‹ 首页

consent-and-agency

@owl-listener · 收录于 5 天前 · 上游提交 1 个月前

Designing for informed user consent, opt-out, and human override.

场景用户授权隐私合规产品设计

适合你，如果你在设计需要用户明确授权的交互流程

/ 下载安装
https://github.com/owl-listener/ai-design-skills/tree/main/claude-plugin/ai-alignment-reasoning/skills/consent-and-agency ↗
/ 通过 npx 安装 校验哈希
npx oh-my-skill add owl-listener/ai-design-skills/consent-and-agency
/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- owl-listener/ai-design-skills/consent-and-agency
/ 已经装过?验证本机副本,不用重装
npx oh-my-skill verify owl-listener/ai-design-skills/consent-and-agency
安装目标可用 --agent / --scope 或 --to 明确指定;省略时只会在唯一已存在的 agent 目录上自动选择,零命中或多命中会停止并提示。content_hash 缺失或不一致均拒装。
144GitHub stars
~508上下文体积 · 单文件
索引托管

怎么用

商店整理自技能原文 · 版本 f41b650 · 表述以原文为准
它做什么

安装后，Claude 会提供关于用户知情同意、退出和人工覆盖的设计原则与模式，帮助你在 AI 产品中确保用户控制权。

什么时候触发

当你询问如何设计 AI 产品的用户控制、同意流程或伦理问题时触发。

装好后可以这样说
Claude 会解释并给出分步同意的设计方法。
Claude 会提供可撤销同意的设计模式。
Claude 会介绍语境化同意的时机。
技能原文 SKILL.md作者撰写 · MIT · f41b650

Consent and Agency

AI products make decisions, take actions, and process information on behalf of users. Consent and agency design ensures users remain in control — understanding what the AI does, agreeing to it, and being able to override it.

Informed Consent for AI

Users should understand and agree to:

  • What data the AI uses: Conversation history, personal data, uploaded documents, browsing behaviour
  • What the AI does with it: Training, personalisation, sharing with third parties, storage
  • What actions the AI takes: Sending messages, making changes, accessing systems
  • What the AI can't do: Limitations that might affect the user's expectations

Consent is not a checkbox at sign-up. It's an ongoing design challenge throughout the experience.

Designing for Agency

Agency means the user feels — and is — in control:

  • Opt-in over opt-out: AI features should be activated by the user, not imposed
  • Reversibility: AI actions should be undoable wherever possible
  • Override mechanisms: The user can always stop, redirect, or override the AI
  • Exit paths: The user can disengage from AI assistance at any point without penalty
  • Preference controls: The user can adjust AI behaviour, scope, and autonomy levels
Consent Patterns
  • Progressive consent: Ask for permission incrementally as new capabilities are needed, not all at once
  • Contextual consent: Ask at the moment the action is about to happen, not in advance
  • Granular consent: Let users consent to specific actions or data uses, not blanket permissions
  • Revocable consent: Users can withdraw consent and have that withdrawal take effect
Agency Anti-Patterns
  • Dark patterns: Making it hard to opt out or override the AI
  • Consent fatigue: Asking for permission so often that users click through without reading
  • Learned helplessness: AI does so much that users forget how to do things themselves
  • Invisible actions: The AI takes actions the user doesn't know about
  • Irreversible defaults: AI actions that can't be undone without user awareness
Design Artefacts
  • Consent flow diagrams per feature
  • Agency checkpoint specifications
  • Override mechanism inventory
  • Data use transparency matrix
  • Opt-out path designs
按 MIT 许可原样转载,未经改动 · 在 GitHub 查看 →

评论

登录即可评论;带「已验证安装」的,是发布者名下有本店的安装或持有记录。
…