← Visual SandboxCONTENT HISTORY

Update to Visual Sandbox

Snapshot Nov 5, 2026 · 01:19 UTC · version 1.0.8

Collection source: downloaded plugin package.

WHAT CHANGED

First saved snapshot

No earlier snapshot is available to establish a change.

Save Visual Sandbox and check future changes in Following.

Up to 10 plugins free · no card required.

Compare saved observations

Download comparison JSON
Full technical diff · 0 changed fields
Full snapshot data
{
  "description": "Make a set of product photos from one photo of the product with the Visual Sandbox MCP tools: hero shots, lifestyle scenes, flat lays and ad images that keep the product the same in every picture. Trigger when the person asks for \"product photos\", \"a product shoot\", \"photos for my store\", \"Amazon or Shopify images\", \"lifestyle shots of my product\", \"a hero image\", or sends a product photo and asks to make it look professional. Uses the MCP tools only.\n",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 280
    }
  ],
  "name": "vsb-product-photoshoot",
  "skill_md_contents": "---\nname: vsb-product-photoshoot\ndescription: >\n  Make a set of product photos from one photo of the product with the Visual\n  Sandbox MCP tools: hero shots, lifestyle scenes, flat lays and ad images\n  that keep the product the same in every picture. Trigger when the person\n  asks for \"product photos\", \"a product shoot\", \"photos for my store\",\n  \"Amazon or Shopify images\", \"lifestyle shots of my product\", \"a hero\n  image\", or sends a product photo and asks to make it look professional.\n  Uses the MCP tools only.\nlicense: Proprietary. See LICENSE for the terms.\n---\n\n# A product photo shoot\n\nOne photo of the product goes in. A set of pictures comes out, and the\nproduct looks the same in all of them: the same shape, the same colour and\nthe same label.\n\nUse the MCP tools only.\n\n## 1. Get the product\n\n- Ask for one clear photo of the product, if the person sent none. A phone\n  photo on a plain table is enough.\n- Pass a public `https` URL straight to `generate`. For a photo attached in\n  the chat, call `upload_media` with it as `file`. For a local file, call\n  `upload_media` with a base64 `data_uri`. Use the URL it returns.\n- Ask where the pictures go: a store page, an ad, or social media. That sets\n  the shape: 1:1 for a store, 4:5 or 9:16 for social media, 16:9 for a\n  banner.\n\n## 2. Plan the set\n\nPropose four shots and let the person change the list before you run:\n\n| Shot | What it shows |\n|------|---------------|\n| Hero | The product alone on a clean background, with soft studio light |\n| Lifestyle | The product in use, in the place a buyer uses it |\n| Detail | A close view of the texture, the material or the label |\n| Flat lay | The product from above, with two or three props that fit it |\n\n## 3. Run the first shot\n\n1. Read [`vsb-image-prompting`](../vsb-image-prompting/SKILL.md) with\n   `get_skill`. Its reference section says what to keep from the photo and\n   what to drop, such as the old background and the old light.\n2. Call `list_models` with `modality: \"image\"`. Pick an edit model that takes\n   a reference image. Read [`vsb-nano-banana`](../vsb-nano-banana/SKILL.md)\n   when you pick a Nano Banana model.\n3. Call `get_model`, then `generate` with the photo as the reference. Name\n   the work with `sandbox_name`, such as \"Candle product shoot\".\n4. Call `get_job` after `eta_seconds`. Compare the product with the photo:\n   the shape, the colour and every word on the label.\n\nRun the hero shot first and show it. Run the other shots only after the\nperson approves the look.\n\n## 4. Run the rest of the set\n\n- Use the same model and the same reference on every shot.\n- Start every prompt with the same sentence that describes the product, so\n  the product stays the same.\n- Send the same `sandbox_name` on every call, so the set lands on one canvas.\n\n## 5. Hand it over\n\nGive one `share_url` for each picture and the `sandbox_url` for the set.\nOffer one next step: ad variations of the hero shot with\n[`vsb-ad-variations`](../vsb-ad-variations/SKILL.md), or a short video of it\nwith [`vsb-video`](../vsb-video/SKILL.md).\n\n## Rules\n\n- Never change the product. A changed label or shape is a failed shot, even\n  when the picture looks good. Say so and run the shot again.\n- Never add a logo, a price or a claim that the person did not give you.\n- When a run is refused for want of credit, say the balance is too low, and\n  follow what the server instructions say about credit.\n"
}

SHA-256 of public snapshot: b0160b8d8782458ad9fd390314332c55f91711d14d588b9242623c467c3d5003