Skip to content

JimLiu/baocut / skills/baocut/built-in-skills/design

design

Verified

用户要做界面、网页、海报、图表或信息图、示意图、原型这类视觉设计稿时用:在工作目录写一份设计稿(canvas.json 加每块画板一个 .dc.html),校验通过后线程里出现设计稿卡片,用户在功能区预览、编辑与标注。也用于按用户的意见或设计稿标注改已有的设计稿。幻灯片不用它(用 slides),视频画面里的字卡与动效也不用它(用动效图形)。

FileKindSize
.baocut-meta.jsonconfig1.8 KB
SKILL.mdskill md17.5 KB
references/brand-colors.mdmarkdown2.2 KB
references/brand-typography.mdmarkdown1.5 KB
references/craft.mdmarkdown15.3 KB
references/design-system-components.mdmarkdown11.5 KB
references/diagrams.mdmarkdown9.9 KB
references/format.mdmarkdown11.6 KB
references/print.mdmarkdown5.5 KB
references/questions.mdmarkdown4.6 KB
references/view-state.mdmarkdown5.4 KB

references/questions.md

View on GitHub
# 动手前先问

<!-- Generated from skills/_shared/ask-first.md by
scripts/inline-shared.ts — edit the fragment, never this block. -->

<!-- shared:ask-first -->
只在有人能回答时才问。BaoCut 没有提问卡片(`AskUserQuestion` 调用会被拒绝):把问题以纯文本写在回复里,列出选项,用用户的语言,然后结束这一轮;否则(headless 运行、调用方是 agent、「直接做吧」)照 SKILL.md 说的做:自己决定、动手做,并用一行说明你的假设。

先读用户给你的材料。仍有两个或更多会改变结果的决定没定的 brief,值得在你第一次写入之前发**一条**消息,最多 4 个问题;只有一处你可以取默认值的、brief 齐全的,或只是小修改的,一条都不发。

问题从用户的材料里来,不从表单里来:点出你读到了什么(「你的笔记讲了四件事」)、其中的矛盾或缺口,以及最能改变你要做的东西的那个决定,最关键的放最前面:只有读过他们 brief 的人才问得出的问题。绝不问对话里已经回答过的;场景已经隐含的就取默认值并说出来;套话式的需求收集问题(受众?篇幅?做界面还是原型?)只用于确实空白的 brief。

选项才是真功夫:为**这一份**作品给出 2–4 个具体方向(「先讲重组」,而不是「叙事」),每个在一条你说得出名字的维度上有区别,绝不是同一个想法的几种深浅;label 几个字,能承载这个选择;`description` 几个字,没增加信息就省掉;你的首选放第一个,标上「(Recommended)」,事实类问题不标。默认 `"multiSelect": true`,因为回答的人往往还在探索;只有选项互斥时(一种篇幅、一种格式)才用 `false`。不放「其他」或「你来定」这类选项(他们随时可以用自己的话回答),也不出只能用自由文本回答的问题。

把回答当作决定,并在你那一行假设里复述;他们留给你的,你来决定并说出你选了什么。只有在他们要求更多,或某个回答引出了你之前不可能问到的问题时,才再问一轮(最多 4 个新问题);否则就动手做。绝不重复问。
<!-- /shared:ask-first -->

## 设计稿要问的问题

问用户给你的页面、应用或 PRD 对**这份**设计还没定下的地方:这个界面能做好几件事时先做哪一件,谁会来到这个界面,他们产品里哪些要沿用、哪些要打破,画板之间的哪些差异能帮他们做选择。用户提了某个产品却什么都没附?去要(一个链接、一张截图),而不是闭着眼设计。没有要对齐的东西,也看不出想要什么风格?给出两三个具体方向,或者用 2–4 块低保真画板来问。做界面还是做原型:按信号定(见 SKILL.md);没有信号就选一个并说出来。

比如用户贴了他们应用的 Projects 页面链接(密集的 13px 表格,右上角一个「New project」按钮,隔两个标签页在 Settings 里有一个 Import from GitHub 流程),要「给还没有项目的团队做一个更好的 empty state」。一组合格的问题(这是它的内容;在 BaoCut 里你把它写成纯文本):

```json
{"questions": [
  {"question": "New project already sits top-right and Import from GitHub lives in Settings. What should the empty state push people toward?", "header": "Main path", "multiSelect": true, "options": [
    {"label": "Starter templates (Recommended)", "description": "Three cards fill the empty table"},
    {"label": "Import from GitHub", "description": "The Settings flow surfaces here"},
    {"label": "Invite teammates", "description": "An inline invite field"},
    {"label": "New project, centered", "description": "The existing button, moved center"}]},
  {"question": "The page is all-business (tight tables, no illustration anywhere in the app). What may the empty state add?", "header": "Feel", "multiSelect": true, "options": [
    {"label": "Stay in system (Recommended)", "description": "Your table's type, one line icon"},
    {"label": "One warm moment", "description": "A small illustration, only here"},
    {"label": "A sample row", "description": "A faint example project row"}]},
  {"question": "A new team hits two more empties right after this one (Members, API keys). Cover them so they read as a set?", "header": "Scope", "multiSelect": false, "options": [
    {"label": "Projects only (Recommended)", "description": "Three artboards of this screen"},
    {"label": "All three empties", "description": "One direction carried across them"}]}]}
```
canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall