agentleFS
adymireadymire/CraftLayer/skills/image-art-direction/SKILL.md

image-art-direction

Skill0 starsChanged 3 days agoMITView on GitHub

Select and implement imagery that supports a product story while respecting authenticity, accessibility, performance, and licensing.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use when choosing photography, screenshots, illustrations, textures, or other visual assets for an interface.

    line 10
  2. Distinctive:

    Do not add imagery solely to fill space or imply customers, product capabilities, or outcomes that do not exist.

    line 15
  3. Distinctive:

    Prefer authentic product assets and properly licensed originals.

    line 27
  4. Distinctive:

    Use responsive sizes, efficient formats, and appropriate loading priority.

    line 32
  5. Distinctive:

    Never invent product screenshots, customer logos, or testimonials.

    line 38
  6. Distinctive:

    Do not redistribute an asset when license terms are unclear.

    line 39
  7. Distinctive:

    Avoid text embedded in images when the information must be searchable or accessible.

    line 40
  8. Distinctive:

    Check authenticity, license record, responsive crop, alt-text purpose, format/size, loading behavior, and visual contrast.

    line 57

≈ “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

Image Art Direction

When to use

Use when choosing photography, screenshots, illustrations, textures, or other visual assets for an interface.

When not to use

Do not add imagery solely to fill space or imply customers, product capabilities, or outcomes that do not exist.

Inputs and assumptions

Identify message, audience, brand, placement, crop behavior, source and license, performance budget, and whether the asset is decorative or informational.

Workflow

  1. State what the image contributes that text or layout does not.
  2. Prefer authentic product assets and properly licensed originals.
  3. Match composition, aspect ratio, crop, and focal point to actual responsive placements.
  4. Provide concise useful alternative text for informative images; use an empty alternative for decorative images.
  5. Use responsive sizes, efficient formats, and appropriate loading priority.
  6. Record asset source, creator, license, attribution, and restrictions.
  7. Review crop and contrast against real content and themes.

Decision rules

  • Never invent product screenshots, customer logos, or testimonials.
  • Do not redistribute an asset when license terms are unclear.
  • Avoid text embedded in images when the information must be searchable or accessible.
  • Respect privacy and consent for identifiable people.

Example

A product screenshot may use clearly labeled sample data, but must not be presented as a real customer result or live production metric.

Common failures

  • Generic stock images unrelated to the product.
  • Hero images that crop away the meaningful subject on mobile.
  • Missing attribution, oversized files, or redundant alt text.

Validation

Check authenticity, license record, responsive crop, alt-text purpose, format/size, loading behavior, and visual contrast.

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.