Token导航 LogoToken导航

Agent Skill · 研究检索

ux-ethics-%26-content-strategy(用户体验道德 %26 内容策略)

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。它适合让 Agent 提炼结构、补齐章节、统一术语、检查链接或把零散材料整理成可读文档。使用时应保留项目已有事实、命令和路径,不要把未确认的信息写成确定结论;涉及对外文案时,还需要控制语气,避免过度营销或夸大能力。

ux-ethics-%26-content-strategy 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,暂无第三方扫描结果,按安装量在研究检索类的 73,675 个 Skill 里排第 11,725。

总安装 10,983周安装 463GitHub Stars 3下载 3,193核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:ux-ethics-%26-content-strategy(用户体验道德 %26 内容策略)
来源仓库:https://github.com/phazurlabs/ux-ui-mastery
仓库路径:skills/ux-ethics-%26-content-strategy
安装命令:
npx skills add https://github.com/phazurlabs/ux-ui-mastery --skill 'UX Ethics & Content Strategy'
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/phazurlabs/ux-ui-mastery --skill 'UX Ethics & Content Strategy'

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。它适合让 Agent 提炼结构、补齐章节、统一术语、检查链接或把零散材料整理成可读文档。使用时应保留项目已有事实、命令和路径,不要把未确认的信息写成确定结论;涉及对外文案时,还需要控制语气,避免过度营销或夸大能力。

适用于 UX 伦理与内容策略相关的文档撰写。需审慎处理敏感话题与合规声明。ux-ethics-%26-content-strategy 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/ux-ethics-%26-content-strategy

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/phazurlabs/ux-ui-mastery --skill 'UX Ethics &…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

ux-ethics-%26-content-strategy 怎么安装?

在终端执行 npx skills add https://github.com/phazurlabs/ux-ui-mastery --skill 'UX Ethics & Content St…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

ux-ethics-%26-content-strategy 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

ux-ethics-%26-content-strategy 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

ux-ethics-%26-content-strategy 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

ux-ethics-%26-content-strategy 用的人多吗?

公开数据是累计安装 10,983 次,近一周安装 463 次,下载 3,193 次,GitHub 3 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

ux-ethics-%26-content-strategy 安全吗?

没有查到第三方扫描结果,安全性无法从公开资料判断,安装前请自行审查源码、依赖和命令行为。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 没有第三方扫描结果,安全性只能靠自己读源码判断。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 要求有安全扫描结论才肯安装的团队。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
ux-ethics-%26-content-strategy

用户体验道德 %26 内容策略 · 本页

10,9833需要联网未明确未收录

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

UX Ethics & Content Strategy — Designing with Integrity

Ethics in Design Philosophy

"Design is a political act. Every thing we design goes on to design us back." — Anne-Marie Willis

Design decisions shape human behavior at massive scale. A dark pattern deployed to millions of users does millions of units of harm. Ethical design is not a constraint on creativity — it is the foundation that makes design trustworthy and sustainable. Users who feel respected become loyal; users who feel manipulated become adversaries.

Core Ethical Principles

  1. Respect autonomy — users must make informed, uncoerced decisions
  2. Transparent by default — never hide information that affects user decisions
  3. Benefit over extraction — design for user value, not just engagement metrics
  4. Inclusive representation — content, imagery, and language must reflect human diversity
  5. Privacy as a right — treat user data as if it were your own; collect minimum, protect maximum

Dark Pattern Identification and Avoidance

What Are Dark Patterns?

Dark patterns (deceptive patterns) are user interface designs that trick users into doing things they did not intend. Coined by Harry Brignull, they exploit cognitive biases and attention limitations for business gain at user expense.

The Dark Pattern Taxonomy

Trick Questions

  • Confusing wording that leads users to unintended selections
  • Double negatives in opt-out checkboxes: "Uncheck to not receive no emails"
  • Ethical alternative: Use clear, affirmative language. "Send me marketing emails: Yes/No"

Sneak into Basket

  • Adding items to cart without explicit user action
  • Pre-selected add-ons, insurance, or donations during checkout
  • Ethical alternative: Start with an empty basket. Suggest add-ons clearly but never pre-select

Roach Motel

  • Easy to get into a situation (subscribe, create account) but hard to get out (cancel, delete)
  • Requiring phone calls to cancel what was started online
  • Ethical alternative: Make cancellation as easy as signup. Offer a self-service cancellation flow

Privacy Zuckering

  • Confusing privacy settings that result in sharing more data than intended
  • Default-public profiles, buried privacy controls, complex permission language
  • Ethical alternative: Default to maximum privacy. Use plain language. Show exactly what will be shared

