eachlabs-product-visuals — Claude Code skill: product visuals
A skill that turns product photos into e-commerce shots, lifestyle scenes and short videos through EachLabs models. Useful when a store or ad needs imagery.
npx skills add eachlabs/skills --skill eachlabs-product-visuals -a claude-codeWhat eachlabs-product-visuals does
The skill maps EachLabs models to product tasks and walks the agent through the prediction API. Its tables list slugs: product-to-photoshoot for a studio-style shot, product-photo-to-modelshoot for a product worn or held by a model, product-backround-remover and rembg-enhance for cutting out the background, eachlabs-product-arc-shot-v1 for an arc shot, pixverse-v5-6-image-to-video for motion from a still. General-purpose options are there too, among them gpt-image-v1-5-edit, flux-2-turbo-edit and qwen-image-edit-2511-multiple-angles.
Each job follows the same four steps. First GET https://api.eachlabs.ai/v1/model?slug=<slug> to confirm the model exists and read its request_schema. Then POST https://api.eachlabs.ai/v1/prediction with the slug, version "0.0.1" and inputs that match the schema. After that, poll GET https://api.eachlabs.ai/v1/prediction/{id} until the status reads "success" or "failed", and pull the output URL from the response.
Requests carry the key in the X-API-Key header, so EACHLABS_API_KEY has to be set in the environment — without it nothing runs. Keys come from eachlabs.ai. For a whole catalog the skill suggests firing off separate POST requests in parallel and polling each prediction on its own.
What it helps with
- shoot a product on a clean white background with studio light
- swap the background for transparent and export PNG
- place a product in a lifestyle interior scene
- get several angles of one item for a listing
- turn a still product photo into a short video
Example prompts for the agent
- Shoot the product in
product.jpgon a white background with soft studio lighting - Put the mug from the photo on a wooden desk in a home office, morning light
- Generate product angles at 45-degree horizontal steps
How to install eachlabs-product-visuals
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-product-visuals -a claude-code2Manually: put the files in place
~/.claude/skills/eachlabs-product-visuals/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/eachlabs-product-visuals/
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-product-visuals -a codex2Manually: put the files in place
.agents/skills/eachlabs-product-visuals/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-product-visuals -a cursor2Manually: put the files in place
.cursor/skills/eachlabs-product-visuals/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install eachlabs/skills eachlabs-product-visuals2Manually: put the files in place
.github/skills/eachlabs-product-visuals/SKILL.md1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-product-visuals -a gemini-cli2Platform CLI
gemini skills install https://github.com/eachlabs/skills --path skills/eachlabs-product-visualsManually: put the files in place
.devin/skills/eachlabs-product-visuals/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-product-visuals -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about eachlabs-product-visuals
How do I install eachlabs-product-visuals in Claude Code?
Run npx skills add eachlabs/skills --skill eachlabs-product-visuals -a claude-code. The skill lands at ~/.claude/skills/eachlabs-product-visuals/SKILL.md.
What does eachlabs-product-visuals do?
It guides the agent through generating product photos, lifestyle scenes, multi-angle views and short videos with EachLabs models. The skill picks the right model for a task and shows how the API call is shaped.
What do I need before using it?
An EachLabs key stored in the EACHLABS_API_KEY environment variable, sent in the X-API-Key header. Predictions will not be created without it.
