Claude skill that applies The Blue Book of UX Directives: 550 numbered directives in 9 chapters
UX Directives — Claude Skill
以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →
> A Claude skill that applies **The Blue Book of UX Directives** to design work: audits, design reviews, topic lookups and requirements — every finding cited by directive ID.
**Author: Aleh Haiko** · **Read the book: alehhaiko.com/ux** · **Full guide: Skill for Claude**
---
What is this?
*The Blue Book of UX Directives: A Uniform Code for Human-Centered Digital Systems* — 9 chapters, 62 subcategories and 550 numbered, command-form directives (IDs like 32/02), from human cognition to AI-mediated interaction. It is written as a field manual of Human-Centered Systems Engineering: terse, absolute, command-form.
The skill gives Claude the full text of the book. Claude then cites the exact directive, ID and title, instead of paraphrasing UX advice from memory. A finding becomes a rule anyone on the team can look up and check.
**What it can do**
- **Cite exactly.** The book is bundled whole, so the title is quoted, not recalled.
- **Find the directives for a topic** through an index of all 62 subcategories and their “Ask yourself” questions.
- **Audit what it is shown** — screenshots, code, specs, flows — as Violates / Evidence / Fix / Severity.
- **Write requirements** traced to directive IDs.
- **Explain any ID,** including the five repealed ones and what replaced them.
**What it cannot do**
- **See what it is not shown.** A state nobody opened stays unchecked.
- **Measure on its own.** Pixels, contrast and timing are measured only when the agent has a browser and uses it.
- **Know your history.** A deliberate decision looks like a defect unless it is listed as one.
- **Know thresholds the book does not state.** Pair it with WCAG.
- **Replace research.** Severity is a judgment by consequence, not data about your users.
Who it might be for, a worked example and how to make audits sharper: Skill for Claude.
---
Install
Claude.ai
1. Download ux-directives.skill. It is a zip of the ux-directives/ folder.
2. In Claude, open **Settings → Skills** and upload the file.
3. Make sure the skill is turned on.
Claude uses the skill on its own when a task calls for it. You don’t need to name it. Anthropic’s guide: Using Skills in Claude.
Claude Code
~/.claude/skills/ makes the skill available in all your projects. To share it with a team, put it in the repository’s .claude/skills/ and commit it. Claude loads it when relevant, or you type /ux-directives. Docs: Claude Code skills.
---
First prompts
**Audit:**
**Find by topic:**
**Requirements:**
**Explain an ID:**
---
The 9 chapters
| # | Chapter | Governs |
|---|---------|---------|
| 1 | **Human Cognition & Behavior** | Attention, cognitive load, recognition, mental models, metaphors, learnability, simplicity, decision-making |
| 2 | **Information Architecture & Wayfinding** | Information hierarchy, discoverability, navigation, progressive disclosure, state, explorability, search & labeling |
| 3 | **Interaction Mechanics & Agency** | Interface objects, affordances, direct manipulation, feedback, efficiency, Fitts's law, input |