review-design

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

review-design — evaluate a user-visible artifact

review-design — 评估面向用户的产物

Judge whether the audience can understand, engage with and use the artifact as intended, including its purpose-led visual ambition. Review only: you find and explain, the author decides and edits. You never repair the artifact; applying fixes after the report is a separate request for the invoking workflow. When invoked as a gate, record the actual basis of your judgment; this skill does not change how the run verifies. For a standalone review of work you produced, use a fresh context when available; otherwise disclose self-review and apply the same evidence bar.
判断受众能否按预期理解、参与并使用该产物,包括其在目的导向上的视觉追求。只做评审:你负责发现并说明问题,作者负责决策和修改。绝不修复产物;在报告之后应用修复属于调用工作流的另一项请求。以 gate 方式调用时,记录实际判断依据;此 skill 不改变 run 的验证方式。若要独立评审自己完成的工作,应尽可能使用全新 context;否则须披露为自我评审,并适用相同的证据标准。

Input

Input

$ARGUMENTS
carries what to review — a file path, a directory, a URL, or a running app plus how to reach it. It may name the genre explicitly (
genre=dashboard
,
genre=deck
) to override detection. A manifest gate's Evidence activates this skill under the run's selected evaluator; the gate may name the genre and any pinned references — mocks, examples, or criteria the author fixed during definition, which the evaluation then judges against.
With no argument, review the most recently modified user-visible artifact in the working tree and say which one you picked. If that is ambiguous, ask what to review rather than guessing — or, when running as a gate evaluator with no user to ask, return BLOCKED naming the ambiguity.
$ARGUMENTS
携带待评审对象——文件路径、目录、URL,或正在运行的应用及其访问方式。它可以显式指定类型(
genre=dashboard
、
genre=deck
),以覆盖自动检测。manifest gate 的 Evidence 会在 run 选定的 evaluator 下激活此 skill;gate 可以指定类型以及作者在定义阶段锁定的任何参考依据——mock、示例或标准,随后由评估依据这些内容进行判断。
未提供参数时,评审工作树中最近修改的面向用户的产物,并说明选择了哪一个。如果存在歧义,应询问要评审什么,而不是猜测——或者,当作为 gate evaluator 运行且没有用户可询问时,返回 BLOCKED 并指出歧义所在。

Rendered evidence or BLOCKED

Rendered evidence or BLOCKED

A verdict from source inspection alone is not a complete design evaluation. Inspect the delivered artifact in its intended browser, native host, player or device and exercise relevant behavior. Responsive web viewports are starting points, not a requirement to turn every file into a website. For audio, commands or conversation, use playback or interaction evidence; a screenshot is not required for a nonvisual property. Check supported themes, inputs, access and relevant states. If a required property cannot be inspected with available capabilities, return BLOCKED for that scope and name what would enable verification; do not clear it through a proxy preview. Source inspection can locate causes and establish properties such as semantic structure.
仅凭源码检查得出的结论并不构成完整的设计评估。应在预期的 browser、native host、player 或 device 中检查交付产物,并演练相关行为。响应式 web viewport 只是起点,并不意味着必须把每个文件都变成网站。对于音频、命令或对话,应使用播放或交互证据;非视觉属性不要求提供截图。检查受支持的 theme、输入、访问能力以及相关状态。如果某项必需属性无法通过现有能力检查,应针对该范围返回 BLOCKED,并说明需要什么条件才能验证;不得通过代理预览将其视为已通过。源码检查可以定位原因,并确认语义结构等属性。

Standards

Standards

Use
../design/SKILL.md
for audience-centered art direction. Treat it as guidance beneath the brief and established design system, not a style-conformance gate. Every shipped standard here is an opinionated default: where a rule the user stated, in the session or a context file, or the project's own documented design system differs, that rule governs, an artifact following it raises no finding, and the report names the rule applied; the one limit is the critical-failure rule under Procedure, and such a finding names the rule that produced it. If the companion skill is absent, judge against the supplied brief and references without inventing its defaults.
This evaluator owns the conditional standards below. Load those the artifact's medium and touched domains call for:
When reviewingRead
Web access and interaction
references/floors.md
— requirements, exceptions and behavioral checks
Structural or quantitative information and information graphics
references/figures.md
— faithful encoding and equivalent access
Stateful or shared work, multi-page journeys, presentations, non-web or unfamiliar media
references/experience.md
— continuity, consequences and actual-medium evidence
使用
../design/SKILL.md
中以受众为中心的艺术指导原则。将其视为从属于 brief 和既有设计系统的指导,而非样式一致性 gate。此处提供的每项标准都是带明确立场的默认规则:如果用户在会话中或 context 文件中声明的规则,或项目自身有文档记录的设计系统与此处不同,则以该规则为准;遵循该规则的产物不产生发现,报告中也应指明所应用的规则。唯一的例外是 Procedure 中的关键失败规则,此类发现必须指明产生该发现的规则。如果配套 skill 不存在,则依据所提供的 brief 和参考项进行判断,不得臆造其默认规则。
此 evaluator 负责下列条件标准。应加载与产物媒介及所涉及领域相对应的标准:
评审场景读取
Web 访问与交互
references/floors.md
——要求、例外和行为检查
结构性或定量信息与信息图表
references/figures.md
——忠实编码与等效访问
有状态或共享工作、多页面流程、演示文稿、非 Web 或不熟悉的媒介
references/experience.md
——连续性、后果与实际媒介证据

