawns as a tabz-expert subagent with isolated tab group.

## When to Use

- Building landing pages, apps, or websites that need visual assets
- Creating hero images, team photos, feature icons, product screenshots
- Generating product demo videos or background ambient videos

## Quick Start

```
/tabz:generating-assets Generate assets for a [industry] landing page:
- Hero image: [description]
- Feature icons: [description]
- Product video: [description]
```

## Tab Group Isolation

tabz-expert automatically creates an isolated tab group before browser work:

```bash
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
```

## DALL-E Image Generation

### URLs
| Page | URL |
|------|-----|
| DALL-E 3 GPT | `https://chatgpt.com/g/g-iLoR8U3iA-dall-e3` |
| Images Gallery | `https://chatgpt.com/images` |

### Workflow

```bash
# 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"}'
```

Validation Details

Front Matter
Required Fields
Valid Name Format
Valid Description
Has Sections
Allowed Tools
Instruction Length:
5740 chars