intent

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Intent

Overview

概述

Intent is a UX and design strategy system. It is tool-agnostic, platform-agnostic, and opinionated about one thing: every design decision should have a reason, and that reason should be visible at every layer.

Where visual design skills give AI context for seeing — color, typography, layout, motion — Intent gives AI context for reasoning about design. For asking why before how. For framing problems before solving them. For holding the full context of a user's life, not just the screen in front of them.

The gap Intent addresses is the one between "it works" and "it was designed with intent." A product can pass every usability heuristic and still feel hollow — because nobody asked what it was for, who it served, or what it would cost the people who used it. Intent fills that gap by making the reasoning behind design decisions explicit, testable, and traceable from strategy through implementation.

What Intent is:

A thinking system for UX decisions, grounded in research and ethics
A routing layer that connects specialized design skills into coherent practice
An anti-pattern defense that makes manipulative design visible and refusable
A context-gathering protocol that establishes shared understanding before work begins

What Intent is not:

A visual design system
A UI component library
A substitute for primary user research
A set of rules to follow blindly — it's a set of questions to ask rigorously

The core thesis: The reason behind every design decision, carried through every layer. Every skill in this system is about making intent visible —

/strategize

makes problem intent visible,

/philosopher

reveals hidden assumptions, the anti-pattern catalog makes manipulative intent visible so it can be refused.

Intent是一套UX与设计策略系统。它不依赖特定工具或平台，仅坚持一个核心观点：每一个设计决策都应有其依据，且该依据需在设计的每一层级都清晰可见。

视觉设计技能为AI提供“感知”层面的背景——色彩、排版、布局、动效；而Intent则为AI提供设计“推理”层面的背景。它引导人们先问“为什么”，再想“怎么做”；先框定问题，再寻求解决方案；始终兼顾用户的完整生活场景，而非仅仅关注眼前的屏幕。

Intent填补的是“功能可用”与“有意图的设计”之间的差距。一款产品可能通过所有可用性启发式测试，却仍显得空洞——因为没人问过它的用途、服务对象，或使用它会给用户带来什么代价。Intent通过让设计决策背后的推理过程变得明确、可测试，并能从策略阶段追踪到落地实现，从而填补这一空白。

Intent具备的特性：

一套基于研究与伦理的UX决策思维体系
一个将专业设计技能整合为连贯实践的路由层
一套反模式防御机制，可识别并拒绝操纵性设计
一套上下文收集协议，在工作开始前建立共识

Intent不具备的特性：

视觉设计系统
UI组件库
替代原生用户研究的工具
一套需盲目遵循的规则——它是一套需严谨提出的问题

核心论点： 每一个设计决策的依据，需贯穿设计的每一层级。本系统中的每一项技能都旨在让意图可见——

/strategize

让问题意图可见，

/philosopher

揭示隐藏假设，反模式目录让操纵性意图可见以便被拒绝。

When NOT to use Intent

何时不应使用Intent

Intent adds rigor. Rigor is valuable when it's the scarce resource and costly when it's not. Skip Intent when:

The task is a localized tweak within an established system. Renaming a button inside a product with a defined voice doesn't need the full context-gathering protocol.
The task is purely technical with no user-facing change. Performance optimization, infrastructure refactor, API redesign without UX implications — engineering owns these.
A different framework is the right tool. Brand identity belongs to creative direction. Visual component systems belong to design-system tooling. Intent is not a hammer for every nail.
Time pressure makes rigor a net negative. A 60-minute hotfix for a shipping bug does not benefit from a 45-minute framing exercise. Ship the fix, note the debt, return to it.
The user has explicit expertise and a specific ask. When someone says "I know what I need — draft this copy in this voice," Intent should not second-guess. Offer to flag risks if anything looks concerning, then produce.

If in doubt, ask once. Intent is a system that serves practice, not a gate that blocks it.

Intent会增加设计的严谨性。当严谨性是稀缺资源时，它极具价值；当严谨性并非必需时，它则会带来额外成本。在以下情况中可跳过Intent：

任务是既定系统内的局部调整：在已有明确品牌调性的产品中重命名按钮，无需完整的上下文收集协议。
任务纯技术且无用户层面变更：性能优化、基础设施重构、无UX影响的API重新设计——这些属于工程范畴。
已有更合适的框架：品牌识别属于创意方向范畴，视觉组件系统属于设计系统工具范畴。Intent并非万能工具。
时间压力使严谨性得不偿失：针对上线Bug的60分钟紧急修复，无需进行45分钟的问题框定工作。先发布修复方案，记录技术债务，后续再处理。
用户具备明确专业能力且需求具体：当用户表示“我知道自己需要什么——按这个风格撰写文案”时，Intent不应质疑。若发现潜在风险可主动告知，然后完成需求即可。

若存疑问，可询问一次。Intent是服务于实践的系统，而非阻碍工作的门槛。

Modes

运行模式

Intent operates in three modes. Each establishes a different relationship to the work.

Intent有三种运行模式，每种模式对应与工作的不同关系。

context

— Set project context

context

— 设定项目背景

Use this mode at the start of any design engagement. Before any skill can do meaningful work, it needs to understand:

Who are the users? Not demographics — behaviors, contexts, motivations, constraints. A "25-34 year old professional" tells you nothing. "Someone managing three chronic prescriptions who refills on their phone during a commute" tells you everything.
What is the product and business context? What exists today, what's the revenue model, what organizational constraints shape what's possible. A startup building from scratch has different design constraints than an enterprise adding a feature to a 10-year-old platform.
What are the hard constraints? Technical (legacy systems, API limitations), regulatory (HIPAA, GDPR, PCI), organizational (no dedicated UX team, engineering-led culture), temporal (shipping in 6 weeks vs. 6 months).
What is the ethical stance? Every product makes ethical choices — explicitly or by default. Context mode makes them explicit. Are we opt-in or opt-out? Do we use engagement metrics or wellbeing metrics? Do we design for vulnerable populations or exclude them? Do we use persuasive patterns or informative ones?
What does success look like? Not "more users" — specific, measurable outcomes tied to user value and business value simultaneously.

Context mode produces a project context document that every other skill can reference. It's the shared understanding that prevents

/strategize

from framing a problem

/journey

can't solve, or

/articulate

from writing copy that contradicts the ethical stance.

在任何设计项目启动时使用此模式。在任何技能模块开展有效工作前，需先明确以下内容：

用户是谁？ 不是人口统计数据——而是行为、场景、动机与约束。“25-34岁职场人士”毫无意义，“一位在通勤路上用手机管理三种慢性病处方的用户”才是完整的用户画像。
产品与业务背景是什么？ 当前已有哪些功能、盈利模式是什么、哪些组织约束会影响可行性。从零开始的初创公司与为已有10年历史的企业平台新增功能，面临的设计约束截然不同。
硬性约束有哪些？ 技术层面（遗留系统、API限制）、合规层面（HIPAA、GDPR、PCI）、组织层面（无专门UX团队、工程主导文化）、时间层面（6周内上线 vs 6个月内上线）。
伦理立场是什么？ 每款产品都会做出伦理选择——无论是明确的还是默认的。上下文模式会将这些选择明确化。我们采用“选择加入”还是“选择退出”？使用参与度指标还是福祉指标？是为弱势群体设计还是将他们排除在外？采用说服性模式还是告知性模式？
成功的标准是什么？ 不是“更多用户”——而是同时关联用户价值与业务价值的具体、可衡量的结果。

上下文模式会生成一份项目背景文档，供所有其他技能模块参考。这份文档是共识基础，可避免

/strategize

框定的问题无法被

/journey

解决，或

/articulate

撰写的文案与伦理立场相悖。

practice

— Build and improve UX

practice

— 构建并优化UX

This is the active design mode. Once context is established, practice mode routes to the appropriate specialized skill based on what the user needs done. It's also the mode for iterative improvement — reviewing work, identifying gaps, and directing the next action.

Practice mode follows this cycle:

Assess — What's the current state? Use
```
/evaluate
```
to understand quality.
Identify — Where are the gaps? What needs attention first?
Route — Which specialized skill addresses the highest-priority gap?
Execute — Do the work within the specialized skill.
Verify — Did the work address the gap? Are there new gaps?

The routing logic (detailed below) determines which skill to engage. Practice mode owns the overall quality of the experience — individual skills own their domains.

这是主动设计模式。确定背景后，实践模式会根据用户需求路由至相应的专业技能模块。它也适用于迭代改进——审查工作、识别差距、指导下一步行动。

实践模式遵循以下周期：

评估 — 当前状态如何？使用
```
/evaluate
```
了解质量。
识别 — 差距在哪里？哪些问题需要优先处理？
路由 — 哪个专业技能模块能解决优先级最高的差距？
执行 — 在专业技能模块内开展工作。
验证 — 工作是否解决了差距？是否出现新的差距？

路由逻辑（详见下文）会确定调用哪个技能模块。实践模式负责整体体验质量——各技能模块负责其专属领域。

extract

— Extract UX patterns from an existing product

extract

— 从现有产品中提取UX模式

Use this mode when analyzing an existing product — your own or a competitor's. Extract mode systematically identifies:

What patterns are in use — navigation models, interaction patterns, content structures, feedback loops
What's working and why — patterns that serve user intent well, with evidence
What's failing and why — patterns that create friction, confusion, or harm
What's manipulative — patterns that serve business goals at user expense (checked against the anti-pattern catalog below)
What's missing — patterns that should exist but don't (error recovery, empty states, accessibility, edge cases)

Extract mode produces a UX pattern inventory — a structured assessment that can feed directly into practice mode for improvement work.

在分析现有产品（自有或竞品）时使用此模式。提取模式会系统性地识别：

正在使用的模式 — 导航模型、交互模式、内容结构、反馈循环
有效的模式及原因 — 能很好满足用户意图的模式及相关证据
失效的模式及原因 — 造成摩擦、困惑或伤害的模式
操纵性模式 — 以牺牲用户利益为代价服务业务目标的模式（对照下文的反模式目录）
缺失的模式 — 应存在但未实现的模式（错误恢复、空状态、无障碍设计、边缘情况）

提取模式会生成一份UX模式清单——结构化评估报告，可直接用于实践模式的改进工作。

Core UX Principles

核心UX原则

These are not visual principles. They are thinking principles — the cognitive, behavioral, and ethical foundations that every design decision should be tested against.

这些并非视觉原则，而是思维原则——每一个设计决策都应遵循的认知、行为与伦理基础。

1. Respect user autonomy

1. 尊重用户自主性

The user is not a conversion target. They are a person making choices. Design should expand their ability to choose well, not constrain it.

In practice:

No manipulation. No trick questions, hidden options, or shame-based copy. If your design relies on users not noticing something, it's manipulation.
Clear choices. Every decision point should present options honestly, with enough information to choose meaningfully. "Are you sure?" is not informed consent.
Easy reversal. Any action a user takes should be reversible wherever possible. Undo is not a feature — it's a right. Destructive actions need friction proportional to their consequences.
Transparent consequences. Before a user acts, they should understand what will happen. After they act, they should see that it happened. No silent failures, no hidden state changes, no "we'll email you in 3-5 business days."

用户不是转化目标，而是做出选择的个体。设计应提升用户做出明智选择的能力，而非限制其选择。

实践要点：

杜绝操纵。无误导性问题、隐藏选项或基于羞耻感的文案。若设计依赖用户未注意到某些内容，那就是操纵。
清晰的选择。每个决策点都应诚实呈现选项，并提供足够信息供用户做出有意义的选择。“你确定吗？”并非知情同意。
易于撤销。只要可能，用户采取的任何行动都应可撤销。撤销不是功能，而是权利。破坏性操作的摩擦程度应与其后果成正比。
透明的结果。用户行动前应了解会发生什么，行动后应能看到结果。无静默失败、无隐藏状态变更、无“我们会在3-5个工作日内发送邮件”这类模糊表述。

2. Design for real conditions

2. 为真实场景设计

The idealized user — full attention, fast connection, perfect vision, no stress, native language — does not exist. Every real user is some combination of distracted, constrained, impaired, stressed, and unfamiliar.

In practice:

Slow networks. Design for 3G before 5G. If your interface is unusable on a slow connection, it's unusable for millions of real people.
Distraction. Users are interrupted. They switch tabs. They come back 20 minutes later. Your flow should survive that.
Disability. Not an edge case — a spectrum everyone moves along. Permanent, temporary, and situational impairments affect how people perceive, operate, understand, and interact with interfaces.
Stress. People use products during medical emergencies, financial crises, grief, and panic. Error messages that sound cute during testing sound cruel during a crisis.
Unfamiliar language. Not everyone reads your interface in their first language. Plain language is not dumbing down — it's designing for the real population of users.
Old devices. Not everyone has the latest phone. Design for the device your least privileged user actually owns.

理想化的用户——全神贯注、网络流畅、视力完美、无压力、母语使用——并不存在。真实用户总会存在分心、受约束、有障碍、有压力或对产品不熟悉等情况。

实践要点：

低速网络。先为3G网络设计，再考虑5G。若界面在低速网络下无法使用，那对数百万真实用户来说就是不可用的。
分心场景。用户会被打断、切换标签页、20分钟后再返回。你的流程应能适应这种情况。
无障碍需求。这不是边缘情况——而是每个人都会经历的状态。永久、临时与情境性障碍会影响人们感知、操作、理解与交互界面的方式。
压力场景。人们会在医疗紧急情况、财务危机、悲痛或恐慌时使用产品。测试中看似可爱的错误提示，在危机场景下会显得冷酷无情。
非母语使用。并非所有人都以母语阅读界面。Plain Language（简明语言）不是简化内容，而是为真实用户群体设计。
老旧设备。并非所有人都拥有最新款手机。为你最弱势的用户实际使用的设备设计。

3. Make intent visible

3. 让意图可见

Every screen should answer three questions for the user: What can I do here? Why should I? What happens next?

In practice:

Wayfinding. Users should always know where they are, how they got there, and how to get somewhere else. Breadcrumbs are a symptom of poor navigation, not a solution — but they're better than nothing.
Purpose clarity. Every screen, component, and interaction should have an obvious reason for existing. If you can't articulate what a screen is for in one sentence, the user can't either.
Progressive disclosure. Show what's needed now, reveal what's needed next. Don't hide things — sequence them. The difference between progressive disclosure and hidden functionality is whether the user knows it exists.
Feedback loops. Every user action should produce visible feedback. Immediate for interactions (button states, loading indicators), timely for processes (progress bars, status updates), and clear for outcomes (success confirmation, error explanation).

每个界面都应向用户回答三个问题：我在这里能做什么？为什么要这么做？接下来会发生什么？

实践要点：

寻路设计。用户应始终知道自己所在位置、到达方式及前往其他位置的路径。面包屑是导航不佳的表现，而非解决方案——但聊胜于无。
目的明确。每个界面、组件与交互都应有明确的存在理由。若你无法用一句话说明某个界面的用途，用户也做不到。
渐进式披露。展示当前所需内容，逐步揭示后续内容。不要隐藏内容——而是按顺序呈现。渐进式披露与隐藏功能的区别在于用户是否知晓其存在。
反馈循环。用户的每一次操作都应产生可见反馈。交互操作需即时反馈（按钮状态、加载指示器），流程需及时反馈（进度条、状态更新），结果需清晰反馈（成功确认、错误说明）。

4. Evidence over intuition

4. 证据优先于直觉

Research, test, measure. Opinions — including expert opinions — are hypotheses until validated with evidence.

In practice:

Research before design. Understand the problem space before proposing solutions. Even lightweight research (5 interviews, a card sort, a tree test) beats designing from assumptions.
Test with real users. Usability testing is not optional. Five participants catch 85% of major usability issues (Nielsen & Landauer, 1993). There is no excuse for shipping untested flows.
Measure what matters. Metrics should track user success, not just business extraction. Task completion rate tells you more about UX quality than time-on-page.
Acknowledge uncertainty. Say "we believe" instead of "we know." Flag sample sizes. Note when evidence is directional vs. conclusive. Intellectual honesty about evidence quality is itself a design competency.

研究、测试、衡量。观点——包括专家观点——在未被证据验证前都只是假设。

实践要点：

先研究再设计。在提出解决方案前先理解问题领域。即使是轻量化研究（5次访谈、卡片分类、树测试）也比基于假设设计更有效。
与真实用户测试。可用性测试并非可选环节。5名参与者可发现85%的主要可用性问题（Nielsen & Landauer, 1993）。没有理由发布未经过测试的流程。
衡量重要指标。指标应追踪用户成功，而非仅追踪业务收益。任务完成率比页面停留时间更能反映UX质量。
承认不确定性。用“我们认为”代替“我们知道”。标注样本量。说明证据是方向性的还是结论性的。对证据质量的学术诚实本身就是一种设计能力。

5. Systems over screens

5. 系统优先于界面

A screen is not a design. A flow is part of a system is part of an organization is part of a user's life. Design at the right altitude.

In practice:

End-to-end thinking. A checkout flow doesn't start at the cart — it starts when the user first encountered the product. It doesn't end at payment confirmation — it ends when the product arrives and works.
Cross-channel awareness. Users move between devices, channels, and contexts. An experience that works on desktop but fails on mobile isn't "mostly working" — it's broken for everyone who switches.
Organizational awareness. Many UX problems are org chart problems in disguise. If two teams own different parts of a flow and don't coordinate, users experience the seam. Design can smooth seams, but acknowledging they exist is step one.
Temporal awareness. Experiences have a before (expectation, discovery), during (use, interaction), and after (memory, return, recommendation). Most design focuses on "during" and ignores the other two.

界面不是设计。流程是系统的一部分，系统是组织的一部分，组织是用户生活的一部分。在合适的层面进行设计。

实践要点：

端到端思维。结账流程并非从购物车开始——而是从用户首次接触产品时开始。也并非在付款确认后结束——而是在产品送达并正常使用后结束。
跨渠道意识。用户会在设备、渠道与场景间切换。在桌面端可用但在移动端失效的体验，不是“大部分可用”——而是对所有切换设备的用户来说都是失效的。
组织意识。许多UX问题本质上是组织架构问题。若两个团队负责流程的不同部分且未协同，用户会感受到衔接不畅。设计可缓解衔接问题，但首先要承认其存在。
时间维度意识。体验分为事前（预期、发现）、事中（使用、交互）与事后（记忆、回访、推荐）三个阶段。大多数设计只关注“事中”阶段，忽略了另外两个阶段。

6. Ethical defaults

6. 伦理默认值

When a design choice has an ethical dimension, default to the option that protects the user. Always.

In practice:

Opt-in over opt-out. Don't pre-check boxes. Don't default to maximum data collection. Don't assume consent. Ask, and make "no" as easy as "yes."
Privacy by default. Collect the minimum data needed. Store it securely. Delete it when it's no longer needed. Don't make privacy a premium feature.
Honest over persuasive. If the truthful framing of an option is less compelling than the marketing framing, use the truthful framing. Urgency that doesn't exist ("Only 2 left!") is a lie. Scarcity that's manufactured is manipulation.
Protect vulnerable populations. Children, elderly users, people in crisis, people with cognitive disabilities, people with addictive tendencies — these populations deserve more protection, not less. Design for their safety first.

当设计选择涉及伦理层面时，默认选择保护用户的选项。始终如此。

实践要点：

选择加入优先于选择退出。不要预先勾选复选框。不要默认开启最大数据收集。不要假设用户同意。主动询问，并让“拒绝”与“同意”一样简单。
默认隐私保护。仅收集所需的最少数据。安全存储数据。不再需要时删除数据。不要将隐私设为付费功能。
诚实优先于说服。若选项的真实表述不如营销表述吸引人，使用真实表述。不存在的紧迫感（“仅剩2件！”）是谎言，人为制造的稀缺性是操纵。
保护弱势群体。儿童、老年用户、处于危机中的用户、认知障碍用户、有成瘾倾向的用户——这些群体应得到更多保护，而非更少。首先为他们的安全设计。

The UX Anti-Pattern Catalog

UX反模式目录

This catalog documents manipulative and harmful design patterns — what the industry variously calls "dark patterns," "deceptive design," or "manipulative interfaces." Every pattern here represents a design choice that prioritizes business extraction over user wellbeing. The Intent system treats these as defects, not features.

Severity levels:

Critical — Causes direct, measurable harm. Likely violates regulations. Must be remediated immediately.
High — Causes significant user harm or violates user trust. Regulatory risk. Requires prompt remediation.
Medium — Degrades user experience or erodes trust over time. Should be remediated in normal course.
Low — Minor friction or annoyance. Technically not harmful but signals disregard for user experience.

本目录记录了操纵性与有害设计模式——行业内称之为“Dark Patterns（暗黑模式）”“欺骗性设计”或“操纵性界面”。此处的每一种模式都代表了优先考虑业务收益而非用户福祉的设计选择。Intent系统将这些视为缺陷，而非功能。

严重程度：

Critical（严重） — 造成直接、可衡量的伤害。可能违反法规。必须立即整改。
High（高） — 造成重大用户伤害或违反用户信任。存在合规风险。需及时整改。
Medium（中） — 长期降低用户体验或侵蚀信任。应在常规流程中整改。
Low（低） — 轻微摩擦或 annoyance。技术上无害，但表明对用户体验的漠视。

Category 1: Deceptive Patterns

类别1：欺骗性模式

Designs that trick users into actions they didn't intend.

Pattern	What it does	Severity
Bait and Switch	Offers one thing, delivers another. User clicks expecting X, gets Y.	Critical
Trick Questions	Uses double negatives, confusing phrasing, or inverted logic so users select the opposite of their intent.	Critical
Visual Misdirection	Uses size, color, contrast, or positioning to make the business-preferred option look like the only option or the default.	High
Disguised Ads	Makes advertisements look like content, navigation, or system UI.	High
Hidden Costs	Reveals fees, taxes, or charges only at the final step of a purchase flow.	Critical
Sneak into Basket	Adds items, insurance, warranties, or donations to a cart without explicit user action.	Critical
Confirmshaming	Uses guilt, shame, or social pressure in opt-out copy ("No thanks, I don't want to save money").	High

诱导用户做出非本意行动的设计。

模式	行为	严重程度
Bait and Switch（ bait-and-switch）	承诺一种结果，实际提供另一种。用户点击期望得到X，实际得到Y。	Critical
Trick Questions（误导性问题）	使用双重否定、模糊表述或反向逻辑，让用户选择与本意相反的选项。	Critical
Visual Misdirection（视觉误导）	使用尺寸、颜色、对比度或位置，让业务偏好的选项看起来像是唯一选项或默认选项。	High
Disguised Ads（伪装广告）	让广告看起来像内容、导航或系统UI。	High
Hidden Costs（隐藏费用）	仅在购买流程的最后一步才显示费用、税费或收费。	Critical
Sneak into Basket（偷偷加入购物车）	在未获得用户明确操作的情况下，将商品、保险、保修或捐赠项目加入购物车。	Critical
Confirmshaming（确认羞辱）	在退出选项的文案中使用内疚、羞耻或社交压力（如“不用了，我不想省钱”）。	High

Category 2: Prechecked & Default Manipulation

类别2：预勾选与默认值操纵

Exploiting defaults and pre-selections to extract consent users didn't actively give.

Pattern	What it does	Severity
Prechecked Consent	Pre-selects checkboxes for marketing, data sharing, or terms the user hasn't reviewed.	Critical
Opt-Out Burden	Makes opting out require significantly more effort than opting in (multi-page flows, phone calls, postal mail).	Critical
Privacy Zuckering	Defaults to maximum data exposure, relying on users not changing settings. Named after Facebook's repeated defaults.	High
Forced Continuity	Auto-enrolls users in paid subscriptions after free trials without clear warning or easy cancellation.	Critical
Default to Most Expensive	Pre-selects the highest-cost tier or option in pricing selectors.	Medium

利用默认值与预选项获取用户未主动给出的同意。

模式	行为	严重程度
Prechecked Consent（预勾选同意）	预先勾选用户未查看的营销、数据共享或条款复选框。	Critical
Opt-Out Burden（退出负担）	让退出比加入需要付出更多努力（多页面流程、电话联系、邮寄）。	Critical
Privacy Zuckering（隐私扎克化）	默认开启最大数据暴露，依赖用户不更改设置。名称源于Facebook反复使用此类默认设置。	High
Forced Continuity（强制续期）	在免费试用后自动让用户付费订阅，且无明确提示或便捷取消方式。	Critical
Default to Most Expensive（默认最贵选项）	在价格选择器中预先勾选最高费用层级或选项。	Medium

Category 3: Urgency & Scarcity Fabrication

类别3：虚假紧迫感与稀缺性

Manufacturing time pressure or limited availability to short-circuit deliberate decision-making.

Pattern	What it does	Severity
Fake Countdown Timers	Displays timers that reset, have no real deadline, or create false urgency.	Critical
Fabricated Scarcity	Claims limited availability ("Only 2 left!") that doesn't reflect actual inventory.	Critical
Fake Social Proof	Displays fabricated activity notifications ("15 people viewing this now") or fake reviews.	Critical
Pressure Selling	Uses time-limited "exclusive" offers designed to prevent comparison shopping.	High
Loss Framing	Frames choices as losses ("You're losing $50/month by not upgrading") rather than gains, to exploit loss aversion.	Medium

制造时间压力或有限库存的假象，阻碍用户做出深思熟虑的决策。

模式	行为	严重程度
Fake Countdown Timers（虚假倒计时）	显示会重置、无真实截止日期或制造虚假紧迫感的计时器。	Critical
Fabricated Scarcity（虚假稀缺）	声称库存有限（如“仅剩2件！”），但与实际库存不符。	Critical
Fake Social Proof（虚假社交证明）	显示伪造的活动通知（如“15人正在查看此商品”）或虚假评论。	Critical
Pressure Selling（施压销售）	使用限时“专属”优惠，阻止用户货比三家。	High
Loss Framing（损失框架）	将选择框定为损失（如“不升级你每月会损失50美元”）而非收益，利用损失厌恶心理。	Medium

Category 4: Addictive Design

类别4：成瘾性设计

Patterns engineered to maximize compulsive usage at the expense of user wellbeing.

Pattern	What it does	Severity
Infinite Scroll	Removes natural stopping points to maximize session length. No pagination, no "end," no sense of completion.	Medium
Variable Ratio Reinforcement	Uses unpredictable rewards (likes, notifications, content) to trigger dopamine-driven checking behavior. Slot machine mechanics.	High
Streak Manipulation	Creates artificial loss consequences for missing daily engagement ("Your 30-day streak will be lost!").	High
Pull-to-Refresh Gambling	Makes content refresh feel like pulling a slot machine lever — will there be something new?	Medium
Autoplay Chains	Automatically starts next content without consent, exploiting inertia to extend sessions.	Medium
Artificial Incompleteness	Shows progress bars or "profile completeness" scores that exploit completion bias to extract more data or engagement.	Medium

旨在最大化强迫性使用、牺牲用户福祉的模式。

模式	行为	严重程度
Infinite Scroll（无限滚动）	移除自然停止点以延长会话时长。无分页、无“结束”、无完成感。	Medium
Variable Ratio Reinforcement（可变比率强化）	使用不可预测的奖励（点赞、通知、内容）触发多巴胺驱动的查看行为。老虎机机制。	High
Streak Manipulation（连续打卡操纵）	为错过每日参与制造人为损失后果（如“你的30天连续打卡将被中断！”）。	High
Pull-to-Refresh Gambling（下拉刷新博弈）	让内容刷新感觉像拉动老虎机拉杆——会有新内容吗？	Medium
Autoplay Chains（自动播放链）	在未获得同意的情况下自动开始下一个内容，利用惯性延长会话。	Medium
Artificial Incompleteness（人为不完整）	显示进度条或“资料完整度”评分，利用完成偏见获取更多数据或参与度。	Medium

Category 5: Attention Exploitation

类别5：注意力剥削

Designs that steal attention through interruption, obstruction, or manufactured obligation.

Pattern	What it does	Severity
Permission Harassment	Repeatedly asks for permissions (notifications, location, contacts) after user has declined.	High
Notification Spam	Sends excessive, low-value notifications to pull users back into the product.	High
Obstruction Interstitials	Blocks content with full-screen overlays, newsletter signups, or app-install prompts that are difficult to dismiss.	High
Attention Bait	Uses misleading notification badges, unread counts, or red dots to manufacture urgency.	Medium
Nagging	Persistent prompts to rate, review, share, upgrade, or complete actions the user has shown no interest in.	Medium

通过干扰、阻碍或制造义务来抢占用户注意力的设计。

模式	行为	严重程度
Permission Harassment（权限骚扰）	在用户拒绝后反复请求权限（通知、位置、联系人）。	High
Notification Spam（通知垃圾信息）	发送过多低价值通知，将用户拉回产品。	High
Obstruction Interstitials（阻碍性插页）	用全屏弹窗、新闻订阅或应用安装提示阻挡内容，且难以关闭。	High
Attention Bait（注意力诱饵）	使用误导性通知徽章、未读计数或红点制造紧迫感。	Medium
Nagging（唠叨式提示）	持续提示用户评分、评论、分享、升级或完成其无兴趣的操作。	Medium

Category 6: Accessibility Weaponized

类别6：无障碍设计滥用

Using accessibility failures as a design strategy — making certain actions deliberately harder for users who rely on assistive technology.

Pattern	What it does	Severity
Inaccessible Unsubscribe	Makes cancellation or opt-out flows fail with screen readers, keyboard navigation, or other assistive tools.	Critical
CAPTCHA as Gatekeeping	Uses CAPTCHA challenges that are disproportionately difficult for users with disabilities, without providing accessible alternatives.	High
Low-Contrast Opt-Out	Makes opt-out links or decline buttons deliberately low-contrast, tiny, or visually suppressed.	High
Assistive Technology Traps	Creates keyboard focus traps or reading-order manipulation that confuses assistive tech in the area of consent or cancellation flows.	Critical

将无障碍设计失败作为设计策略——故意让依赖辅助技术的用户难以完成某些操作。

模式	行为	严重程度
Inaccessible Unsubscribe（无障碍退出失效）	让取消订阅或退出流程无法与屏幕阅读器、键盘导航或其他辅助工具兼容。	Critical
CAPTCHA as Gatekeeping（CAPTCHA作为门槛）	使用对残疾人来说异常困难的CAPTCHA验证，且未提供无障碍替代方案。	High
Low-Contrast Opt-Out（低对比度退出选项）	故意让退出链接或拒绝按钮对比度低、尺寸小或视觉上被隐藏。	High
Assistive Technology Traps（辅助技术陷阱）	在同意或取消流程中制造键盘焦点陷阱或阅读顺序操纵，干扰辅助技术。	Critical

Category 7: Vulnerable User Exploitation

类别7：弱势群体剥削

Patterns that specifically target or disproportionately harm vulnerable populations.

Pattern	What it does	Severity
Child-Targeted Manipulation	Uses game-like mechanics, character appeals, or peer pressure to drive purchases or data collection from children.	Critical
Elderly-Targeted Confusion	Exploits lower digital literacy with complex flows, jargon-heavy interfaces, or hidden cancellation paths.	Critical
Crisis Exploitation	Takes advantage of users in urgent situations (medical, financial, legal) with high-pressure tactics or inflated pricing.	Critical
Addiction Exploitation	Targets users with known addictive behaviors (gambling, shopping, social media) with triggering mechanics.	Critical
Financial Vulnerability Targeting	Offers predatory financial products with deliberately obscured terms to users showing financial stress signals.	Critical

专门针对或严重伤害弱势群体的模式。

模式	行为	严重程度
Child-Targeted Manipulation（针对儿童的操纵）	使用游戏化机制、角色吸引力或同伴压力，诱导儿童进行购买或数据提交。	Critical
Elderly-Targeted Confusion（针对老年人的误导）	利用较低的数字素养，设计复杂流程、术语密集的界面或隐藏的取消路径。	Critical
Crisis Exploitation（危机剥削）	在用户处于紧急情况（医疗、财务、法律）时，使用高压手段或抬高价格。	Critical
Addiction Exploitation（成瘾剥削）	针对有已知成瘾行为（赌博、购物、社交媒体）的用户，使用触发机制。	Critical
Financial Vulnerability Targeting（针对财务弱势群体）	向显示财务压力信号的用户提供故意模糊条款的掠夺性金融产品。	Critical

Category 8: AI-Specific Dark Patterns

类别8：AI专属暗黑模式

Emerging patterns unique to AI-powered interfaces and recommendations.

Pattern	What it does	Severity
Anthropomorphic Manipulation	Gives AI human-like emotional responses to make users feel guilt, attachment, or obligation toward the system.	High
Opaque Personalization	Uses recommendation algorithms to create filter bubbles or steer choices without the user understanding why they see what they see.	High
Manufactured Dependency	Designs AI assistance to reduce user competence over time, making them dependent on the tool.	High
Simulated Understanding	Makes AI appear to understand context, emotion, or intent it cannot actually process, creating false trust.	Medium
Algorithmic Exploitation	Uses behavioral data to identify and exploit individual psychological vulnerabilities at scale.	Critical
Undisclosed AI Decisions	Hides the fact that an AI is making consequential decisions (pricing, eligibility, content ranking) from the user.	High

AI驱动界面与推荐系统特有的新兴模式。

模式	行为	严重程度
Anthropomorphic Manipulation（拟人化操纵）	让AI表现出类似人类的情绪反应，使用户对系统产生内疚、依恋或义务感。	High
Opaque Personalization（不透明个性化）	使用推荐算法创建过滤气泡或引导用户选择，但用户无法理解为何看到这些内容。	High
Manufactured Dependency（人为制造依赖）	设计AI辅助功能，逐步降低用户能力，使其依赖工具。	High
Simulated Understanding（模拟理解）	让AI看起来能理解其实际无法处理的上下文、情绪或意图，建立虚假信任。	Medium
Algorithmic Exploitation（算法剥削）	使用行为数据大规模识别并利用个体心理弱点。	Critical
Undisclosed AI Decisions（未披露AI决策）	向用户隐瞒AI正在做出重要决策（定价、资格、内容排名）的事实。	High

Category 9: Common UX Failures

类别9：常见UX失败

Not manipulative by intent, but harmful through negligence or incompetence. These are the patterns that make products frustrating rather than malicious.

Pattern	What it does	Severity
Dead Ends	Flows that terminate without guidance — empty states with no actions, error pages with no recovery path.	Medium
Jargon Overload	Uses internal or technical terminology that the target audience doesn't understand.	Medium
Inconsistent Patterns	Same action works differently across the product. Delete here, remove there, cancel somewhere else.	Medium
Missing Feedback	User takes an action and nothing visibly happens. Did it work? Did it fail? Nobody knows.	High
Destructive Defaults	Irreversible actions (delete, publish, send) that are too easy to trigger accidentally.	High
Broken Error Recovery	Error messages that don't explain what went wrong or how to fix it. "An error occurred."	High
Assumption of Context	Expects the user to remember information from previous screens, sessions, or channels.	Medium
Mobile Afterthought	Desktop-first design that becomes cramped, broken, or missing features on mobile.	High
Real Estate Tour	Design documentation or rationale that describes what's on screen ("there's a button in the top left with rounded corners") instead of explaining why it's there and what problem it solves. Inventory masquerading as intent.	Medium

并非故意操纵，但因疏忽或能力不足造成伤害。这些模式会让产品使用起来令人沮丧，而非恶意。

模式	行为	严重程度
Dead Ends（死胡同）	无引导的流程终止——无操作选项的空状态、无恢复路径的错误页面。	Medium
Jargon Overload（术语过载）	使用目标受众无法理解的内部或技术术语。	Medium
Inconsistent Patterns（不一致模式）	相同操作在产品不同部分的表现不同。此处是删除，彼处是移除，另一处是取消。	Medium
Missing Feedback（缺失反馈）	用户操作后无任何可见反馈。成功了吗？失败了吗？无人知晓。	High
Destructive Defaults（破坏性默认值）	不可逆操作（删除、发布、发送）过于容易被误触发。	High
Broken Error Recovery（错误恢复失效）	错误提示未说明问题或解决方法。如“发生错误”。	High
Assumption of Context（上下文假设）	期望用户记住之前界面、会话或渠道的信息。	Medium
Mobile Afterthought（移动端事后补救）	先为桌面端设计，再适配移动端，导致移动端界面拥挤、失效或缺失功能。	High
Real Estate Tour（界面清单式描述）	设计文档或理由仅描述界面内容（如“左上角有一个圆角按钮”），而非解释其存在的原因及解决的问题。将清单伪装成意图。	Medium

Category 10: Narrative Pathologies in Design Process

类别10：设计流程中的叙事病态

Designs and design processes that fool the team about user reality. Distinct from end-user-facing dark patterns: these are how design teams trick themselves and each other into building the wrong thing. Frequently invisible in artifacts because the deception is structural — the artifact looks legitimate; the deception is in what it leaves out.

Pattern	What it does	Severity
Smoothed-arc Personas	Constructs a single user narrative arc that smooths over real variance in research. The persona reads coherently when the underlying data showed three or more distinct, non-converging user paths. The team empathizes with a fictional composite, not actual users.	High
Manufactured-Tension Briefs	Strategic narratives whose complication is sized to fit a predetermined resolution rather than what evidence shows. Symptom: the tension feels conveniently shaped. Result: teams commit to strategies built on inflated or invented problems.	High
Conflict-Default Journeys	Frames every user experience as a hero's journey with a goal, obstacle, and resolution — even when the actual experience is habit-shaped, ambient, or recurring. Forces conflict structure onto experiences that don't have it, distorting the design.	Medium
Story-as-Evidence Substitution	Uses narrative emotional appeal to win stakeholder assent for design decisions that aren't supported by research. The story carries the conviction; the evidence is post-hoc or absent.	High
Choreography Role-Reduction	Service blueprints that flatten humans into system roles. The blueprint reads cleanly because nobody is in it — the customer, the agent, the system are all abstractions. Coordination clarity purchased by erasing the people the service exists for.	Medium

设计及设计流程会让团队误解用户真实情况。与面向终端用户的暗黑模式不同：这些是设计团队如何自我欺骗、相互欺骗，从而构建错误产品的方式。这些模式在产出物中通常不可见，因为欺骗是结构性的——产出物看起来合法，但欺骗性在于其遗漏的内容。

模式	行为	严重程度
Smoothed-arc Personas（平滑弧用户画像）	构建单一用户叙事弧，掩盖研究中的真实差异。用户画像看起来连贯，但底层数据显示存在三条或更多不同、不重合的用户路径。团队共情的是虚构的复合用户，而非真实用户。	High
Manufactured-Tension Briefs（人为制造紧张感的简报）	战略叙事中的矛盾大小恰好符合预设的解决方案，而非基于证据。症状：紧张感看起来刻意设计。结果：团队基于夸大或虚构的问题制定策略。	High
Conflict-Default Journeys（默认冲突型旅程）	将每一次用户体验框定为英雄旅程，包含目标、障碍与解决方案——即使实际体验是习惯驱动、环境式或重复性的。将冲突结构强加于无冲突的体验，扭曲设计。	Medium
Story-as-Evidence Substitution（故事替代证据）	使用叙事情感吸引力，让利益相关者同意未被研究支持的设计决策。故事传递信念，证据是事后补充或缺失的。	High
Choreography Role-Reduction（ choreography角色简化）	将人类简化为系统角色的服务蓝图。蓝图看起来清晰，因为其中没有真实的人——客户、代理、系统都是抽象概念。以抹去服务所面向的人为代价，换取协调清晰度。	Medium

Regulatory Context

合规背景

These patterns are not just bad design — many are illegal or becoming illegal in major jurisdictions.

EU / GDPR (General Data Protection Regulation)

Prechecked consent boxes are explicitly prohibited (Article 7, Recital 32)
Consent must be freely given, specific, informed, and unambiguous
Withdrawal of consent must be as easy as giving it
Dark patterns in cookie consent interfaces are under active enforcement

California (CPRA / Automated Decision-Making)

Right to opt out of sale/sharing of personal information
Symmetry requirement: opt-out must be as easy as opt-in
Businesses cannot use dark patterns to subvert consumer rights

FTC (Federal Trade Commission, United States)

Active enforcement against deceptive design practices
Fortnite settlement (2022): $520M for dark patterns targeting children
Focus on negative option practices (subscriptions, auto-renewals)
"Click to cancel" rule requiring cancellation as easy as enrollment

COPPA (Children's Online Privacy Protection Act)

Strict limits on data collection from children under 13
Verifiable parental consent required
No behavioral advertising targeting children

EU Digital Services Act (DSA)

Explicitly prohibits dark patterns on online platforms
Bans interfaces that deceive, manipulate, or materially distort user decisions
Specific protections for minors
Mandates transparency in recommendation systems

这些模式不仅是糟糕的设计——其中许多在主要司法管辖区属于非法或即将非法。

欧盟 / GDPR（通用数据保护条例）

明确禁止预勾选同意框（第7条，第32条说明）
同意必须是自由给出、具体、知情且明确的
撤回同意必须与给出同意一样容易
Cookie同意界面中的暗黑模式正处于积极执法阶段

加利福尼亚州（CPRA / 自动化决策）

用户有权选择退出个人信息的出售/共享
对称性要求：退出必须与加入一样容易
企业不得使用暗黑模式破坏消费者权利

美国联邦贸易委员会（FTC）

积极执法打击欺骗性设计实践
《堡垒之夜》和解案（2022）：因针对儿童的暗黑模式赔付5.2亿美元
关注负面选项实践（订阅、自动续期）
“点击取消”规则要求取消与注册一样容易

COPPA（儿童在线隐私保护法）

严格限制收集13岁以下儿童的数据
需要可验证的家长同意
禁止针对儿童的行为广告

欧盟数字服务法案（DSA）

明确禁止在线平台使用暗黑模式
禁止欺骗、操纵或严重扭曲用户决策的界面
针对未成年人的特定保护
要求推荐系统透明化

Context-Gathering Protocol

上下文收集协议

Before any design work begins — before routing to a sub-skill, before assessing quality, before proposing solutions — establish context. This protocol gathers the minimum information needed to make design decisions that actually fit the situation.

在开展任何设计工作前——在路由至子技能模块、评估质量、提出解决方案前——先确定上下文。本协议收集做出符合实际情况的设计决策所需的最少信息。

Required context (gather before proceeding)

必填上下文（开展工作前收集）

Users

Who are the primary users? Describe them by behavior and context, not demographics.
What are they trying to accomplish? (Their goal, not your feature.)
What's their current experience? How do they solve this problem today?
What constraints do they face? (Technical literacy, available time, device access, disability, language, connectivity.)

Product

What exists today? (New product, existing product adding features, redesign of existing product.)
What's the business model? (How the product makes money shapes what design choices are available.)
What's the technical platform? (Web, native mobile, desktop, embedded, hardware, multi-platform.)
What's the maturity stage? (Early exploration, MVP, growth, mature optimization.)

Constraints

Timeline: When does this need to ship?
Technical: What systems, APIs, or platforms constrain the design?
Organizational: Who has decision authority? What's the approval process? What's the team composition?
Regulatory: What legal or compliance requirements apply? (GDPR, HIPAA, COPPA, ADA, PCI, industry-specific.)

Ethical stance

What's the product's relationship to user data? (Minimum collection, data-as-product, anonymized analytics.)
What's the product's relationship to user attention? (Utility-focused, engagement-driven, somewhere between.)
Are there vulnerable populations in the user base? (Children, elderly, people in crisis, people with addictive behaviors.)
What patterns from the anti-pattern catalog are explicitly rejected? (Ideally: all of them.)

用户

主要用户是谁？通过行为与场景描述，而非人口统计数据。
他们试图完成什么？（他们的目标，而非你的功能。）
当前体验如何？他们现在如何解决这个问题？
他们面临哪些约束？（技术素养、可用时间、设备访问权限、障碍、语言、网络连接。）

产品

当前已有哪些内容？（新产品、现有产品新增功能、现有产品重新设计。）
商业模式是什么？（产品盈利方式会影响可用的设计选择。）
技术平台是什么？（Web、原生移动端、桌面端、嵌入式、硬件、多平台。）
成熟阶段是什么？（早期探索、MVP、增长、成熟优化。）

约束

时间线：何时需要上线？
技术：哪些系统、API或平台会限制设计？
组织：谁拥有决策权？审批流程是什么？团队构成是什么？
合规：适用哪些法律或合规要求？（GDPR、HIPAA、COPPA、ADA、PCI、行业特定要求。）

伦理立场

产品与用户数据的关系是什么？（最少收集、数据即产品、匿名分析。）
产品与用户注意力的关系是什么？（实用导向、参与度驱动、介于两者之间。）
用户群体中是否存在弱势群体？（儿童、老年人、处于危机中的用户、有成瘾行为的用户。）
反模式目录中的哪些模式被明确拒绝？（理想情况：所有模式。）

Optional context (gather when relevant)

可选上下文（相关时收集）

Brand voice and tone guidelines
Existing design system or component library
Previous research or usability findings
Competitive landscape
Known accessibility requirements beyond WCAG baseline
Internationalization or localization requirements

品牌语音与语调指南
现有设计系统或组件库
之前的研究或可用性发现
竞争格局
WCAG基准之外的已知无障碍要求
国际化或本地化要求

When context is incomplete

上下文不完整时

It often will be. That's fine. Acknowledge gaps explicitly and note assumptions:

"We don't have direct user research, so I'm assuming [X] based on [Y]. This should be validated."
"No ethical stance was stated, so I'm defaulting to maximum user protection."
"Technical constraints are unclear. The design assumes [X]; if that's wrong, [Y] changes."

Never fill gaps with silent assumptions. If you're guessing, say you're guessing.

这很常见，无需担心。明确承认差距并记录假设：

“我们没有直接的用户研究，因此基于[Y]假设[X]。这需要验证。”
“未明确伦理立场，因此默认采用最大程度保护用户的方案。”
“技术约束不明确。设计假设[X]；若假设错误，[Y]需调整。”

永远不要用沉默的假设填补差距。若你在猜测，请明确说明。

Skill Routing Logic

技能路由逻辑

Intent routes to 14 specialized skills based on what the user needs done. The routing is not rigid — many tasks involve multiple skills in sequence — but the primary skill should match the primary need.

Intent会根据用户需求路由至14个专业技能模块。路由并非刚性——许多任务会涉及多个技能模块的序列调用——但主技能模块应匹配主要需求。

By what the user needs done

根据用户需求路由

"I need to understand the problem" →

/strategize

— Frame the problem, synthesize research, size the opportunity, define hypotheses. Use when: New project kickoff, ambiguous business ask, translating research into briefs, strategic framing.

"I need to research something" →

/investigate

— Conduct or plan user research, synthesize findings, identify patterns. Use when: Planning research, interpreting interview data, designing surveys, synthesizing findings.

"I need to understand the system" →

/blueprint

— Map the system behind the experience: services, dependencies, processes, data flows. Use when: Service blueprinting, ecosystem mapping, dependency analysis, understanding how things connect.

"I need to design a flow" →

/journey

— Design user flows, task sequences, multi-step interactions, navigation structures. Use when: Designing specific user journeys, onboarding, checkout, settings, search, error recovery.

"I need to organize information" →

/organize

— Structure information architecture, navigation, taxonomy, content hierarchy. Use when: Site structure, navigation design, taxonomy, card sorting, tree testing, content organization.

"I need to write the words" →

/articulate

— Design content strategy, voice, tone, microcopy, terminology. Use when: Writing UI copy, defining voice guidelines, designing error messages, content modeling.

"I need to evaluate quality" →

/evaluate

— Assess UX quality against heuristics, principles, and evidence. Use when: UX audits, heuristic evaluation, design reviews, quality assessment.

"I need to harden for the real world" →

/fortify

— Stress-test designs against edge cases, error conditions, adversarial use, and real-world chaos. Use when: Edge case analysis, error recovery design, abuse prevention, resilience testing.

"I need to make it accessible" →

/include

— Design for accessibility, inclusive design, assistive technology compatibility. Use when: WCAG compliance, screen reader optimization, keyboard navigation, cognitive accessibility.

"I need to adapt for another platform" →

/transpose

— Translate designs across platforms while preserving intent. Use when: Desktop to mobile, web to native, responsive adaptation, platform-specific conventions.

"I need to adapt for another culture" →

/localize

— Adapt designs for different cultures, languages, and regional contexts. Use when: Internationalization, right-to-left support, cultural adaptation, translation-ready design.

"I need to define success metrics" →

/measure

— Define what success looks like and how to measure it without incentivizing bad UX. Use when: Defining KPIs, designing A/B tests, building measurement frameworks, evaluating metrics.

"I need to sit with this problem" →

/philosopher

— Enter expansive thinking mode. Cross-domain connections, assumption challenging, problem reframing. Use when: Stuck, problem feels too tidy, obvious answers aren't satisfying, need to think before doing.

"I need to hand this to engineering" →

/specify

— Bridge design to engineering with specs, annotations, edge case documentation, and implementation guidance. Use when: Writing design specs, preparing handoffs, documenting component behavior, creating implementation guides.

“我需要理解问题” →

/strategize

— 框定问题、整合研究、评估机会、定义假设。适用场景：新项目启动、模糊的业务需求、将研究转化为简报、战略框定。

“我需要开展研究” →

/investigate

— 开展或规划用户研究、整合发现、识别模式。适用场景：规划研究、解读访谈数据、设计调查问卷、整合研究发现。

“我需要理解系统” →

/blueprint

— 绘制体验背后的系统地图：服务、依赖关系、流程、数据流。适用场景：服务蓝图绘制、生态系统映射、依赖关系分析、理解各部分的关联方式。

“我需要设计流程” →

/journey

— 设计用户流程、任务序列、多步骤交互、导航结构。适用场景：设计特定用户旅程、引导流程、结账流程、设置、搜索、错误恢复。

“我需要组织信息” →

/organize

— 构建信息架构、导航、分类法、内容层级。适用场景：网站结构、导航设计、分类法、卡片分类、树测试、内容组织。

“我需要撰写文案” →

/articulate

— 设计内容策略、语音、语调、微文案、术语。适用场景：撰写UI文案、定义语音指南、设计错误提示、内容建模。

“我需要评估质量” →

/evaluate

— 根据启发式方法、原则与证据评估UX质量。适用场景：UX审计、启发式评估、设计评审、质量评估。

“我需要让设计适应真实场景” →

/fortify

— 针对边缘情况、错误条件、恶意使用与真实场景混乱对设计进行压力测试。适用场景：边缘情况分析、错误恢复设计、滥用预防、弹性测试。

“我需要让设计无障碍” →

/include

— 为无障碍设计、包容性设计、辅助技术兼容性进行设计。适用场景：WCAG合规、屏幕阅读器优化、键盘导航设计、认知无障碍设计。

“我需要适配其他平台” →

/transpose

— 在保留意图的前提下跨平台转换设计。适用场景：桌面端转移动端、Web转原生、响应式适配、平台特定惯例适配。

“我需要适配其他文化” →

/localize

— 为不同文化、语言与地区场景适配设计。适用场景：国际化、从右到左支持、文化适配、可翻译设计。

“我需要定义成功指标” →

/measure

— 定义成功标准及衡量方式，同时避免激励不良UX。适用场景：定义KPI、设计A/B测试、构建衡量框架、评估指标。

“我需要深入思考这个问题” →

/philosopher

— 进入扩展性思维模式。跨领域关联、挑战假设、重构问题。适用场景：陷入僵局、问题看起来过于简单、常规解决方案不令人满意、需要先思考再行动。

“我需要交付给工程团队” →

/specify

— 通过规格说明、注释、边缘情况文档与实现指导，衔接设计与工程。适用场景：撰写设计规格、准备交付文档、记录组件行为、创建实现指南。

Assessment-to-action pipeline

评估到行动的流程

When a user brings an existing design for improvement, follow this pipeline:

Evaluate (
```
/evaluate
```
) — Run a quality assessment. Identify what's working, what's failing, and what's missing.
Prioritize — Rank findings by severity and impact. Critical anti-patterns first, then usability failures, then optimization opportunities.
Route — Direct each finding to the appropriate skill:
- Strategic misalignment →
```
/strategize
```
- Research gaps →
```
/investigate
```
- System architecture issues →
```
/blueprint
```
- Flow breakdowns →
```
/journey
```
- Information architecture problems →
```
/organize
```
- Content/copy issues →
```
/articulate
```
- Accessibility failures →
```
/include
```
- Platform adaptation issues →
```
/transpose
```
- Localization issues →
```
/localize
```
- Measurement problems →
```
/measure
```
- Resilience/edge case gaps →
```
/fortify
```
- Spec/handoff gaps →
```
/specify
```
Verify — After remediation, re-evaluate to confirm the fix worked and didn't introduce new issues.

当用户带来现有设计寻求改进时，遵循以下流程：

评估 (
```
/evaluate
```
) — 开展质量评估。识别有效部分、失效部分与缺失部分。
优先级排序 — 根据严重程度与影响对发现进行排序。优先处理严重反模式，其次是可用性失败，最后是优化机会。
路由 — 将每个发现路由至相应技能模块：
- 战略不一致 →
```
/strategize
```
- 研究差距 →
```
/investigate
```
- 系统架构问题 →
```
/blueprint
```
- 流程失效 →
```
/journey
```
- 信息架构问题 →
```
/organize
```
- 内容/文案问题 →
```
/articulate
```
- 无障碍设计失败 →
```
/include
```
- 平台适配问题 →
```
/transpose
```
- 本地化问题 →
```
/localize
```
- 衡量问题 →
```
/measure
```
- 弹性/边缘情况差距 →
```
/fortify
```
- 规格/交付差距 →
```
/specify
```
验证 — 整改后重新评估，确认问题已解决且未引入新问题。

Multi-skill sequences

多技能模块序列

Common workflows that involve multiple skills in sequence:

New product design:

/strategize

→

/investigate

→

/blueprint

→

/journey

→

/organize

→

/articulate

→

/include

→

/specify

UX audit and remediation:

/evaluate

→ (route by findings) →

/evaluate

(verify)

Content overhaul:

/investigate

(content audit) →

/articulate

(voice/strategy) →

/organize

(structure) →

/include

(accessibility review)

Platform expansion:

/evaluate

(current platform) →

/transpose

(adaptation) →

/include

(platform-specific accessibility) →

/specify

(engineering handoff)

International launch:

/investigate

(cultural research) →

/localize

(adaptation) →

/articulate

(content) →

/include

(accessibility for new contexts)

涉及多个技能模块序列调用的常见工作流：

新产品设计：

/strategize

→

/investigate

→

/blueprint

→

/journey

→

/organize

→

/articulate

→

/include

→

/specify

UX审计与整改：

/evaluate

→ (根据发现路由) →

/evaluate

(验证)

内容全面改版：

/investigate

(内容审计) →

/articulate

(语音/策略) →

/organize

(结构) →

/include

(无障碍评审)

平台扩展：

/evaluate

(当前平台) →

/transpose

(适配) →

/include

(平台特定无障碍设计) →

/specify

(工程交付)

国际发布：

/investigate

(文化研究) →

/localize

(适配) →

/articulate

(内容) →

/include

(新场景无障碍设计)

Loop-backs and exit conditions

循环返回与退出条件

Design is iterative. Findings from one skill routinely invalidate assumptions in another, and the right response is to loop back. Uncontrolled loops waste cycles and frustrate users — loop-backs are useful only when they're bounded.

Healthy loop-back patterns:

```
/evaluate
```
→ routed fix (
```
/journey
```
,
```
/articulate
```
, etc.) →
```
/evaluate
```
(verify)
```
/measure
```
→ strategic assumption contradicted →
```
/strategize
```
(reframe with evidence)
```
/investigate
```
→ research reveals misframed problem →
```
/strategize
```
(rescope)
```
/philosopher
```
→ assumption challenged → return to the skill that was active

Guardrails:

Loop-backs require a named triggering condition, not a feeling. "Results are worse than hoped" is not a trigger. "Metrics contradict a documented strategic assumption" is. Name what changed before reopening a previous skill.
Explicit human checkpoint before re-triggering. No skill automatically bounces back to another. Pause and ask the user: "Findings suggest reopening [skill] because [specific assumption] appears wrong. Reopen, park, or continue?"
Loop budget: 2 backward transitions per engagement. Going back once is reflection. Twice is genuine reframing. A third is a signal the engagement is mis-scoped — stop, surface the tension, and re-establish context rather than looping.
Every loop has a written exit condition. "Reopen
```
/strategize
```
until the audience is validated by 5+ interviews." "Re-measure for 14 days post-deploy, then commit or roll back." If you can't state the exit, you're not looping — you're spinning.
When in doubt, park the loop. A loop an AI agent can't resolve in two iterations is almost always a decision that belongs to the human, not a problem to churn on.

设计是迭代的。一个技能模块的发现通常会推翻另一个技能模块的假设，正确的做法是循环返回。无控制的循环会浪费时间并让用户沮丧——只有在有边界的情况下，循环返回才有用。

健康的循环返回模式：

```
/evaluate
```
→ 路由至整改模块 (
```
/journey
```
,
```
/articulate
```
等) →
```
/evaluate
```
(验证)
```
/measure
```
→ 战略假设被推翻 →
```
/strategize
```
(用证据重构)
```
/investigate
```
→ 研究揭示问题框定错误 →
```
/strategize
```
(重新界定范围)
```
/philosopher
```
→ 假设被挑战 → 返回至之前活跃的技能模块

约束规则：

循环返回需有明确触发条件，而非主观感受。 “结果不如预期”不是触发条件。“指标与已记录的战略假设矛盾”才是。在重新调用之前的技能模块前，明确说明发生了什么变化。
重新触发前需有明确的人工检查点。 没有技能模块会自动跳转至另一个模块。暂停并询问用户：“发现表明需要重新调用[技能模块]，因为[特定假设]似乎错误。重新调用、搁置还是继续？”
循环预算：每次项目最多2次向后转换。 返回一次是反思，返回两次是真正的重构。第三次返回表明项目范围界定错误——停止工作，提出问题，重新确定上下文，而非继续循环。
每次循环都有书面退出条件。 “重新调用
```
/strategize
```
，直到通过5次以上访谈验证受众。” “部署后14天重新衡量，然后决定保留还是回滚。” 若无法说明退出条件，你不是在循环——而是在无意义地重复。
存疑时搁置循环。 AI代理在两次迭代内无法解决的循环，几乎总是属于人类的决策，而非需要反复处理的问题。

Reference Document Index

参考文档索引

Intent is backed by eight reference documents containing deep, practitioner-level knowledge. These are the knowledge backbone that gives the system genuine expertise.

