Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add majiayu000/spellbook --skill product-ux-expertgit clone --depth 1 https://github.com/majiayu000/spellbookWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/majiayu000/spellbook/product-ux-expert)<a href="https://agentmods.dev/skills/majiayu000/spellbook/product-ux-expert"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/product-ux-expert/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/majiayu000/spellbook/product-ux-expert"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/product-ux-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00043 | $0.03069 |
| Opus 5 | $0.00022 | $0.01535 |
| Sonnet 5 | $0.00009 | $0.00614 |
| Haiku 4.5 | $0.00004 | $0.00307 |
Grade A, and why
product-ux-expert scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 450 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product UX Expert
Core Principles
- Reduce Cognitive Load — Minimize mental effort required for every interaction
- Accessibility First — WCAG 2.2 AA is the baseline, not an afterthought
- Evidence-Based — Decisions backed by user research, not assumptions
- Anticipatory Design — Predict user needs before they ask
- Ethical Design — No dark patterns, transparent data practices
- Mobile First — Design for smallest screens, enhance for larger
Quick Reference
Nielsen's 10 Heuristics
| # | Heuristic | Key Question |
|---|---|---|
| 1 | Visibility of System Status | Does the user always know what's happening? |
| 2 | Match System & Real World | Does it use familiar language and concepts? |
| 3 | User Control & Freedom | Can users easily undo or exit? |
| 4 | Consistency & Standards | Does it follow platform conventions? |
| 5 | Error Prevention | Does it prevent errors before they occur? |
| 6 | Recognition over Recall | Is information visible, not memorized? |
| 7 | Flexibility & Efficiency | Are there shortcuts for experts? |
| 8 | Aesthetic & Minimalist Design | Is every element necessary? |
| 9 | Help Users with Errors | Are error messages helpful and actionable? |
| 10 | Help & Documentation | Is help available when needed? |
Cognitive Psychology
Cognitive Load Types
Intrinsic Load — Complexity inherent to the task itself
Extraneous Load — Unnecessary complexity from poor design (eliminate this!)
Germane Load — Mental effort for learning/understanding (support this)
Key Laws
Hick's Law — More choices = longer decision time
→ Limit options to 5-7, use progressive disclosure
Miller's Law — Working memory holds 7±2 items
→ Chunk information, use visual grouping
Fitts's Law — Larger, closer targets are easier to click
→ Make primary actions big and accessible
Jakob's Law — Users expect your site to work like others
→ Follow established patterns
Von Restorff — Different items are more memorable
→ Highlight CTAs with contrast
Serial Position — First and last items remembered best
→ Put key info at start/end of lists
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 450 lines · 43 tokens per session scan A d3e0b940dd71
product-ux-expert is a skill published in the GitHub repository majiayu000/spellbook (278 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 3,069 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
pneuma-session
Instructions for renaming an active Pneuma session and replacing its default preview with a useful title and summary. A Pneuma session is one work area inside a larger project.
pneuma-preferences
Persistent user preference memory across sessions. Consult this skill BEFORE making any design, style, or aesthetic decisions — choosing colors, themes, layouts, fonts, tone of voice, content density, or visual direction. Also consult when starting a new creative task in any mode, when the user corrects your style…
session-handoff
Use when the user wants to hand off, transfer, pause, or continue the current session in a new session or with another agent — asks for a "session handoff", a "prompt para a próxima sessão", to "continuar de onde paramos", or invokes /session-handoff; also when context is running low and in-flight work must survive a…
Cursor rules for avoiding placeholder or broken image URLs, using stable visual
Cursor rules for avoiding placeholder or broken image URLs, using stable visual assets, and checking alt text, dimensions, licensing, and responsive behavior.
Tailwind CSS Patterns
Use this skill when styling UI with Tailwind and you want consistent design tokens, maintainable class composition, and good accessibility defaults.
Cursor rules for embedding Beefree SDK's no-code content editors (for emails, pa
Cursor rules for embedding Beefree SDK's no-code content editors (for emails, pages, and popups) into a web application.