Is there a Claude Code skill for Amazon listing images?
Yes, a Wireflow skill for Claude Code plans Amazon listing images from your product photo and renders each one as a 2048x2048 square, about 10 credits each.
Yes, Wireflow's amazon-product-images skill turns one real photo of your product into a listing image set inside Claude Code: a main image draft on white, a feature infographic, lifestyle, size and scale, detail, what's in the box, how to use and a comparison. It writes each image's brief with your callout text in quotes, shows the cost and waits for your yes, then renders each image as a 2048x2048 square with Seedream 5 Lite.
Claude reads back every word in the finished images before handing them over, and saves the set to ./wireflow-outputs/. Without a Wireflow connection, you still get the slot plan and the copy for each image, ready for a designer. Skill files and examples are in the skill's folder on GitHub.
How do I install the listing images skill in Claude Code?
Install the Wireflow plugin, which adds every Wireflow skill and the Wireflow connector:
/plugin marketplace add wireflowINC/skills
/plugin install wireflow-skills@wireflow
Claude Code shows the plugin's details first, so you can review it and choose its scope. Then run /mcp, choose wireflow and sign in with your Wireflow account. The skill shows up as /wireflow-skills:amazon-product-images, and Claude also picks it up from plain requests.
To add only this skill, use the skills CLI, or copy the skills/amazon-product-images folder into ~/.claude/skills/. Then connect Wireflow once and run /mcp to sign in, with no API key to copy.
npx skills add wireflowINC/skills --skill amazon-product-images
claude mcp add --transport http wireflow https://www.wireflow.ai/api/mcp
What do I give Claude to make listing images?
Give it your product photo at an https:// URL and your real product facts:
Make Amazon listing images for my serum. Photo: https://example.com/serum.jpg
Facts: frosted glass bottle, 30 ml / 1 fl oz, precise dropper. I need the
main image, an infographic and a lifestyle shot in a bathroom.
It asks for the product name, three to five real features or specs for callouts, real dimensions or weight if you want a size image, and who buys it and where it is used. Those facts go into the images word for word, so they have to come from you. The same skill answers requests for A+ style images and for Etsy, Walmart or Shopify gallery images.
Which images are in a listing set?
The skill proposes up to eight images, and you drop any you do not need.
| # | Image | What it shows |
|---|---|---|
| 1 | Main image (draft) | The product alone on white, about 85% of the frame, no text or props |
| 2 | Feature infographic | Three to four callouts with lines or icons pointing at the product |
| 3 | Lifestyle | The product in use in the buyer's real setting |
| 4 | Size and scale | Dimension lines with real measurements, or the product next to a familiar object |
| 5 | Detail close-up | Material, texture, mechanism or finish |
| 6 | What's in the box | A labelled flat lay of everything included |
| 7 | How to use | Three numbered steps |
| 8 | Comparison | Your own versions or sizes side by side, never a competitor's brand |
Can I use the generated main image on Amazon?
Check first: the main image is a generated draft, and the skill does not check Amazon's rules for you. Read Amazon's current product image requirements in Seller Central before a generated image goes in the main image slot, because the rules differ by category and they change.
In the skill's recorded test, the main image came out near-white with faint shading rather than flat white, and the bottle filled less than 85% of the frame. Treat it as a draft: whiten the background in an editor, or re-run with a stronger brief.
Will the callout text be spelled correctly?
You give every word in quotes and approve it before anything renders, and Claude then reads each word in the finished image against that text. In the recorded test, all three callouts on the feature infographic were spelled exactly right. One wrong letter means a re-render, and the skill asks first.
Keep each callout to three to five words.
What will the skill never put in an image?
It never adds invented claims, awards, star ratings, review quotes, "best seller" badges or a competitor's brand. Callouts, dimensions and contents come from you, word for word, and comparisons only cover your own sizes or versions.
How many credits does a listing set cost?
About 10 credits per image, as listed in the skills repo on 8 October 2026; the two test images measured 10 and 13.
| Step | Credits |
|---|---|
| Slot plan, briefs, callout copy, quote | 0 |
| Each rendered image (2048x2048) | About 10 |
| A six-image gallery | About 60 to 78 |
| Fixing one image | About 10, only after you approve |
Rendering needs credits on your Wireflow account. The Free plan includes 0 credits each month, and paid plans start at $36 a month for 2,660 credits (pricing).
Does the listing images skill work in Cursor, Codex or Claude Desktop?
It is built for Claude Code, and the skills CLI also installs it in Cursor, Codex and other agents that read SKILL.md. Rendering then needs that agent connected to the Wireflow MCP server, and the skill's README says Wireflow has not tested those agents itself. In Claude.ai and Claude Desktop, add https://www.wireflow.ai/api/mcp as a custom connector; saving files needs a shell, so there you get the image links instead.
Connection steps for each agent are in Use Wireflow from your agent. Every Wireflow skill is listed on the agent skills page.
To turn the main image into a short product clip, use the product video skill. To build listing images on the Wireflow canvas instead, see the Amazon listing image generator.