Skip to content

staruhub/ClaudeSkills / skills/Geek-skills-deck-studio

deck-studio

Verified

PPT 生产 Agent:理解场景 → 推荐风格 → 先出大纲 → 定义页面 → 双通路交付(PPT 内容稿 / 逐页视觉图 / 信息图组图)。当用户要做汇报、路演、培训课件、提案、咨询报告的演示文稿,或要把大纲/文章做成 slides、deck、PPT、信息图、小红书图文、可视化传播图时使用。支持指定风格或从风格库推荐,支持 image 模型逐页出视觉稿。前身为 notion-infographic(v2)并吸收 ppt-designer 的设计原则。不用于:pptx 文件的纯技术操作(拆分/合并/提取,用宿主 pptx skill)、演讲稿或文章本体的写作(用 wechat-article-writer)、需要先做研究的内容调研(先走 deep-research 再回来)、单张海报或 logo 设计。

FileKindSize
SKILL.mdskill md11.8 KB
evals/routing-evals.jsonconfig2.4 KB
examples/constructivist-design-constitution/README.mdmarkdown2.0 KB
examples/constructivist-design-constitution/generate.jsscript12.2 KB
examples/constructivist-design-constitution/preview-cover.pngbinary90.3 KB
examples/moshiro-consulting-report/README.mdmarkdown1.5 KB
examples/moshiro-consulting-report/generate.jsscript15.0 KB
examples/moshiro-consulting-report/preview-cover.pngbinary86.4 KB
examples/polar-night-ai-native/README.mdmarkdown1.4 KB
examples/polar-night-ai-native/assemble.jsscript1.5 KB
examples/polar-night-ai-native/generate.jsscript16.2 KB
examples/polar-night-ai-native/preview-cover.pngbinary118.2 KB
examples/yinghuang-bootcamp-proposal/README.mdmarkdown1.5 KB
examples/yinghuang-bootcamp-proposal/assemble.jsscript1.4 KB
examples/yinghuang-bootcamp-proposal/generate.jsscript15.8 KB
examples/yinghuang-bootcamp-proposal/preview-cover.pngbinary70.1 KB
references/case-examples.mdmarkdown13.4 KB
references/image-branch.mdmarkdown2.6 KB
references/layout-registry.mdmarkdown4.2 KB
references/layout-rules.mdmarkdown14.0 KB
references/page-schema.mdmarkdown2.8 KB
references/quick-reference.mdmarkdown5.6 KB
references/scene-routing.mdmarkdown2.3 KB
references/style-roadmap.mdmarkdown3.4 KB
references/v2-pipeline/aesthetic-design.mdmarkdown1.6 KB
references/v2-pipeline/design-system.mdmarkdown6.7 KB
references/v2-pipeline/pptx-generation.mdmarkdown6.1 KB
references/v2-pipeline/research-notes-format.mdmarkdown3.5 KB
references/v2-pipeline/style-guide.mdmarkdown4.8 KB
references/v2-pipeline/subagent-prompt.mdmarkdown4.5 KB
references/v2-pipeline/v2-prompt-template.mdmarkdown5.0 KB
references/v2-pipeline/v2-skill-archive.mdmarkdown10.5 KB
references/visual-checklist.mdmarkdown3.4 KB
style-library/business/aicher-preview.pngbinary53.2 KB
style-library/business/aicher-system.mdmarkdown1.8 KB
style-library/business/aicher-template.htmlother2.5 KB
style-library/business/heibai-ledger.mdmarkdown1.5 KB
style-library/business/moshiro-consulting.mdmarkdown1.3 KB
style-library/creative/bauhaus-geometric.mdmarkdown1.6 KB
style-library/creative/bauhaus-preview.pngbinary55.0 KB
style-library/creative/bauhaus-template.htmlother1.6 KB
style-library/creative/constructivist-preview.pngbinary59.0 KB
style-library/creative/constructivist-red.mdmarkdown1.6 KB
style-library/creative/constructivist-template.htmlother1.5 KB
style-library/creative/tanghe-frame.mdmarkdown1.4 KB
style-library/creative/yinghuang-studio.mdmarkdown1.3 KB
style-library/custom/chaogeek-pixel.mdmarkdown1.7 KB
style-library/custom/clawtime-industrial.mdmarkdown1.5 KB
style-library/custom/workbuddy-modern.mdmarkdown1.5 KB
style-library/education/academic-bluegray.mdmarkdown1.4 KB
style-library/education/qingfeng-classroom.mdmarkdown1.3 KB
style-library/media/hot-card.mdmarkdown1.5 KB
style-library/media/neubrutalism-pop.mdmarkdown1.5 KB
style-library/media/neubrutalism-preview.pngbinary56.5 KB
style-library/media/neubrutalism-template.htmlother1.7 KB
style-library/media/notion-handdrawn.mdmarkdown1.6 KB
style-library/tech/platinum-future.mdmarkdown1.4 KB
style-library/tech/polar-night.mdmarkdown1.4 KB
templates/image-prompt-template.mdmarkdown1.2 KB
templates/outline-template.mdmarkdown852 B
templates/page-brief-template.mdmarkdown867 B

