agentleFS
Sign inStart free
boazsegevboazsegev/omoya/skills/web-ux/SKILL.md

web-ux

Skill1 starsChanged 6 days agoMITView on GitHub

This skill should be used when designing or auditing web user experience.

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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:

    Start from the primary user tasks.

    line 9
  2. Distinctive:

    Remove steps before polishing visuals.

    line 10
  3. Distinctive:

    Follow platform and web conventions unless a measured gain justifies deviation.

    line 14
  4. Distinctive:

    Prefer undo to confirmation.

    line 17
  5. Distinctive:

    Ask only what the task needs.

    line 22
  6. Distinctive:

    Use one idea per section and one primary action per page.

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

UX Practices

Method

  • Start from the primary user tasks; measure completion, time, errors and abandonment.
  • Remove steps before polishing visuals.
  • Validate with real users or analytics; label untested conclusions as heuristic.

Flows

  • Follow platform and web conventions unless a measured gain justifies deviation.
  • Minimize steps, choices and recall; disclose complexity progressively.
  • Prefill, remember and default safely.
  • Prefer undo to confirmation.
  • Design every state: empty, loading, error, success and offline.
  • Give feedback within 100 ms, and progress for longer waits.

Forms

  • Ask only what the task needs.
  • Validate inline, explain errors beside the field, and never discard input.
  • Name buttons by outcome.

Pages

  • Order content by attention: value and primary action first, proof near the decision, reference last.
  • Use one idea per section and one primary action per page.

Audits

  • Report location, problem, affected task, severity, evidence and specific fix, ordered by impact.

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.

Check your setup, free