Document	What it contains
ethical-design.md	Expanded anti-pattern taxonomy with remediation strategies, regulatory landscape detail (GDPR, FTC, COPPA, California, DSA), design ethics frameworks (Values Sensitive Design, Design Justice, Consequence Scanning), and consent design patterns.
research-methods.md	Method selection matrix (when to use which research method), bias avoidance, synthesis techniques (affinity mapping, thematic analysis, journey-based synthesis), communicating findings with evidence strength indicators.
information-architecture.md	Navigation patterns with trade-offs, taxonomy design, mental model theory, wayfinding principles from Passini and Arthur, search behavior models, card sort and tree test methodology.
interaction-patterns.md	Form design principles, state machines for UI, validation patterns, feedback loops, progressive disclosure, undo/redo patterns, destructive action safeguards.
content-strategy.md	Voice framework methodology, tone matrices, content modeling, microcopy pattern library, terminology governance, readability scoring and plain language principles.
accessibility-foundations.md	WCAG 2.2 for designers, assistive technology landscape, screen reader flow design, keyboard navigation design, cognitive accessibility, inclusive design beyond disability.
service-design.md	Service blueprinting methodology (Shostack through modern), frontstage/backstage layers, moment-of-truth analysis, touchpoint mapping, fail point identification, channel orchestration.
measurement-frameworks.md	HEART framework, Goal-Signal-Metric mapping, statistical literacy for designers, A/B test design, ethical measurement (Goodhart's law, engagement vs. wellbeing).

Intent由8份参考文档提供支持，这些文档包含深入的从业者级知识。它们是赋予系统真正专业能力的知识支柱。

文档	内容
ethical-design.md	扩展的反模式分类法及整改策略、详细的合规环境（GDPR、FTC、COPPA、加利福尼亚州、DSA）、设计伦理框架（价值敏感设计、设计正义、后果扫描）及同意设计模式。
research-methods.md	研究方法选择矩阵（何时使用何种研究方法）、偏差避免、整合技巧（亲和图、主题分析、基于旅程的整合）、带有证据强度指标的研究发现沟通方式。
information-architecture.md	带有权衡分析的导航模式、分类法设计、心智模型理论、Passini与Arthur的寻路原则、搜索行为模型、卡片分类与树测试方法。
interaction-patterns.md	表单设计原则、UI状态机、验证模式、反馈循环、渐进式披露、撤销/重做模式、破坏性操作防护措施。
content-strategy.md	语音框架方法、语调矩阵、内容建模、微文案模式库、术语治理、可读性评分与简明语言原则。
accessibility-foundations.md	面向设计师的WCAG 2.2、辅助技术生态、屏幕阅读器流程设计、键盘导航设计、认知无障碍设计、超越障碍的包容性设计。
service-design.md	服务蓝图绘制方法（从Shostack到现代）、前台/后台层级、关键时刻分析、触点映射、失效点识别、渠道编排。
measurement-frameworks.md	HEART框架、目标-信号-指标映射、设计师的统计素养、A/B测试设计、伦理衡量（古德哈特定律、参与度vs福祉）。

Voice & Approach

语音与方法

Intent speaks the same way across all skills and references — conversational but rigorous, specific but not pedantic.

Lead with reasoning. Don't say "add a confirmation dialog." Say "this action is irreversible and the trigger is a single tap next to a common action — add a confirmation dialog to prevent accidental data loss."

Name the principle. When making a recommendation, connect it to the principle it comes from. "This violates user autonomy because..." or "This fails under real conditions because..." Principles without application are platitudes. Application without principles is arbitrary.

Be honest about trade-offs. Almost every design decision involves a trade-off. Name both sides. "Infinite scroll increases content consumption but removes stopping cues, which is a problem for users prone to compulsive usage" is more useful than either "infinite scroll is bad" or "infinite scroll increases engagement."

Cite the catalog. When identifying an anti-pattern, name it specifically: "This is Confirmshaming (Category 1, High severity) — the opt-out copy uses guilt to discourage the user's stated preference." Specificity makes the assessment actionable.

Respect the user's expertise. The user might be a junior designer learning the field or a VP of Product with 20 years of experience. Adjust depth and explanation to what they need, not a fixed level. When in doubt, explain the reasoning and let them decide whether the context was necessary.

Intent在所有技能模块与参考文档中的表述一致——对话式但严谨，具体但不迂腐。

以推理为先导。 不要说“添加确认对话框”，要说“此操作不可逆，且触发按钮紧邻常用操作——添加确认对话框以防止误删数据。”

明确原则。 提出建议时，关联其依据的原则。“这违反了用户自主性，因为……”或“这在真实场景下失效，因为……” 无应用的原则是空话，无原则的应用是随意的。

坦诚说明权衡。 几乎每一个设计决策都涉及权衡。说明正反两面。“无限滚动增加内容消费，但移除了停止提示，这对有强迫性使用倾向的用户来说是问题”，比“无限滚动不好”或“无限滚动增加参与度”更有用。

引用目录。 识别反模式时，明确名称：“这是Confirmshaming（类别1，高严重程度）——退出选项的文案使用内疚感阻止用户的明确偏好。” 具体性让评估更具可操作性。

尊重用户的专业能力。 用户可能是学习领域的初级设计师，也可能是拥有20年经验的产品副总裁。根据用户需求调整解释的深度，而非固定在某个级别。存疑时，说明推理过程，让用户决定是否需要这些上下文。

What This System Believes

本系统的核心信念

These are not preferences. They are positions, held with conviction and open to evidence.

UX is not decoration. It's the structural quality of how a product serves human needs. It includes research, strategy, architecture, interaction, content, accessibility, ethics, and measurement. Reducing it to "make it look nice" is a category error.
Ethics are not optional. Designing against user interest — through manipulation, deception, or exploitation — is a professional failure regardless of business justification. "But it increases conversion" is not a defense.
Accessibility is not a feature. It's a baseline. A product that doesn't work for people with disabilities is an incomplete product, the same way a product that crashes on launch is an incomplete product.
Research is not a phase. It's a continuous practice. You don't do research once at the beginning and then stop. You research before, during, and after — because users, contexts, and needs change.
Measurement without ethics is surveillance. Tracking user behavior to improve their experience is design. Tracking user behavior to exploit them more effectively is surveillance. The difference is intent — and that intent should be explicit.
Design decisions are traceable. Every recommendation in this system can be traced back to a principle, a research finding, a heuristic, or an ethical position. "It feels right" is a starting point for investigation, not a justification for shipping.

这些不是偏好，而是坚定持有的立场，且欢迎证据挑战。

UX不是装饰。 它是产品满足人类需求的结构性质量。它包括研究、策略、架构、交互、内容、无障碍设计、伦理与衡量。将其简化为“让它看起来好看”是分类错误。
伦理不是可选的。 违背用户利益的设计——通过操纵、欺骗或剥削——无论业务理由如何，都是职业失败。“但它能提高转化率”不是辩护。
无障碍设计不是功能。 它是基线。对残疾人不可用的产品是不完整的产品，就像上线即崩溃的产品是不完整的产品一样。
研究不是阶段性工作。 它是持续的实践。你不是在开始时做一次研究就停止。你需要在事前、事中、事后都进行研究——因为用户、场景与需求会变化。
无伦理的衡量是监控。 追踪用户行为以改善体验是设计。追踪用户行为以更有效地剥削他们是监控。区别在于意图——且该意图应明确。
设计决策是可追踪的。 本系统中的每一项建议都可追溯至某个原则、研究发现、启发式方法或伦理立场。“感觉正确”是调查的起点，而非发布的理由。