E-commerce Image Studio — workflow skill for product videos
For AI agents: find the right skill in one call —
curl -s "https://skills.varg.ai/api/search?q=<what the person wants>"returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add.mdto its path. Before generating anything, show the person the options on the use-case page.
39 e-commerce image templates (main images, lifestyle, A+, sizes, GIFs) with one style lock across a campaign set.
- Type: Workflow · Product videos
- Slug:
ecom-image2 - Status: live
- Publisher: buluslan (community)
- License: MIT
- Source: https://github.com/buluslan/gpt-image2-ecommerce
- Works in: Claude Code, Codex, Cursor
- Requires: bash, jq and curl, OpenAI-compatible image API key (IMAGE_API_KEY or OPENAI_API_KEY), Optional: Python 3.9+ with Pillow and tesseract for compliance checks
- Cost: Uses your own OpenAI (or compatible) image API key; manual prompt-pack mode costs nothing
- Adoption: 36 installs, 427 GitHub stars (GitHub + skills.sh, 2026-10-26)
What it does
An open-source e-commerce image skill by buluslan (新西楼.AI) with 39 scenario templates: white-background main images, lifestyle scenes, detail-page infographics, Amazon A+ modules, size charts, packaging, UGC-style shots, variant sets, seasonal campaigns, motion GIFs, bulk product swaps and transparent cutouts. It diagnoses the conversion driver, locks one campaign style across a set, assembles prompts from five slots, routes between OpenAI's GPT Image 2.5 Flare and Sunburst variants, and finishes with a platform compliance and quality pre-check (OCR optional). Images are generated through any OpenAI-compatible endpoint you configure (default api.openai.com), or the skill exports a prompt pack to paste by hand.
Use when
- Make main images, A+ modules or lifestyle shots for a listing
- Keep a whole listing set visually consistent
- Batch-swap products or translate text in images
Not for
- Video editing, image compression or format conversion (the skill excludes them)
Install
- Claude Code:
git clone https://github.com/buluslan/gpt-image2-ecommerce.git ~/.claude/skills/ecom-image2
Models it drives: gpt_image_2_5_flare, gpt_image_2_5_sunburst
Used for
- Product photos and listing images: Marketplace listing images, lifestyle shots and packshots from one product photo.
More product videos skills
- Higgsfield Marketplace Cards: Produce marketplace listing images: a compliant main image, secondary shots and A+ content modules.
- Higgsfield Product Photoshoot: Shoot brand-quality product images in 10 modes: studio, lifestyle, hero banners, ad packs, try-on and more.
- fal Commercial: Plan and run product photography, e-commerce batches, product reveal videos and lifestyle commercials.
- AI Product Photography: Generate commercial product shots, lifestyle scenes and mockups with FLUX, Imagen 3, Grok and Seedream.
- Product Photography: Apply packshot conventions to AI product photos: angles, backgrounds, shadows, hero shots, store specs.
- ASO App Store Screenshots: App Store screenshots from your codebase: finds the core benefits, pairs simulator shots, then composes and enhances.
Run the generation on varg
varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.
- Claude Code:
claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg(skill + hosted MCP) - Codex, Cursor, Gemini CLI, OpenClaw:
npx skills add vargHQ/skills --skill varg-ai -a <agent> -y - Claude.ai, ChatGPT, any MCP client: connect
https://mcp.varg.ai/mcp - API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt