agentleFS
nassaj2011nassaj2011/claude-skills-for-chatgpt/skills/frontend-design-direction/SKILL.md

frontend-design-direction

Skill0 starsChanged 25 days agoMITView on GitHub

Create deliberate, distinctive, accessible frontend visual direction and interface composition grounded in the product's users and brand.

6 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

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

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 2

    Distinctive

    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 screenshots and browser testing when a UI execution environment exists.

    line 14
  2. Distinctive:

    Do not substitute a static mockup for functioning behavior when the user requested an application.

    line 17

“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “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

Frontend design direction

  1. Establish audience, primary task, brand, information hierarchy, target devices and emotional tone. Explore references only when authorized/available.
  2. Choose a clear visual concept justified by product context, rather than adding gradients or illustrations by default.
  3. Plan hierarchy: navigation, primary action, content density, typography, spacing, rhythm, imagery and meaningful empty states.
  4. Sketch interactions and account for loading, error, partial data, zero results, disabled actions, destructive confirmation and permission denial.
  5. Design mobile-first; consider touch targets, keyboard navigation, readable contrast, screen readers, RTL and localization.
  6. Implement against the project's current design system/components; avoid unrelated framework changes or broad refactors.
  7. Use screenshots and browser testing when a UI execution environment exists; correct broken layouts before calling it done.

Output: visual rationale, key screen/state inventory, responsive rules, implementation details, visual verification and limitations. Do not substitute a static mockup for functioning behavior when the user requested an application.

Local RTL example

Review examples/frontend-rtl/index.html and tokens.css for a Persian RTL accessible-form prototype. The node --test examples/frontend-rtl/ui.test.mjs check covers state logic only. Perform real browser layout, keyboard and screen-reader checks before asserting visual/accessibility quality.

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.