newsletter-visuals

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Newsletter Visual Assets

新闻通讯视觉资产

Analyze a newsletter draft, identify the highest-impact opportunities for visual enhancement, and generate on-brand visual assets. Every visual must clarify, persuade, or engage — never decorate.

Core Principle: Visuals earn their place through measurable impact on clarity, engagement, or persuasion. A newsletter with zero visuals is better than one with decorative filler.

分析新闻通讯草稿，识别影响最大的视觉优化机会，并生成符合品牌风格的视觉资产。所有视觉元素必须提升清晰度、增强说服力或提高吸引力——绝不能仅作为装饰。

When to Use

核心原则

Use this skill when:

Enhancing a newsletter draft with visual assets
A draft contains
```
[screenshot]
```
placeholders that need strategic evaluation
The user asks to "add visuals", "create images", or "make this more visual"
A newsletter draft is text-heavy and could benefit from visual breaks

视觉元素的价值在于对内容清晰度、吸引力或说服力的可衡量提升。没有视觉元素的新闻通讯也比充斥装饰性冗余视觉的内容要好。

Prerequisites

适用场景

MANDATORY: A design system must exist before generating any visuals. Check

~/.claude/.context/design-systems/

for available design systems. If none exists, STOP and invoke

branding-kit:design-system

to create one. If one exists, verify its Application Guidelines cover newsletter/website assets.

在以下场景中使用本技能：

为新闻通讯草稿添加视觉资产
草稿包含
```
[screenshot]
```
占位符，需要进行战略性评估
用户要求「添加视觉元素」「创建图片」或「提升视觉效果」
新闻通讯草稿文字内容过多，需要视觉元素来分割内容

Content Type Resolution

前置条件

Content Type	Reference File	Key Focus
Substack newsletter	`references/substack-constraints.md`	Aspect ratios, email rendering, resolution

MANDATORY: Read the relevant reference file before generating any assets.

强制要求：在生成任何视觉资产之前，必须存在一个设计系统。请检查

~/.claude/.context/design-systems/

路径下是否有可用的设计系统。如果不存在，请停止操作并调用

branding-kit:design-system

创建一个。如果已存在，请确认其应用指南涵盖新闻通讯/网站资产相关内容。

Workflow

内容类型适配

Step 1: Audit the Draft

—

Read the full draft and catalog every section. For each section, evaluate:

Existing visuals — Does it already have a
```
[screenshot]
```
placeholder, code block, table, or other visual element? Note what it covers and whether it's sufficient.
Complexity — Is the concept hard to explain in text alone? (process flows, architectures, comparisons, data)
Engagement risk — Is this a point where readers are likely to disengage? (long text-only stretches, dense technical explanations)
Persuasion opportunity — Could a visual make a claim more believable? (cost data, performance comparisons, before/after scenarios)

Existing
[screenshot]
placeholders: These represent real UI captures the author will provide. Treat them as existing visuals. Only recommend replacing one if the concept would be better served by a diagram or illustration — and explicitly flag this to the user with justification.

内容类型	参考文件	核心关注点
Substack新闻通讯	`references/substack-constraints.md`	宽高比、邮件渲染、分辨率

强制要求：在生成任何资产之前，请阅读对应的参考文件。

Step 2: Score and Rank Opportunities

工作流程

—

步骤1：审核草稿

For each potential visual opportunity, score on three dimensions (1-5 each):

Dimension	1 (Low)	5 (High)
Clarity lift	Text explains it fine	Text alone is confusing or requires re-reading
Engagement lift	Section is already engaging	Long text-only stretch, reader likely to skim past
Uniqueness	Generic/decorative visual	Visual reveals structure or data text can't convey

Total score = Clarity + Engagement + Uniqueness (max 15)

Hard rules:

Only visuals scoring 10+ make the shortlist
Maximum 5 visuals per newsletter issue (fewer is often better)
At least one visual in the first half of the newsletter
Never add a visual within 150 words of another (visual fatigue)
Visuals scoring below 8 are never included

通读完整草稿，记录每个章节的情况。针对每个章节，评估以下几点：

现有视觉元素——是否已包含
```
[screenshot]
```
占位符、代码块、表格或其他视觉元素？记录其覆盖内容及是否足够。
内容复杂度——该概念仅用文字是否难以解释？（如流程、架构、对比、数据）
吸引力风险——读者是否可能在此处失去兴趣？（如大段纯文字、密集的技术说明）
说服机会——视觉元素是否能让某个观点更可信？（如成本数据、性能对比、前后对比场景）

现有
[screenshot]
占位符：这些代表作者将提供的真实UI截图，视为已存在的视觉元素。仅当图表或插图能更好地呈现概念时，才建议替换，并需向用户明确说明理由。

Step 3: Select Visual Types

步骤2：对机会打分排序

Choose the type based on what the visual needs to accomplish:

Visual Type	Use When	Examples
Conceptual diagram	Explaining a process, architecture, or flow	Flowcharts, swimlane diagrams, network diagrams
Comparison visual	Showing differences between two or more things	Side-by-side layouts, before/after
Data visualization	Making numbers or ratios tangible	Bar charts, token cost comparisons
Custom illustration	Engaging the reader emotionally or setting context	Hero images, conceptual metaphors
Annotated screenshot	Adding context to an existing UI capture	Callout boxes, arrows, numbered annotations

Never use illustrations when a diagram would be more informative. Illustrations are for engagement; diagrams are for clarity. When in doubt, choose the one that teaches.

