agentleFS
astriaaiastriaai/skills/product-photoshoot/SKILL.md

product-photoshoot

Skill2 starsChanged 28 days agoMITView on GitHub

Create product photographs or coordinated fashion lookbooks from supplied product images, SKUs, or saved references. Use for "shoot this product", ecommerce packshots, lifestyle product shots, "re-shoot our catalog", or the same product across several scenes. For garments worn by a person use virtual-try-on; a whole-store template pipeline uses store-photoshoot. Respect a named provider and requests for advice only.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use astria-api for live schemas, reference tokens, HTTPS media transport, idempotency, workspace scope, and checking completion.

    line 12
  2. Very specific:

    Use the supplied images or reference IDs.

    line 17
  3. Distinctive:

    Ask for the product image only when no usable reference is available.

    line 22
  4. Distinctive:

    Use the requested number of shots and scenes.

    line 24
  5. Distinctive:

    Do not author or modify a template merely to run a photoshoot.

    line 32
  6. Very specific:

    Use the returned subject class after its token, for example <faceid:123:1> bag.

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Product photoshoots

Produce the requested product photographs with Astria, retaining the supplied product's visible design, color, material, logos, and proportions. Do not claim that generated images guarantee exact SKU fidelity.

Use astria-api for live schemas, reference tokens, HTTPS media transport, idempotency, workspace scope, and checking completion.

Resolve inputs and scope

Use the supplied images or reference IDs. For a named product or SKU, search list_references by title, then inspect the match with get_reference. Resolve ambiguity rather than selecting an unrelated SKU. If the only input is a local path or attachment, obtain an accessible HTTPS URL through a host upload capability or the optional authenticated CLI; never invent a URL. Ask for the product image only when no usable reference is available.

Use the requested number of shots and scenes; for an unspecified single-product shoot start with one image and sensible studio lighting. An explicit generation request authorizes that scope. Planning a shoot does not authorize submission.

Make the photographs

For an existing template, use list_templates / get_template before run_template. Preserve reference-slot order from the returned template. Do not author or modify a template merely to run a photoshoot.

For a one-off targeted edit of an existing product shot, use generate_images with input_image and the edit instruction. For a product reused across several scenes, reuse an existing reference or create one with create_reference from the supplied views; reuse its ID on every shot. Use the returned subject class after its token, for example <faceid:123:1> bag. Discover models with list_models; use the user's selection or catalog default rather than a hardcoded model ID.

A multi-scene request needs distinct scene prompts, not repeated copies of one prompt with a larger image count. Keep product details and reference IDs stable while varying only the requested setting, angle, lighting, or styling.

Deliver and review

Retain each returned prompt ID and check get_prompt for completion. Show all requested finished assets through the host's result presentation; identify pending or failed shots accurately. Check visible product details against the source when images can be inspected. Report material mismatches; do not submit extra paid corrections beyond the requested scope.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.