markdown-to-storyboard

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Markdown to Storyboard

Markdown 转故事板

Convert any markdown text into a structured storyboard CSV — the universal handoff format for downstream tools (slide builders, video editors, image generators).

将任意Markdown文本转换为结构化的故事板CSV文件——这是下游工具（幻灯片制作器、视频编辑器、图像生成器）通用的交付格式。

Workflow

工作流程

1. Analyze the Source Markdown

1. 分析源Markdown内容

Read the markdown and identify:

Title and subtitle
Section headings (H2/H3) → natural slide boundaries
Key arguments / data points / quotes per section
Narrative arc: setup → development → climax → conclusion

读取Markdown内容并识别：

标题和副标题
章节标题（H2/H3）→ 自然的幻灯片分界点
每个章节的核心论点/数据点/引用内容
叙事结构：开场→展开→高潮→结尾

2. Ask User Preferences

2. 询问用户偏好

Prompt for (defaults in parentheses):

Slide count (auto: 8–15 based on content length, ~1 slide per 150–300 words)
Audience (general)
Tone (professional)
Language (same as source)

If user declines to specify, use defaults and proceed.

提示用户确认（括号内为默认值）：

幻灯片数量（自动：根据内容长度生成8–15张，每150–300字对应约1张幻灯片）
受众（普通大众）
语气（专业正式）
语言（与源内容一致）

如果用户不愿指定，使用默认值继续执行。

3. Assign Slide Types and Layouts

3. 分配幻灯片类型与布局

Available

slide_type

values:

Type	Purpose	Typical layout
`cover`	Opening slide	`full_bg`
`toc`	Table of contents (optional, 12+ slides)	`center_text`
`section`	Chapter divider	`center_text`
`content`	Core information	`left_img_right_text` or `top_img_bottom_text`
`quote`	Key quote or statistic	`full_bg`
`data`	Chart / number-driven	`two_column`
`summary`	Closing recap	`center_text` or `left_img_right_text`
`end`	Thank-you / Q&A / CTA	`full_bg`

Available

layout

values:

full_bg

left_img_right_text

top_img_bottom_text

center_text

two_column

可用的

slide_type

值：

类型	用途	典型布局
`cover`	开场幻灯片	`full_bg`
`toc`	目录（可选，幻灯片数量≥12时使用）	`center_text`
`section`	章节分隔页	`center_text`
`content`	核心信息页	`left_img_right_text` 或 `top_img_bottom_text`
`quote`	关键引用或统计数据页	`full_bg`
`data`	图表/数据驱动页	`two_column`
`summary`	结尾总结页	`center_text` 或 `left_img_right_text`
`end`	致谢/问答/行动号召页	`full_bg`

可用的

layout

值：

full_bg

left_img_right_text

top_img_bottom_text

center_text

two_column

4. Write the Image Prompt for Each Slide

4. 为每张幻灯片撰写图像提示词

For each slide, write an

image_prompt

(English, regardless of content language) that:

Describes a concrete scene, not an abstract concept
Includes a style keyword consistent across all slides (e.g. "flat vector illustration, soft pastel palette")
Specifies composition hints matching the layout (e.g. "wide shot, negative space on the right" for
```
left_img_right_text
```
)
Cover and end slides get more dramatic / visually impactful prompts

为每张幻灯片撰写

image_prompt

（无论源内容语言如何，均使用英文），要求：

描述具体场景，而非抽象概念
包含一个在所有幻灯片中保持一致的风格关键词（例如："flat vector illustration, soft pastel palette"）
指定与布局匹配的构图提示（例如：对于
```
left_img_right_text
```
布局，使用"wide shot, negative space on the right"）
开场页和结束页使用更具视觉冲击力的提示词

5. Draft Speaker Notes

5. 撰写演讲者备注

speaker_notes

column: 1–3 sentences of what the presenter would say. Leave empty if not requested.

speaker_notes

列：1–3句话的演讲者台词。如果未被请求则留空。

6. Output the CSV

6. 输出CSV文件

Write the storyboard to

storyboard.csv

using

execute_code

python

import csv

rows = [
    # [slide_no, slide_type, title, bullet_points, image_prompt, speaker_notes, layout]
]

header = ["slide_no", "slide_type", "title", "bullet_points", "image_prompt", "speaker_notes", "layout"]

with open("storyboard.csv", "w", newline="", encoding="utf-8") as f:
    writer = csv.writer(f)
    writer.writerow(header)
    writer.writerows(rows)

Column spec:

Column	Type	Description
`slide_no`	int	1-indexed
`slide_type`	str	One of the types above
`title`	str	Slide headline, ≤ 10 words
`bullet_points`	str	Newline-separated ( `\n` ). Each ≤ 20 chars. Max 5 items
`image_prompt`	str	English prompt for image generation
`speaker_notes`	str	Optional presenter notes
`layout`	str	One of the layouts above

使用

execute_code

将故事板写入

storyboard.csv

：

python

import csv

rows = [
    # [slide_no, slide_type, title, bullet_points, image_prompt, speaker_notes, layout]
]

header = ["slide_no", "slide_type", "title", "bullet_points", "image_prompt", "speaker_notes", "layout"]

with open("storyboard.csv", "w", newline="", encoding="utf-8") as f:
    writer = csv.writer(f)
    writer.writerow(header)
    writer.writerows(rows)

列规范：

列名	类型	描述
`slide_no`	整数	从1开始编号
`slide_type`	字符串	上述类型之一
`title`	字符串	幻灯片标题，≤10个单词
`bullet_points`	字符串	换行分隔（ `\n` ）。每条≤20字符。最多5条
`image_prompt`	字符串	用于图像生成的英文提示词
`speaker_notes`	字符串	可选的演讲者备注
`layout`	字符串	上述布局之一

7. Present for Review

7. 呈现供审核

Display the storyboard as a markdown table for the user to review. Wait for confirmation before the next pipeline step. If changes requested, update

storyboard.csv

and re-display.

将故事板以Markdown表格形式展示给用户审核。等待用户确认后再进行下一流程步骤。如果用户要求修改，更新

storyboard.csv

并重新展示。

Pacing Guidelines

节奏指南

Opening (slides 1–2): Hook — cover + bold opening statement or question
Body (slides 3 to N-2): One idea per slide. Alternate
```
content
```
and
```
quote
```
/
```
data
```
to vary rhythm
Closing (slides N-1 to N): Summary of key takeaways + end slide
Avoid consecutive slides of the same type. Insert a
```
section
```
divider between major parts.

开场（幻灯片1–2）：吸引注意力——封面页+醒目的开场陈述或问题
主体（幻灯片3至N-2）：每张幻灯片一个核心观点。交替使用
```
content
```
和
```
quote
```
/
```
data
```
类型以调整节奏
结尾（幻灯片N-1至N）：核心要点总结+结束页
避免连续使用同一类型的幻灯片。在主要部分之间插入
```
section
```
分隔页。

Text Density Rules

文本密度规则

Title: imperative or question form, ≤ 10 words
Bullets: ≤ 5 per slide, each ≤ 20 characters (CJK) / ≤ 12 words (Latin)
Prefer fragments over full sentences
Numbers stand alone: "3x faster" not "It is three times faster"

标题：使用祈使句或疑问句形式，≤10个单词
项目符号：每张幻灯片≤5条，每条≤20个字符（中文）/ ≤12个单词（拉丁文）
优先使用短语而非完整句子
数字单独呈现：例如用"3x faster"而非"It is three times faster"