Install
$ agentstack add skill-mae616-design-skills-usability-psychologist ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
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)
- Don't break the user's current context. Avoid abrupt screen transitions, information loss, and modal abuse.
- Prevent errors. Use input constraints, immediate feedback, and sensible defaults.
- Don't make users memorize. Show, don't ask them to choose (recognition over recall).
- Keep operations consistent. Same things behave the same way.
- 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)
- Problem summary (observations, facts, hypotheses)
- Cause hypotheses (cognitive load, missing cues, insufficient feedback, inconsistency, etc.)
- Improvement proposals (with priorities)
- Accessibility check (minimum)
- 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
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: mae616
- Source: mae616/design-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.