针对每个潜在的视觉优化机会，从三个维度打分（1-5分）：

维度	1分（低）	5分（高）
清晰度提升	文字已能清晰解释	仅用文字会令人困惑或需要反复阅读
吸引力提升	章节本身已具吸引力	大段纯文字，读者可能快速略过
独特性	通用/装饰性视觉元素	视觉元素能呈现文字无法传达的结构或数据

总分 = 清晰度 + 吸引力 + 独特性（最高15分）

硬性规则：

仅总分≥10分的视觉元素进入候选名单
每期新闻通讯最多包含5个视觉元素（越少往往效果越好）
新闻通讯前半部分至少包含一个视觉元素
任意两个视觉元素之间的文字内容不得少于150字（避免视觉疲劳）
总分低于8分的视觉元素绝不采用

Step 4: Present the Visual Brief

步骤3：选择视觉类型

Before generating anything, present the brief to the user for approval:

For each recommended visual:

Location — Exact section and paragraph
Type — Which visual type
Purpose — What it clarifies, persuades, or engages (one sentence)
Description — What the visual shows (the concept, not the generation prompt)
Score — The three dimension scores and total

Also include:

Sections where you did NOT recommend visuals and why
Any
```
[screenshot]
```
placeholders you recommend replacing (with justification)

Do NOT generate prompts or images until the user approves the brief.

根据视觉元素的目标选择合适的类型：

视觉类型	适用场景	示例
概念图	解释流程、架构或逻辑	流程图、泳道图、网络图
对比视觉	展示两个或多个事物的差异	并排布局、前后对比
数据可视化	让数字或比例更直观	柱状图、代币成本对比图
定制插图	从情感上吸引读者或设定场景	首图、概念隐喻图
带注释的截图	为现有UI截图添加上下文	标注框、箭头、编号注释

当图表更具信息性时，绝不要使用插图。插图用于提升吸引力，图表用于提升清晰度。如有疑问，选择能传递知识的类型。

Step 5: Generate Visual Assets

步骤4：提交视觉方案简报

After approval, generate each visual using

art:nanobanana

Design system integration: Load the design system from

~/.claude/.context/design-systems/

and apply it to every prompt — colors, typography, illustration style, brand constraints.

Prompt construction:

[SUBJECT]: What the visual depicts
[COMPOSITION]: Layout, arrangement, spatial relationships
[STYLE]: From the design system — colors, typography, illustration style
[CONSTRAINTS]: What to avoid, what NOT to include
[FORMAT]: Aspect ratio and resolution (from substack-constraints reference)

Prompt rules:

Be specific about spatial relationships ("left side shows X, right side shows Y")
Include exact hex colors from the design system
Specify "no text" or exact text to render (minimize text — AI text rendering is unreliable)
Always include the style from your design system — never leave style ambiguous
Never fabricate data that isn't in the source draft

在生成任何内容之前，需将视觉方案简报提交给用户审批：

针对每个推荐的视觉元素：

位置——具体章节和段落
类型——所选的视觉类型
目的——该元素将提升清晰度、增强说服力或提高吸引力的具体说明（一句话）
描述——视觉元素展示的内容（概念，而非生成提示词）
得分——三个维度的得分及总分

还需包含：

未推荐视觉元素的章节及原因
建议替换的
```
[screenshot]
```
占位符及理由

在用户批准简报之前，不得生成提示词或图片。

Step 6: Write Captions and Alt Text

步骤5：生成视觉资产

For each generated visual:

Caption — 1 sentence that adds context the image doesn't show. Good captions answer "so what?" — they don't just describe what's visible.
Alt text — Descriptive text for accessibility. Convey informational content, not visual style. ("Bar chart showing agent teams use 7x more tokens than single agents" not "blue and orange bar chart")

获得批准后，使用

art:nanobanana

生成每个视觉元素。

设计系统集成：从

~/.claude/.context/design-systems/

加载设计系统，并将其应用于每个提示词——包括颜色、排版、插图风格、品牌约束。

提示词结构：

[SUBJECT]: 视觉元素的主题
[COMPOSITION]: 布局、排列、空间关系
[STYLE]: 来自设计系统——颜色、排版、插图风格
[CONSTRAINTS]: 需避免的内容
[FORMAT]: 宽高比和分辨率（来自substack-constraints参考文件）

提示词规则：

明确说明空间关系（如「左侧展示X，右侧展示Y」）
包含设计系统中的精确十六进制颜色值
指定「无文字」或需呈现的精确文字（尽量减少文字——AI文字渲染不可靠）
始终包含设计系统的风格——绝不要让风格模糊
绝不编造原始草稿中不存在的数据

Step 7: Verify Against Checklist

步骤6：编写说明文字和替代文本

Run the quality checklist before presenting final assets.

