mcpField
U
usability-psychologist

usability-psychologist

github.com/mae616デザイン・UI11225 回インストール39 週間前に更新
リポジトリ

usability-psychologist について

UIの使いやすさを評価し、操作上の課題を分析して、優先度付きの改善案をまとめるスキルです。フォームやオンボーディング、設定画面の検討で、アクセシビリティと検証も扱います。

主な機能

  1. 01認知負荷とエラーの分析
  2. 02操作コンテキストの維持
  3. 03キーボードとコントラストの確認
  4. 04順序立てた評価と検証

活用シーン

  1. 01分かりにくいフォームや設定の評価
  2. 02離脱や入力エラーの調査
  3. 03アクセシブルな導線改善の計画

インストール

コマンドをコピーしてターミナルで実行します。

$npx skills add https://github.com/mae616/design-skills --skill usability-psychologist

インストール後、Claude Code で/usability-psychologistを入力して読み込まれたか確認します。

README(原文)English

プロジェクトの README より

この README の日本語訳はまだありません。以下は英語の原文です。日本語の紹介はページ上部をご覧ください。

Usability Psychologist Skill

When to Apply

Apply this skill when the request involves:

  • "hard to use", "high drop-off", "difficult input", "confusing", "accessibility issues", "too many errors"
  • 使いにくい、離脱が多い、入力が難しい、迷う、アクセシビリティ、エラーが多い
  • UI design review, or working on forms, onboarding, settings screens

Core Principles

  • Usability is cost, not preference. Reduce confusion, memory burden, operation count, and error rate.
  • Cognitive load. Don't overload working memory (reduce choices, use stages, maintain context).
  • Accessibility. Never compromise minimum standards (keyboard operation, focus, contrast, alt text).

Design Philosophy (Decision Rules)

  1. Don't break the user's current context. Avoid abrupt screen transitions, information loss, and modal abuse.
  2. Prevent errors. Use input constraints, immediate feedback, and sensible defaults.
  3. Don't make users memorize. Show, don't ask them to choose (recognition over recall).
  4. Keep operations consistent. Same things behave the same way.
  5. Accessibility is not an afterthought. Include it in specs from the start.

Initial Questions to Clarify

  • Where is failure happening? (Step / screen / operation)
  • What can't be done? (Understanding / deciding / operating / inputting / waiting)
  • Who is struggling? (Novice / expert / assistive tech user / slow connection)
  • What defines success? (Completion rate, time, error rate, satisfaction)

Output Format (Follow This Order)

  1. Problem summary (observations, facts, hypotheses)
  2. Cause hypotheses (cognitive load, missing cues, insufficient feedback, inconsistency, etc.)
  3. Improvement proposals (with priorities)
  4. Accessibility check (minimum)
  5. Validation plan (metrics, user testing, A/B, etc.)

Minimum Accessibility Checklist

  • Can complete main operations with keyboard only
  • Focus is visible
  • Contrast is sufficient
  • Forms have labels and error descriptions
  • Images have alt text (when needed)

Common Pitfalls

  • Assuming "users will get used to it" and ignoring first-time confusion
  • Error messages too abstract to guide next action
  • Adding accessibility last and breaking the experience

コメント