agentsclimarketplace

Product photography

Skill yigityildiz0/universal-ai-skill-library/skills/common/product-photography

Plan, generate, edit, or review AI product photography for e-commerce, packaging, ads, catalogs, and product launches. Use for product photos, packshots, hero images, lifestyle scenes, product image sets, studio lighting, or marketplace-ready visuals while preserving product identity and required details.From its SKILL.md

Install
npx -y skills add yigityildiz0/universal-ai-skill-library --skill product-photography

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

  • 26 days oldThe repository was created 26 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.6 KB, 443 tokens by cl100k_base, as published. Nobody here has run it

Product Photography

Create a coherent product image set using the active host’s image capability. Do not choose a provider or model automatically.

Intake

Establish the product, non-negotiable identity details, audience, channel, brand constraints, target ratio, and whether a reference image is authoritative. When the product must remain exact, treat every visible label, logo, geometry, color, material, and included accessory as a preservation requirement.

Plan the image set

Choose only shots that serve the channel:

NeedReliable shot
Listing leadclean packshot or hero
Product understandingalternate angle and detail
Sizescale or in-hand view
Use caselifestyle scene
Rangecollection or variants
Conversion supportfeature/included-items frame

For a full e-commerce set, use 5–9 complementary images rather than repeating the same angle.

Direction

  1. Match lighting to the material: diffuse for catalog clarity, rim/controlled reflection for premium tech or glass, natural light for believable lifestyle scenes.
  2. Use a centered, uncluttered composition for packshots; reserve negative space and contextual props for campaign/lifestyle images.
  3. Specify camera angle, background, shadow, surface, material behavior, and exclusions in the prompt or edit brief.
  4. Keep one visual system across the set: consistent white balance, perspective, texture treatment, background family, and crop logic.
  5. Generate or edit one representative frame first; inspect identity before scaling the set.

Verify

  • Compare every output with the authoritative product/reference.
  • Check text, logo, quantity, ports, seams, labels, geometry, and unwanted invented accessories.
  • Check crop, resolution, color space, and marketplace requirements against the channel’s current official rules when relevant.
  • Do not state a marketplace requirement from memory when the asset will be published.

Guardrails

  • Do not fabricate certification marks, claims, packaging text, reviews, or people using the product without authorization.
  • Do not silently alter the product to make it more attractive.
  • Keep source assets and generated variants clearly named; do not overwrite the original.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,512. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.