针对每个生成的视觉元素：

说明文字——一句话，补充图片未展示的上下文。优秀的说明文字应回答「这有什么意义？」——而非仅描述可见内容。
替代文本——为无障碍设计的描述性文字。传递信息内容，而非视觉风格。（如「柱状图显示Agent团队的代币使用量是单个Agent的7倍」，而非「蓝橙配色的柱状图」）

Voice Application

步骤7：对照检查清单验证

ALWAYS invoke

writing:voice

before finalizing any written output (captions). Voice is applied after the structural draft is complete but before brand compliance.

Invocation point: After writing captions and alt text, before presenting to the user.

在提交最终资产之前，运行质量检查清单。

Brand Compliance

语气应用

When creating assets for The AI Launchpad, invoke

branding-kit:brand-guidelines

to resolve the correct design system and check anti-patterns.

Invocation point: After voice application, as the final quality gate.

在完成任何书面输出（说明文字）之前，必须调用

writing:voice

。语气调整应在结构草稿完成后、品牌合规检查前进行。

调用时机：编写完说明文字和替代文本后，提交给用户之前。

Quality Checklist

品牌合规

Design system loaded before any generation
Every visual scores 10+ on the clarity/engagement/uniqueness scale
Maximum 5 visuals in the brief
At least one visual in the first half of the newsletter
No two visuals within 150 words of each other
Brief presented and approved before generation
Every prompt includes design system colors and style
No fabricated data in any visual
Captions answer "so what?" (not just describe the image)
Alt text conveys information, not visual style
```
writing:voice
```
invoked for captions
```
branding-kit:brand-guidelines
```
invoked for brand compliance

为The AI Launchpad创建资产时，调用

branding-kit:brand-guidelines

以获取正确的设计系统并检查反模式。

调用时机：语气调整完成后，作为最终的质量把关步骤。

Common Pitfalls

质量检查清单

Too many visuals (6+): Cap at 5. Force-rank by score. Fewer high-impact visuals beat many mediocre ones.
Decorative hero image: Only include a hero if it scores 10+. Most newsletters don't need one.
Inventing data: Only visualize data the author provides. Never fabricate statistics.
Replacing screenshots without asking: Screenshots are the author's real evidence. Only suggest replacing with explicit justification.
Ignoring the design system: Every prompt must reference the design system. No making up colors or styles.
Dark-themed images for email: Default to light backgrounds. Dark images look broken in most email clients.
Text-heavy images: Minimize text in generated images. Put text in captions instead.
Generating before brief approval: Always present the brief first. Wasted assets cost time and API credits.
Using illustrations where diagrams belong: If the goal is clarity, use a diagram. Illustrations are for engagement.

生成前已加载设计系统
每个视觉元素的清晰度/吸引力/独特性总分≥10分
简报中最多包含5个视觉元素
新闻通讯前半部分至少包含一个视觉元素
任意两个视觉元素之间的文字内容不少于150字
生成前已提交简报并获得批准
每个提示词都包含设计系统的颜色和风格
任何视觉元素中均无编造的数据
说明文字回答「这有什么意义？」（而非仅描述图片）
替代文本传递信息，而非视觉风格
已为说明文字调用
```
writing:voice
```
已调用
```
branding-kit:brand-guidelines
```
进行品牌合规检查

—

常见误区

—

视觉元素过多（6个及以上）：最多保留5个，按得分强制排序。少量高影响力的视觉元素优于多个平庸的元素。
装饰性首图：仅当首图得分≥10分时才使用。大多数新闻通讯不需要首图。
编造数据：仅可视化作者提供的数据。绝不编造统计信息。
未征求同意就替换截图：截图是作者的真实证据。仅在有明确理由时建议替换。
忽略设计系统：每个提示词必须参考设计系统。不得自行设定颜色或风格。
邮件使用深色主题图片：默认使用浅色背景。深色图片在大多数邮件客户端中显示效果不佳。
文字密集的图片：尽量减少生成图片中的文字。将文字放在说明文字中。
未获简报批准就生成：始终先提交简报。无效的资产会浪费时间和API额度。
用插图替代图表：如果目标是提升清晰度，请使用图表。插图仅用于提升吸引力。