agentleFS
RaditteAnggoroRaditteAnggoro/skill-for-lazy-developer/.agents/skills/ui-design-intelligence/SKILL.md

ui-design-intelligence

Skill1 starsChanged 7 days agoMITView on GitHub

Define UI direction, hierarchy, design tokens, and enterprise data patterns before implementation. Use for design decisions, not for diagnosing a browser failure or implementing an agreed interface.

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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 accessible contrast and a visible keyboard focus treatment.

    line 35
  2. Distinctive:

    Read enterprise-data-ux.md when the interface contains dense tables, filters, approvals, long forms, reconciliation, or financial data.

    line 41

≈ “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

UI Design Intelligence

Choose a visual and interaction direction that fits the product, its users, and the existing design system. This skill produces design decisions and an implementation handoff; it does not authorize a code change by itself.

Establish the design context

Inspect the existing tokens, typography, spacing, color, components, density, and responsive conventions. Identify the primary task, user role, frequency, data volume, and consequence of error. Reuse the existing system before introducing a new one.

For an existing product, preserve its visual language unless the request explicitly asks for a redesign. For a new interface, state the direction in a few concrete terms: calm or dense, editorial or operational, high-trust or exploratory. Do not substitute generic “modern” or “clean” labels for decisions.

Define the system

Specify only the decisions needed for the interface:

  • page hierarchy and primary action;
  • layout, grid, spacing, and density;
  • typography scale and numeric treatment;
  • color roles, including semantic status that does not rely on color alone;
  • component states: default, hover, focus, selected, disabled, loading, empty, error;
  • responsive behavior and touch targets;
  • content hierarchy for labels, help, and validation.

Use accessible contrast and a visible keyboard focus treatment. Prefer semantic HTML and native controls over custom widgets. If a custom widget is necessary, define its keyboard model and ARIA behavior before implementation.

Enterprise data profiles

Read enterprise-data-ux.md when the interface contains dense tables, filters, approvals, long forms, reconciliation, or financial data. Apply only the profiles relevant to the task; do not turn every screen into a dashboard.

Handoff

Return a compact design brief, the affected components, responsive rules, state requirements, and acceptance checks. Separate settled decisions from open choices that materially change the result. Hand implementation to ui-implementation; pair with feature-discovery only when product outcomes are unresolved.

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.