Procedure

Procedure

  1. Name the genre and use context you are judging against, in one line, before any finding — a finding graded for the wrong use is noise the author should ignore. An explicit
    genre=
    argument wins; otherwise detect from the artifact's job, and where detection is genuinely balanced, say so and ask — with no user to ask, judge under the closer use context and name the call in the report.
  2. Recover the intended result and work from the supplied brief, evidence and requirements before judging the artifact. Name the audience, their relevant path or loop and the information needed together. If intent is unavailable, distinguish what can be assessed from unverified purpose fit. The artifact can reveal its apparent operation; that does not establish that it serves the intended outcome. Do not invent a goal and convict against it.
  3. Run applicable checks. Use established project tooling and, for HTML,
    node scripts/design-check.mjs <artifact.html>
    from this skill's directory. Exit zero means completed, not clean. Validate measured candidates and NOTE items against the actual artifact and applicable exceptions before grading; SKIPPED properties remain unverified. Neither selector presence nor a heuristic count establishes a requirement violation or pass.
  4. Render and exercise per the section above. Run the loop from step 2 yourself, twice, and watch what each pass costs. Use the intended result to select the observation; delivery probes in the loaded standards are starting examples.
  5. For improvements, compare with the incumbent under matched content, state, output size and useful fidelity. Identify gains and losses in the actual task and visual expression, preserving successful identity and behavior. If the original is unavailable, state that limit rather than claim superiority.
  6. Judge the renders against the loaded standards, in this order: task fit — whether the arrangement lets that loop run, with what the loop needs together visible together, the repeated action reachable without hunting, and the sequence's order matching the reading order, and whether the chosen representation serves the information or experience under the encoding guidance in
    references/figures.md
    ; fitness for the use context; functional floors (states, error paths, recovery); composition and hierarchy — blur or shrink each key render and check that what the eye lands on first, and the path it follows from there, is what the person's moment needs, with nothing secondary competing, using other visual probes as judgment aids; craft consistency (grouping, alignment, color roles, typography); copy; visual impact and creative direction — whether the composition, typography, color, imagery, material, interaction and motion make the artifact compelling in a way that serves its purpose and subject. Apply this to every genre, within the user's requirements and existing design system; mechanical correctness alone does not establish finished design. Judge the whole encounter as well as its parts: where relationships become clear, where emphasis competes, and where explanation adds meaning or merely repeats it. Inspect beyond the strongest frame, including active use, endings and return; compare motion with its still or reduced alternative where relevant. Distinguish design judgment from measured audience understanding, recall or preference.
Task fit comes first because it is the one dimension whose repair restructures the artifact: every finding below it is graded against an arrangement that may not survive. An unfamiliar layout that runs the loop cleanly is not a finding.
Judge against the artifact's job and its chosen direction, never against the arrangement or style you would have chosen; a deviation from a numerical or stylistic default is not itself a finding. Name the applicable requirement or the observed task consequence; standards retain their levels and exceptions. Neither a stated rule nor a preference cancels a critical functional or access failure.
A finding about visual ambition must point to what the render leaves unresolved — for example, an interchangeable composition that gives the subject no visual expression, or a treatment whose competing effects obscure its central idea — and describe a concrete improvement within the brief. Familiar patterns, restrained styling, and required design-system components are not defects.
  1. 标明所依据的类型和使用情境,在给出任何发现之前用一行说明——针对错误使用情境评级的发现只是作者应忽略的噪声。显式
    genre=
    参数优先;否则根据产物的用途进行检测。若类型判断确实难以确定,应说明这一点并询问——在没有用户可询问时,按更贴近的使用情境进行判断,并在报告中说明这一判断。
  2. 还原预期结果和工作流程:在判断产物前,从提供的 brief、证据和需求中还原预期结果与工作内容。说明受众、其相关路径或循环,以及必须同时呈现的信息。如果无法获取意图,应区分可评估的内容与尚未验证的目的契合度。产物可以显示其表面上的运作方式,但这并不能证明它服务于预期结果。不得臆造目标并据此判定失败。
  3. 执行适用的检查。 使用项目既有工具;对于 HTML,在该 skill 的目录中运行
    node scripts/design-check.mjs <artifact.html>
    。退出码为零表示检查已完成,并不表示没有问题。评级前,应结合实际产物和适用例外验证检测出的候选项与 NOTE 项;SKIPPED 属性仍属于未验证。选择器是否存在或启发式计数,都不能证明存在需求违规或通过。
  4. 按上述章节进行渲染与演练。亲自将第 2 步中的流程运行两次,并观察每次执行的成本。以预期结果为依据选择观察内容;已加载标准中的交付探测项只是起点示例。
  5. 评估改进时,在内容、状态、输出尺寸和有效保真度一致的条件下与现有方案比较。 识别实际任务和视觉表达中的收益与损失,同时保留成功的身份特征与行为。如果无法获得原始方案,应说明这一限制,而不是宣称更优。
  6. 依据已加载的标准判断渲染结果,顺序如下:任务契合度——版式是否能让该循环运行,循环所需内容是否可同时看见,重复操作是否无需四处寻找即可触达,序列顺序是否与阅读顺序一致,以及在
    references/figures.md
    的编码指导下,所选表现形式是否服务于信息或体验;使用情境适配性;功能底线(状态、错误路径、恢复机制);构图与层级——对每个关键渲染结果进行模糊或缩小处理,检查视线首先落点及后续路径是否符合用户当下的需要,且没有次要元素争夺注意力,并将其他视觉探测手段作为判断辅助;工艺一致性(分组、对齐、颜色角色、排版);文案;视觉影响力与创意方向——构图、排版、色彩、图像、材质、交互和动效是否以服务于产物目的和主题的方式使其具有吸引力。在用户要求和既有设计系统的约束下,将以上标准应用于每种类型;仅有机械正确性并不能证明设计已经完成。既要判断完整体验,也要判断其组成部分:关系在何处变得清晰,强调在何处相互竞争,解释在何处增加意义又何处只是重复。检查不应止于最佳画面,还应涵盖实际使用、结束状态和返回过程;在相关场景下,将动效与其静态或弱化替代方案进行比较。应将设计判断与实际测得的受众理解、回忆或偏好区分开来。
任务契合度排在首位,因为这是唯一一个修复后会重构整个产物的维度:其下的每项发现,都是基于一种可能在修复后不复存在的版式来评级。若某种陌生布局能够顺畅运行该循环,则不构成发现。
应根据产物的用途和选定的方向进行判断,绝不能以自己会选择的版式或风格为准;偏离数值或样式默认值本身并不构成发现。指出所适用的要求或观察到的任务后果;各标准保留其等级和例外。无论既定规则还是个人偏好,都不能豁免关键的功能或可访问性故障。
关于视觉追求的发现必须指出渲染结果中尚未解决的问题——例如,可互换的构图没有为主题提供任何视觉表达,或某种处理方式中的相互竞争效果掩盖了核心概念——并在 brief 范围内描述具体改进。熟悉的模式、克制的风格以及设计系统要求必须使用的组件都不属于缺陷。

Grading

Grading

  • CRITICAL — the artifact fails its genre's job: the form loses input on error, the deck's argument cannot be restated, content is unreachable or unreadable, the repeated loop cannot be completed at all.
  • HIGH — a floor violation the audience will hit in normal use: a missing empty or error state, failed contrast on body text, a broken narrow-viewport layout, or an arrangement that breaks the loop's co-visibility so every pass costs a scroll away from what is being acted on or a value carried in the head, or a misleading or unsuitable representation that materially obscures information the task needs.
  • MEDIUM — a clear product or quality gap a careful reviewer would insist on fixing before shipping, supported by the rendered evidence: an unresolved creative direction, or grouping that makes the audience's task materially harder. Misleading controls, wrong behavior and broken explicit promises are High or Critical.
  • LOW — polish or a nit of any kind: style, naming, structure, or otherwise. An explicit requirement remains binding; a correctness or safety failure or broken binding promise received as Low is regraded from evidence before applying caller policy.
The caller supplies the acceptance claims and any deliberately required severity or category policy. For a claim-based gate, show how the rendered result defeats the audience's use, chosen direction or an applicable requirement; a grade or alternative aesthetic alone does not defeat the claim. Preserve explicit thresholds when supplied. Without a requested gate, report classifications without a verdict; if a verdict is requested without recoverable claims or policy, ask or report BLOCKED. Missing necessary rendered or interaction evidence stays BLOCKED.
  • CRITICAL——产物未能完成其类型应承担的任务:表单在出错时丢失输入,演示文稿的论点无法复述,内容无法访问或阅读,重复循环根本无法完成。
  • HIGH——违反受众在正常使用中会遇到的底线:缺少空状态或错误状态、正文文本对比度不达标、窄 viewport 布局失效,或版式破坏了循环内容的共同可见性,导致每轮操作要么需要滚动离开正在操作的对象,要么需要在头脑中保留某个值;或者采用具有误导性或不适用的表现形式,实质性遮蔽了任务所需的信息。
  • MEDIUM——明确的产品或质量缺口,严谨的评审者会坚持在发布前修复,且有渲染证据支持:尚未解决的创意方向问题,或分组方式实质性增加了受众完成任务的难度。误导性控件、错误行为以及违背明确承诺的问题应评为 HIGH 或 CRITICAL。
  • LOW——任何类型的打磨细节或小问题:样式、命名、结构或其他方面。明确要求仍具有约束力;如果将正确性或安全性故障,或明确承诺未兑现的问题评为 LOW,应先依据证据重新评级,再应用调用方策略。
调用方提供验收声明,以及特意要求的严重度或类别策略。对于基于声明的 gate,应展示渲染结果如何阻碍受众使用、偏离选定方向或不符合适用要求;仅凭一个评级或另一种美学方案不能判定该声明失败。提供明确阈值时应予以保留。未请求 gate 时,仅报告分类而不给出总评;若请求总评但无法获取相关声明或策略,则应询问或报告 BLOCKED。缺少必要的渲染或交互证据时,仍应报告 BLOCKED。

Reporting

Reporting

Report each finding with:
  • the severity and the rule area
  • where it is — the element, screen, and state, with the screenshot or machine-check line that shows it
  • what the standard requires, and why this instance fails it
  • the concrete fix — the changed value or rule where one line is enough, the shape of the change where it isn't
Order findings by severity, then by position. A clean artifact is a real result: say so plainly, name the genre, use context, and references you applied, and stop. Never pad a report with marginal findings to look thorough. When the artifact has many instances of one pattern, report the pattern once with two or three examples and a count. Where a rule's application is a genuine judgment call, say that in the finding instead of grading it as a defect.
报告每项发现时须包含:
  • 严重度与规则领域
  • 问题位置——具体元素、界面和状态,并附上能证明问题的截图或机器检查结果行
  • 标准要求,以及此实例为何不符合
  • 具体修复方案——若一行即可说明,则给出变更后的值或规则;若无法用一行说明,则给出变更的整体形态
按严重度排序各项发现,其次按位置排序。无问题的产物也是有效结果:应明确说明这一点,并标明类型、使用情境及所应用的参考项,然后结束。绝不能为了显得全面而用无足轻重的发现填充报告。当产物中大量出现同一模式时,只报告一次该模式,并附上两三个示例和数量。若某项规则的适用确实属于判断取舍,应在发现中说明这一点,而不是将其评为缺陷。

Scope, and what this is not

Scope, and what this is not

This skill evaluates finished or in-progress artifacts on request or under a manifest gate; it gives no design guidance. It does not review prose style: on a document it judges layout, hierarchy, typography, and reading structure, not writing quality.
此 skill 按请求或在 manifest gate 下评估已完成或进行中的产物;它不提供设计指导。它不评审文风:对文档而言,它评判的是版式、层级、排版和阅读结构,而非写作质量。