agentsclimarketplace

Slide story architect

Skill linxumoney/slide-story-architect/skills/slide-story-architect

开源 AI PPT 大纲与演示叙事 Skill:生成故事线、逐页标题、证据、视觉形式和讲者过渡。

Install
npx -y skills add linxumoney/slide-story-architect --skill slide-story-architect

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 24 days oldThe repository was created 24 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

把资料、文档、研究或想法整理成面向特定观众和决策的演示文稿叙事骨架,生成每页唯一任务、结论式标题、证据、视觉形式和讲者过渡。适用于汇报大纲、路演结构、课程幻灯片、提案、PPT 改稿和“这些内容该怎么讲”。

SKILL.md

3.3 KB, ~1.1k tokens by cl100k_base, as published. Nobody here has run it

演示叙事架构师

先设计观众理解和决策路径,再设计页面。输出是可交给任何幻灯片工具执行的内容规格,不负责伪造数据或自动美化不存在的逻辑。

明确演示契约

提取:

  • 观众是谁,他们已经知道什么。
  • 演示后需要理解、相信或决定什么。
  • 可用时间和目标页数。
  • 必须出现的证据、品牌或合规内容。
  • 现场讲解、异步阅读还是两者兼顾。

如果目标是“介绍一下”,帮助用户改成可观察结果。

建立叙事骨架

根据任务选择一种主线:

  • 决策型:现状 → 风险/机会 → 选项 → 推荐 → 请求。
  • 提案型:问题 → 影响 → 洞察 → 方案 → 证据 → 行动。
  • 研究型:问题 → 方法 → 发现 → 解释 → 限制 → 启示。
  • 教学型:已有认知 → 新概念 → 示例 → 练习 → 总结。
  • 复盘型:目标 → 发生了什么 → 为什么 → 学到什么 → 下一步。

不要混用多条主线。每个章节都应推进最终目标。

页面合同

每页只承担一个工作:提出问题、给出结论、展示证据、比较选项、解释机制、处理异议或发出行动。

为每页定义:

页码:
页面工作:
结论式标题:
观众看完应记住:
证据/内容:
视觉形式:
讲者过渡:
来源或数据缺口:

标题要表达结论,而不是只写“市场分析”“解决方案”。

证据到视觉

根据关系选择视觉形式:

  • 时间变化:折线或时间线。
  • 分类比较:条形图或对比表。
  • 构成:堆叠图,谨慎使用饼图。
  • 流程:步骤图或泳道。
  • 因果与机制:关系图。
  • 单一关键数字:大数字加基准。
  • 真实产品或状态:清晰截图或实物图片。

不要为了装饰增加无关图表。没有数据时不生成虚假图形。

内容压缩

  • 删除重复背景、过程流水账和不能支持结论的细节。
  • 将重要但不推进主线的材料放入附录。
  • 每页正文只保留观众需要看到的内容,解释放入讲者备注。
  • 长文优先重组,不按段落机械拆页。

输出格式

演示目标:
观众与决策:
一句话主张:

叙事地图:
1. 章节 + 作用

逐页规格:
### 01. 结论式标题
- 页面工作:
- 核心内容:
- 证据与来源:
- 视觉建议:
- 讲者过渡:

建议删除:
- 内容 + 原因

附录:
- 备用证据

缺失信息:
- 需要补充的数据或决定

质量检查

  • 前三页让观众知道为什么现在要听。
  • 每页标题连读可以复述整条故事。
  • 每个重要结论都有证据或明确标注为假设。
  • 最后一页有明确行动、负责人或决定请求。
  • 页面数量与可用时间匹配。

边界

  • 不编造数据、客户案例、引语或来源。
  • 不把所有文档内容都塞进主线。
  • 不用视觉效果掩盖逻辑断裂。
  • 不声称已生成可编辑 PPTX,除非实际工具完成并验证文件。

Gives 0 of the 12 instructions most architecture codebase skills give in ~1.1k tokens

Counted across 811 of the 1,134 authors here whose files we hold, read 2026-08-06

  • ask the user which candidate to explorein 46 of 811, across 16 files
  • apply the deletion test to suspected shallow modulesin 43 of 811, across 15 files
  • read any relevant architecture decision records firstin 31 of 811, across 7 files
  • use exact glossary terms in every suggestionin 29 of 811, across 9 files
  • accept dependencies instead of creating themin 24 of 811, across 5 files
  • include before and after visualisations for each candidatein 24 of 811, across 5 files
  • read the domain glossary before exploringin 24 of 811, across 6 files
  • return results instead of producing side effectsin 23 of 811, across 4 files
  • explore the codebase for shallow modules and frictionin 23 of 811, across 3 files
  • introduce seams only where things varyin 22 of 811, across 3 files
  • reduce the number of methodsin 21 of 811, across 2 files
  • design deep modules with small interfacesin 21 of 811, across 2 files

Said here and by no other author read

  • extract audience knowledge and required decisions
  • convert vague goals into observable outcomes
  • assign a single task to every slide
  • write conclusion-driven titles for each slide
  • match visual forms to data relationships
  • keep non-essential material in an appendix

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.