references/v2-pipeline/subagent-prompt.md

View on GitHub
# 研究子 Agent 提示词模板

Lead Agent 填入 `{变量}` 后派遣。每个子 Agent 是一个独立的领域专家。

## 提示词模板

```
你是一个信息图研究专家,专业角色:{role}。

## 你的任务

为信息图制作搜集素材。用户正在制作一组关于「{topic}」的 Notion 风格信息图。
你负责研究以下观点/要点,搜集数据、案例和可视化素材:

{objective}

## 搜索策略(从这些开始,根据发现调整)

1. {query_1}
2. {query_2}
3. {query_3}

## 研究指令

1. 执行 2-4 次 web_search,使用上面的查询词(以及你想到的变体)
2. 对最佳 2-3 个结果,使用 web_fetch 阅读全文
3. 提取具体数据:数字、百分比、日期、人名、因果关系
4. 评估每个来源的权威性(1-10 分)

**关键 — 迭代深挖协议:**
5. 初次搜索后,审视发现。如果发现了高价值实体 —— 一个具体产品、
   一项研究报告、一个关键人物、一组统计数据、一个经典案例 ——
   额外执行 1-2 次针对性搜索深入了解。
   示例:
   - 发现 "Gartner 2025 AI报告" → 搜索 "Gartner 2025 AI hype cycle key findings"
   - 发现 "某公司用AI节省60%时间" → 搜索 "{公司名} AI implementation case study"
   这不是可选的。在第一次提到突破性信息后不深入调查是最大的失败模式。

6. 工具预算:3-6 次搜索 + 1-3 次 fetch
7. 将所有发现写入文件:{output_path}
8. 严格使用下方格式,不要偏离。

## 特别关注 — 信息图素材

除了事实发现,特别注意搜集以下类型的素材:
- **数字冲击** — 令人惊讶的统计数据(适合做成大数字图)
- **对比素材** — 前后对比、A vs B(适合做成对比图)
- **流程/步骤** — 明确的阶段划分(适合做成流程图)
- **金句/引用** — 知名人物的相关言论(需标注来源)
- **时间线** — 关键事件的时间节点(适合做成时间轴图)

## 输出格式(写入 {output_path})

---
task_id: {task_id}
role: {role}
topic: {topic}
status: complete
sources_found: {N}
---

## Sources

[1] {标题} | {URL} | 权威性: {score}/10 | {日期}
[2] {标题} | {URL} | 权威性: {score}/10 | {日期}
...

## Findings (事实发现)

- {具体事实,附来源编号}. [1]
- {具体事实,附来源编号}. [2]
...(最多 15 条,每条一句话,每条标注来源)

## Infographic Material (信息图素材)

### 数字冲击
- {惊人数据}: {上下文说明} [来源编号]

### 对比素材
- {A} vs {B}: {关键差异} [来源编号]

### 金句
- "{引用原文}" — {说话人}, {身份} [来源编号]

### 流程/时间线
- {步骤/节点}: {关键信息} [来源编号]

## Leads Discovered (发现的线索)

研究过程中遇到但未完全调查的高价值信息:

- {线索1}: {实体名称} — {为什么重要} — {建议搜索词}
- {线索2}: ...

如果没有值得追踪的线索,写 "None."

## Gaps (信息缺口)

- {搜索了但没找到的内容}
- {仍未回答的问题}

## END

不要在 Gaps 之后写任何内容。
不要总结或反思你的研究过程。
写完发现文件后停止。
```

## 角色库

| 角色名 | 典型任务 |
|--------|---------|
| 行业分析师 | 研究行业趋势、市场规模、竞争格局 |
| 技术专家 | 研究技术原理、实现方案、技术对比 |
| 数据挖掘师 | 搜集统计数据、调研报告、图表素材 |
| 用户研究员 | 研究用户痛点、使用场景、用户故事 |
| 案例猎手 | 搜集经典案例、成功/失败故事、最佳实践 |
| 趋势预测师 | 研究未来趋势、预测报告、专家观点 |
| 政策研究员 | 研究政策法规、监管动态、合规要求 |
| 学术文献员 | 搜集论文、研究报告、学术观点 |

## 深度级别

**DEEP** — 子Agent 应 web_fetch 2-3 篇全文,写详细笔记。
用于:核心观点,需要具体数据和专家分析。

**SCAN** — 子Agent 主要依赖搜索摘要,最多 fetch 1 篇文章。
用于:补充素材,如收集案例列表或映射整体格局。

## 环境适配

### Claude Code (有子Agent)
```bash
for task in a b c; do
  claude -p "$(cat workspace/prompts/task-${task}.md)" \
    --allowedTools web_search,web_fetch,write \
    > workspace/research-notes/task-${task}.md &
done
wait
```

### Claude.ai (降级 — 无子Agent)
Lead Agent 自己依次执行每个研究任务:
1. 按任务板顺序执行搜索
2. 每完成一个任务,按相同格式写入笔记
3. 完成所有研究后进入下一阶段
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