Misdirection

  • Drawing attention to one thing to distract from another
  • Large "Accept All" button with tiny "Manage Preferences" link on cookie banners
  • Ethical alternative: Equal visual weight for all options. "Accept All" and "Reject All" same size

Hidden Costs

  • Revealing additional charges (fees, shipping, tax) only at the final checkout step
  • Ethical alternative: Show total cost including all fees as early as possible in the flow

Bait and Switch

  • User sets out to do one thing but a different, undesirable thing happens
  • "Close" button that actually triggers an action or navigates away
  • Ethical alternative: Controls must do exactly what they visually communicate

Confirmshaming

  • Using guilt-inducing language to decline an offer: "No thanks, I don't want to save money"
  • Ethical alternative: Neutral decline language. "No thanks" or "Maybe later" is sufficient

Forced Continuity

  • Free trial silently converting to paid subscription without clear warning
  • Ethical alternative: Send clear notification before trial ends. Require explicit opt-in to paid tier

Disguised Ads

  • Ads styled to look like content or navigation elements
  • Fake download buttons, sponsored results without clear labeling
  • Ethical alternative: Clearly label all advertising and sponsored content

Dark Pattern Detection Checklist

When reviewing any interface, verify:

  • Can the user complete their goal without unintended side effects?
  • Are all costs, commitments, and consequences visible before action?
  • Is the "undo" or "opt-out" path as easy as the "do" or "opt-in" path?
  • Are default selections in the user's interest, not the business's?
  • Is the visual hierarchy honest (primary action = user's most likely intent)?
  • Would the design be embarrassing if explained transparently to users?

Privacy-Respecting UX Design

Privacy by Design Principles (Ann Cavoukian)

  1. Proactive, not reactive — prevent privacy issues, do not wait for breaches
  2. Privacy as default — maximum privacy without user action required
  3. Embedded in design — privacy is not a bolt-on feature
  4. Full functionality — privacy and functionality are not zero-sum
  5. End-to-end security — protect data throughout its lifecycle
  6. Transparency — be open about data practices
  7. User-centric — respect user autonomy and preferences

Privacy UX Patterns

Data Collection:

  • Ask for data only when needed, in context of the feature that requires it
  • Explain why each piece of data is needed (inline justification)
  • Differentiate required vs. optional fields clearly
  • Offer anonymous/pseudonymous options where possible

Consent:

  • Granular consent: let users choose which data uses to allow
  • Equal-weight accept/decline buttons
  • No pre-checked consent boxes
  • Easy consent withdrawal at any time
  • Record and respect consent preferences

Data Transparency:

  • Privacy dashboard showing what data is stored and how it is used
  • Data export capability (GDPR right to portability)
  • Account deletion that actually deletes data (not just deactivates)
  • Clear data retention policies in plain language

Content Strategy

Content Strategy Framework

Content Purpose: Every piece of content must answer: What is the user trying to do, and how does this content help?

Content Hierarchy:

  1. Essential: Information needed to complete the current task — always visible
  2. Supporting: Context that aids decision-making — visible on demand
  3. Reference: Detailed information for edge cases — accessible but not prominent

Information Architecture Principles

  • Organize content by user mental models, not organizational structure
  • Use card sorting and tree testing to validate IA (see ux-research-methods)
  • Apply the "three-click rule" loosely — it is less about clicks and more about confidence at each step
  • Consistent navigation labels across the entire application

UX Writing and Microcopy

UX Writing Principles

  1. Clear over clever — functional text must be immediately understood
  2. Concise — use the minimum words needed; every word must earn its place
  3. Conversational — write like a knowledgeable friend, not a legal document
  4. Consistent — same terms for same concepts across the entire product
  5. Actionable — tell users what to do, not just what happened

Microcopy Patterns

Button Labels:

  • Use specific verbs: "Save draft", "Send message", "Create account" — not "Submit" or "OK"
  • Destructive actions: "Delete project" not "Delete" — specificity prevents mistakes
  • Loading state: "Saving..." / "Sending..." — reflect the action in progress

Error Messages:

  • Structure: What happened + Why + How to fix
  • Bad: "Error 403: Forbidden"
  • Good: "You don't have permission to edit this file. Ask the project owner for editor access."

Empty States:

  • Explain what the empty area will contain
  • Provide a clear action to populate it: "No projects yet. Create your first project."
  • Use illustration sparingly — it should clarify, not decorate

Confirmation Dialogs:

  • Title: State the action about to happen
  • Body: Explain the consequences
  • Buttons: Specific action labels, not "Yes/No"
  • Example: Title: "Delete this project?" Body: "This will permanently delete 'My Project' and all 23 files. This cannot be undone." Buttons: "Delete project" / "Keep project"

Placeholder Text:

  • Show format or example, not instructions: "jane@example.com" not "Enter your email"
  • Never use placeholder as the only label — it disappears on input

Success Messages:

  • Confirm what happened: "Message sent to 3 recipients"
  • Offer logical next action: "View sent messages"

Readability Optimization

Reading Level:

  • Target 8th grade reading level for consumer products (Flesch-Kincaid)
  • Technical products can target higher but still avoid unnecessary jargon
  • Use Hemingway Editor or similar tools to test readability

Formatting for Scannability:

  • Front-load key information — put the conclusion first, then supporting detail
  • Use bullet points and numbered lists for 3+ related items
  • Bold key terms within paragraphs for scanning
  • Break content into short paragraphs (2-4 sentences max)
  • Use descriptive headings as signposts

Number and Data Formatting:

  • Use locale-appropriate formatting (commas, decimals, date format)
  • Humanize large numbers: "1.2 million" not "1,200,000"
  • Relative time for recent events: "2 hours ago" not "2025-01-15T14:30:00Z"
  • Show units explicitly: "256 MB" not "256"

Inclusive Language

Inclusive Language Guidelines

  • Use gender-neutral language: "they/them" for unknown gender, "chairperson" not "chairman"
  • Avoid ableist metaphors: "check" not "sanity check"; "placeholder" not "dummy"
  • Culturally neutral: avoid idioms that do not translate across cultures
  • Age-neutral: avoid "elderly" (use "older adults"); avoid "digital native" assumptions
  • Use people-first language for disability: "person with a disability" not "disabled person" (though identity-first is preferred by some communities — respect stated preferences)

Content Accessibility

  • Provide alt text for all meaningful images
  • Use descriptive link text (not "click here")
  • Ensure content is understandable without visual formatting
  • Provide text alternatives for video and audio content
  • Support translation and localization in content architecture

Cross-Referencing

  • For visual design of content, reference ui-visual-design-system
  • For accessibility requirements, reference accessibility-inclusive-design
  • For heuristic evaluation of content, reference nng-ux-heuristics
  • For AI content generation ethics, reference ai-spatial-voice-ux

v3.0 Cross-References

The v3.0 upgrade adds dedicated references for microcopy patterns, cross-cultural ethical design, and cognitive bias exploitation awareness.

Microcopy Pattern Library See references/microcopy-pattern-library.md for the component-level microcopy pattern library containing 30+ action verbs organized by context (creation, modification, deletion, navigation, communication), 20+ error message templates following the What-Why-Fix structure, and ready-to-use copy patterns for empty states, loading states, confirmation dialogs, success messages, permission requests, and onboarding flows. This reference transforms the UX Writing and Microcopy section above into a practical, copy-paste-ready resource for product teams.

Cross-Cultural and Localization Ethics See the cross-cultural-i18n-ux skill for ethical considerations specific to cross-cultural design and localization — including cultural sensitivity in content strategy (avoiding Western-centric defaults), right-to-left and bidirectional text implications for UX writing, culturally variable privacy expectations (differing norms around data collection across regions), honorific and formality systems that affect microcopy tone, and legal compliance variations (GDPR, LGPD, PIPL) that shape ethical consent patterns. This skill complements the Inclusive Language section above with global, culturally-aware perspectives.

Cognitive Biases that Dark Patterns Exploit See cognitive-psychology-ux/references/cognitive-biases-design-patterns.md for the comprehensive catalog of cognitive biases most relevant to dark pattern identification and avoidance — including anchoring bias (manipulated reference prices), default effect (pre-selected options exploiting status quo bias), scarcity bias (fake urgency timers), social proof manipulation (fabricated reviews or inflated user counts), and sunk cost fallacy exploitation (making cancellation feel like wasting prior investment). Understanding these biases strengthens the Dark Pattern Detection Checklist above by revealing the psychological mechanisms being exploited.

Key Sources

  • Brignull, H. "Deceptive Patterns" (deceptivedesign.net)
  • Cavoukian, A. "Privacy by Design" framework
  • Krug, S. (2014). "Don't Make Me Think"
  • Podmajersky, T. (2019). "Strategic Writing for UX"
  • NNG Group content strategy and UX writing articles

平台分布

Codex

34.72%
按下载量换算1,109

Claude

29.79%
按下载量换算951

Cursor

17.79%
按下载量换算568

Gemini CLI

10.52%
按下载量换算336

安全审计

暂无安全审计结果可展示。

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills