Back to Details

moda-deck-theme

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

moda-deck-theme

moda-deck-theme

<!-- moda:banner -->
PREREQUISITE — load 
moda-core
once per session (step-0, write contract, free/metered map). Already loaded? Skip ahead. If you cannot load it, the non-negotiables: run 
moda doctor --json
before anything; 
moda brand list
before creating; every write carries the latest revision — on 
stale_revision
, re-read and retry once (it heals); send the canvas link the moment it exists; stuck or failed? 
moda ask "<question>"
— free and fast, never guess.
<!-- /moda:banner -->
<!-- moda:banner -->
前提条件——每个会话仅需加载一次
moda-core
（步骤0，撰写合同，免费/计量映射）。已加载？直接跳过。若无法加载，务必执行以下操作：先运行
moda doctor --json
；创建前执行
moda brand list
；每次写入操作需携带最新版本号——遇到
stale_revision
时，重新读取并重试一次即可解决；画布链接生成后立即发送；遇到问题或失败？使用
moda ask "<question>"
——免费且响应迅速，切勿自行猜测。
<!-- /moda:banner -->

What this is

这是什么

A wizard-style flow for establishing a deck's visual theme with the user before any real content exists. Runs on a blank 1920×1080 slides canvas with a brand kit applied, and ends with twelve placeholder slides that define a complete visual system. If the canvas already has designed slides, or the user wants specific content designed right now, say so and ask how they want to proceed.
Five phases, each gated on explicit approval. Do not generate the next phase without it — "what's next?" or "let's move on" is the gate. Anything the user said in their opening prompt supersedes the defaults below; acknowledge it so they know you read it.
Set up, then open by setting expectations in a sentence or two — four title directions, then section heads and a closing, then the workhorse layouts, pausing at each step, all content placeholder — and go straight into Phase 1:
  1. moda brand list
    , then 
    moda canvas create --name "[Deck] theme" --intent "a slide theme: 4 title directions, ceremonial slides, 8 workhorse layouts" --size 1920x1080 --pages 1 --category slides --brand [KIT]
    .
  2. moda canvas share CANVAS_REF
    — send the link at once: "follow along live here."
  3. LOOK at the kit's assets before designing anything (references/brand.md), and compute the type ladder from references/design-quality.md (1920×1080 → body ≈ 40px, floor 18px).
这是一个向导式流程，用于在实际内容创作前与用户共同确定演示文稿的视觉主题。在已应用品牌套件的空白1920×1080幻灯片画布上运行，最终生成12张占位符幻灯片，定义一套完整的视觉系统。如果画布已有设计好的幻灯片，或用户希望立即设计特定内容，请告知用户并询问后续处理方式。
流程分为五个阶段，每个阶段都需要明确审批才能进入下一环节。未获得审批前请勿生成下一阶段内容——用户说出“下一步？”或“继续吧”即为审批通过。用户初始提示中的任何要求都优先于以下默认规则，请确认用户的要求，让他们知道您已了解。
先完成设置，然后用一两句话说明预期流程：4种标题样式方向、章节标题与收尾页、实用布局，每一步都暂停等待确认，所有内容均为占位符——随后直接进入第一阶段：
  1. 执行
    moda brand list
    ，然后执行
    moda canvas create --name "[Deck] theme" --intent "a slide theme: 4 title directions, ceremonial slides, 8 workhorse layouts" --size 1920x1080 --pages 1 --category slides --brand [KIT]
    。
  2. 执行
    moda canvas share CANVAS_REF
    ——立即发送链接：“点击此处实时跟进”。
  3. 在开始设计前查看套件资产（参考references/brand.md），并根据references/design-quality.md计算字体层级（1920×1080画布→正文字体约40px，最小18px）。

Phase 1 — Title slide, 4 variants

第一阶段——标题幻灯片，4种变体

moda canvas add-pages CANVAS_REF --count 3
, then one 
moda canvas markup CANVAS_REF --file - --page P
per variant: four title slides, each a genuinely different aesthetic axis, all using the brand kit's real colors, type and logo (the variants explore design language, not brand attributes). Pick four from: type-led/anthemic · image-led · editorial · compositional/off-grid · minimalist/reductive · color-shock/block · maximalist/layered · geometric/constructivist · tactile/hand-made · technical/diagrammatic. With directional hints from the user, pick four that fit the direction; without hints, span clearly different territory — one type-driven, one image-driven, one color/composition-driven, one wildcard — and vary your picks across sessions.
Name each page with a letter and its approach ("A — Anthemic") so the user can reference them; page names are set in the edit lane (
update(pageId, { name: 'A — Anthemic' })
, references/edit-code.md). 
moda canvas screenshot CANVAS_REF
and LOOK before presenting. Present them as a choice, noting that only one moves forward and the other three get deleted, so this is the moment to choose.
  • Picks one → make any requested edits, then delete the other three (
    moda canvas delete-items CANVAS_REF [PAGE_IDS]
    ) before proceeding. The clean canvas signals the lock-in.
  • Wants a hybrid ("type from A, layout from C") → build a fifth variant, delete the rest.
  • None work → ask one question — which axis was wrong (typography, layout, color, imagery)? — then generate a fresh four from the remaining approaches. Never iterate on rejected variants.
Unsure which axes a second round should use? 
moda ask "which aesthetic axes should the second round of slide title variants use after the first four were rejected?"
.
执行
moda canvas add-pages CANVAS_REF --count 3
，然后为每个变体执行一次
moda canvas markup CANVAS_REF --file - --page P
：生成4张标题幻灯片，每张都采用截然不同的美学方向，全部使用品牌套件的真实色彩、字体和Logo（变体探索的是设计语言，而非品牌属性）。从以下类型中选择4种：字体主导/大气型 · 图片主导型 · 编辑排版型 · 构图/无网格型 · 极简/简约型 · 色彩冲击/色块型 · 极繁/分层型 · 几何/构成主义型 · 触感/手工风格 · 技术/图表型。根据用户的方向提示选择合适的4种；若无提示，则选择差异明显的类型——一种字体主导、一种图片主导、一种色彩/构图主导、一种 wildcard（ wildcard保留英文）——且每次会话的选择有所不同。
为每个页面命名，包含字母和对应的风格（如“A — Anthemic”），方便用户指代；页面名称在编辑栏设置（
update(pageId, { name: 'A — Anthemic' })
，参考references/edit-code.md）。执行
moda canvas screenshot CANVAS_REF
并查看后再展示给用户。将这些变体作为选项展示，说明仅会保留一种，其余三种将被删除，因此这是选择的关键节点。
  • 用户选中一种 → 根据要求进行编辑，然后删除另外三种（
    moda canvas delete-items CANVAS_REF [PAGE_IDS]
    ），再继续流程。整洁的画布表示已锁定选择。
  • 用户想要混合样式（如“A的字体，C的布局”）→ 生成第五种变体，删除其余所有变体。
  • 所有变体均不符合要求 → 询问一个问题——哪个方向有问题（字体、布局、色彩、图像）？——然后从剩余类型中重新生成4种变体。切勿在已被拒绝的变体上迭代。
不确定第二轮应使用哪些美学方向？执行
moda ask "which aesthetic axes should the second round of slide title variants use after the first four were rejected?"
。

Phase 2 — Ceremonial slides

第二阶段——仪式性幻灯片

moda canvas add-pages CANVAS_REF --count 3
— three slides that set the deck's emotional register, all visibly siblings of the title (same type pairings, color logic, grid):
  1. Section head, punchy — a moment. Large type, strong color, for major breaks.
  2. Section head, quiet — restrained, more whitespace, for subsections. The pair is what gives the deck rhythm instead of every break landing the same.
  3. Closing / thank you — mirrors the title's energy with a sense of arrival, often the title's composition with one clear shift (inverted color, mirrored alignment).
Screenshot all three, present them together, and iterate until approved.
执行
moda canvas add-pages CANVAS_REF --count 3
——生成3张幻灯片，奠定演示文稿的情感基调，所有幻灯片均与标题页风格统一（相同字体搭配、色彩逻辑、网格）：
  1. 章节标题页（醒目型）——突出重点。大字体、鲜明色彩，用于主要章节分隔。
  2. 章节标题页（简约型）——克制风格，留白更多，用于子章节。两种类型搭配可让演示文稿节奏更丰富，避免所有章节分隔都采用相同风格。
  3. 收尾/致谢页——呼应标题页的风格，同时传递完成感，通常采用标题页的构图，但有一处明显变化（如颜色反转、对齐方式镜像）。
截取三张幻灯片的截图，一起展示给用户，迭代修改直至获得审批。

Phase 3 — Theme contract

第三阶段——主题协议

Write the locked system out in plain prose to the user (not a slide, no approval needed — it's a status update): type scale (which font for display vs body, exact sizes, caps/weight rules), color roles (which brand color is background, accent, type, data emphasis), layout pattern (grid, alignment, margins, whether off-grid is in play), image treatment, and logo behavior. Close with: every workhorse slide will adhere to this — now's the moment to adjust. Without this contract Phase 4 drifts; it's the connective tissue and the thing specific feedback points back to.
用直白的文字向用户说明已锁定的系统（无需制作成幻灯片，也无需审批——这是状态更新）：字体层级（标题与正文字体、具体字号、大小写/字重规则）、色彩角色（品牌色分别用作背景色、强调色、字体色、数据突出色）、布局模式（网格、对齐方式、边距、是否采用无网格布局）、图像处理方式、Logo使用规范。结尾说明：所有实用幻灯片都将遵循此协议——现在是调整的最后时机。若无此协议，第四阶段的设计会偏离方向；它是各环节的连接纽带，也是具体反馈的参考依据。

Phase 4 — Workhorse slides

第四阶段——实用幻灯片

Eight layouts, generated 2–3 at a time with a feedback pause between batches so drift gets caught before it compounds: big number / stat hero · two-column comparison · quote / testimonial · 3-up grid · full-bleed image with caption · text-content slide · timeline / process flow · data slide. One 
moda canvas markup
apply per slide, 
moda canvas screenshot
after each batch, and LOOK. Every one must visibly inherit the theme contract; if a slide could belong to a different deck, redo it before moving on.
The text-content slide especially: do not default to bullet lists. Carry the 3–5 points with typographic hierarchy, color emphasis, or a numbered sequence.
生成8种布局，每次生成2-3种，每批生成后暂停等待反馈，避免偏差累积：大数字/数据亮点页 · 双栏对比页 · 引用/推荐语页 · 三列网格页 · 全屏图像带说明页 · 文本内容页 · 时间线/流程页 · 数据图表页。每张幻灯片执行一次
moda canvas markup
，每批生成后执行
moda canvas screenshot
并查看。所有幻灯片必须明显遵循主题协议；如果某张幻灯片看起来属于其他演示文稿，则需重新制作后再继续。
尤其注意文本内容页：请勿默认使用项目符号列表。通过字体层级、色彩强调或编号序列来呈现3-5个要点。

Phase 5 — Handoff

第五阶段——交付

Summarize the twelve slides — title, two section-head styles, closing, eight workhorse layouts — point back to the live link, and offer the two natural next moves: apply the theme to real content, or refine a specific slide. Export only on the user's format words or one accepted offer: 
moda export CANVAS_REF --format pptx|pdf -o …
.
总结12张幻灯片——标题页、两种章节标题样式、收尾页、8种实用布局——指向实时链接，并提供两个后续选项：将主题应用于实际内容，或优化特定幻灯片。仅在用户指定格式或接受选项时导出：
moda export CANVAS_REF --format pptx|pdf -o …
。

Throughout

全程注意事项

  • Placeholder content only. Never invent specific facts, real-sounding metrics, named people or company claims. "Section title here", "Key insight", "47%", "Discover / Build / Launch". Real-looking content invites the user to mistake it for a real claim.
  • One or two sentences of design rationale per phase ("all-caps because your display font has strong caps"). Enough to make feedback precise, not an explanation of the design.
  • Vague feedback gets exactly one question — which axis — then proceed.
  • Iterate refines the direction; pivot abandons it. On a pivot, don't anchor to the previous attempt.
  • A targeted fix to an approved slide is a small 
    moda canvas edit
    code batch (references/edit-code.md); a whole-slide rebuild is 
    moda canvas markup --mode replace
    .
  • 仅使用占位符内容。切勿编造具体事实、看似真实的数据、真实人名或公司声明。使用“此处为章节标题”“核心见解”“47%”“探索/构建/发布”等内容。看似真实的内容会让用户误以为是真实声明。
  • 每个阶段附上1-2句设计说明（如“全部使用大写是因为您的标题字体大写效果突出”）。只需足够让反馈精准，无需详细解释设计原理。
  • 模糊反馈仅需询问一个问题——哪个方向有问题——然后继续流程。
  • 迭代是优化方向；转向是放弃原有方向。若用户要求转向，请勿受之前尝试的影响。
  • 对已审批幻灯片的针对性修改只需执行一小段
    moda canvas edit
    代码（参考references/edit-code.md）；重新制作整张幻灯片则使用
    moda canvas markup --mode replace
    。

Errors

错误处理

invalid_markup
names the element it skipped — one page per apply, then re-run. 
stale_revision
heals: re-read and retry once. Anything else → load moda-core and read its recovery reference.
See also: moda-deck — the full deck build once a theme exists · moda-core — the contract, recovery, everything Moda can do.
invalid_markup
会说明跳过的元素——每次应用仅处理一个页面，然后重新运行。
stale_revision
可修复：重新读取并重试一次。其他错误→加载moda-core并查看其恢复参考文档。
另请参阅：moda-deck——主题确定后的完整演示文稿构建工具 · moda-core——包含合同、恢复功能等Moda的所有核心能力。

References

参考文档

DocLoad when
references/deck-design.mdbefore Phase 1 — concept-first covers, the layout bar
references/markup.mdbefore any markup apply
references/design-quality.mdthe type ladder, imagery, shaders, the AI-slop list
references/brand.mda kit is bound — look at its assets, not just its tokens
references/edit-code.mdpage names; targeted edits to an approved slide
文档加载时机
references/deck-design.md第一阶段前——概念优先封面、布局指南
references/markup.md任何标记应用前
references/design-quality.md字体层级、图像、着色器、AI劣质内容清单
references/brand.md绑定品牌套件后——查看其资产，而非仅查看标记
references/edit-code.md设置页面名称；对已审批幻灯片进行针对性修改