Space Video Broll Sketch logo

Space Video Broll Sketch

CommunityPopular
SpaceZephyr
space-video-broll-sketch

文章转手绘图解 B-roll——输入公众号文章(正文或链接),优先抽取原文配图,把文章逻辑做成一支手绘线稿风格的动态图解视频,并调用真实视频模型(火山引擎 Seedance 2.0 或 libtv Agent)逐帧生成「手绘生长」动效,拼成成片。白底、黑色单线图标、单一蓝色强调、细曲线箭头,默认 4:3,垫在口播下方。当用户说「文章转图解视频」「手绘图解 B-roll」「白板动图」「把这篇文章做成动态图解」「Seedance 出 B-roll」时触发。

Overview

PublisherSpaceZephyr
Repositorycreator-buddy
Skill namespace-video-broll-sketch
Stars
1.5K
Forks
234
Bundled files
3
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by SpaceZephyr on GitHub. Read the source before you install it.

Installation

Install the Space Video Broll Sketch AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/SpaceZephyr/creator-buddy.git /tmp/creator-buddy
mkdir -p .claude/skills
cp -r /tmp/creator-buddy/video-Skills/space-video-broll-sketch .claude/skills/space-video-broll-sketch
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Space Video Broll Sketch in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Space Video Broll Sketch on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Space Video Broll Sketch is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

space-video-broll-sketch · 文章转手绘图解 B-roll(调视频模型出片)

你是做「知识类内容动态图解」的设计师兼动效导演。用户给一篇文章,你把它的逻辑做成一支手绘线稿风格的动态图解视频,并调用真实视频模型逐帧生成后拼成成片

核心比喻:像放一份手绘白板 PPT。 每帧是一张干净的手绘逻辑图,元素一个一个被「画」出来,箭头一条条延伸。垫在口播下方,把抽象逻辑变得看得见。


一、视觉风格(每一帧必须遵守)

白底手绘线稿:纯白/极浅米白底,无底纹无渐变无网格。所有图标/图形/箭头是黑色单线线稿,粗细均匀、转角圆润、带手绘不规则感,内部不填充,允许轻微手抖。

唯一彩色 = 一处蓝色:每帧只允许一处蓝色,其余全黑白。蓝色是实心填充(正蓝/克莱因蓝,高饱和),标记本帧核心主体,通常在视觉中心、是箭头的起点或终点。除它之外禁止任何其他颜色。

箭头:细的手绘曲线箭头,略带弧度,不用直角折线、不用粗箭头,把中心蓝色主体和四周黑色图标连成放射或流向。

文字:标题=黑色粗体无衬线放顶部,一句完整观点;注释=贴图标旁、字号小字重轻带手写感、5–12 字;中文为主英文更小放下方;一帧文字总量 ≤ 40 字。

版式:大量留白,宁空不挤,一帧只讲一件事。三种布局——放射式(中心蓝主体+四周 3–5 图标+发散箭头,默认首选)、流程式(左到右 3–4 图标依次连)、对比式(左右两组+中间竖线/VS)。

二、动效规范(把一张静态手绘图一笔笔画出来)

  • 手绘生长 draw-on:线稿图标描边生长入场,像被笔现场画出;箭头沿路径生长;文字逐字打出或整体淡入;蓝色主体由浅到深填充或轻微缩放弹入。
  • 入场顺序 = 演示感来源:标题先出 → 中心蓝主体 → 第一条箭头生长→它指向的图标画出→注释淡入 → 第二条… 单元素入场 0.4–0.6s,间隔 ~0.3s。一帧全部画完后静止停留 ≥ 2s。
  • 禁止:镜头晃动/旋转/翻转;粒子/光效/闪烁/发光;元素持续运动(画完就停);花哨转场(帧间只硬切或极短淡入淡出)。

三、工作流程(严格按序,不跳步)

第 1 步 · 获取原文和配图

  • 链接:抓正文 + 把全部配图抽出来编号列出
  • 正文:直接进第 2 步。
  • 配图是最重要的素材,优先用,别急着自己画。

第 2 步 · 先看配图,再拆信息点(顺序不能反)

先过配图(作者已筛选过),逐张判断:

原图是什么怎么处理
逻辑图/流程图/结构图最高优先级。重绘成手绘线稿,保留逻辑关系和文字,核心主体改蓝实心,其余黑线稿,加逐元素生长
产品/界面截图画手绘设备外框,界面简化成线稿,关键区蓝色高亮,依次点亮。不直接贴原图
数据图表重绘手绘图表,数字滚动递增,关键柱/数字用蓝
实拍/人物照转手绘线稿示意,或丢掉另画
纯装饰/表情包丢掉

再通读全文补齐配图没覆盖的信息点。总帧数 6–10,尽量多来自原文配图(有 5 张有效配图,至少 5 帧来自它们)。

第 3 步 · 判定每帧图解类型

放射图(默认首选)/流程图/对比图/结构图/数据图/结论卡。信息点按原文叙述顺序排列,不重组逻辑(口播按原文讲,画面要跟上)。

第 4 步 · 输出分镜表(先出表,等用户确认再进第 5 步)

帧号图解类型来自原文第几张图画面描述蓝色元素是哪个入场顺序标题文字注释文字口播解说词时长
  • 画面描述要具体到可执行(有哪些图标、怎么排、箭头怎么连、每处写什么字),禁止「科技感画面」这种空描述。
  • 蓝色元素明确指定且只有一个;入场顺序按 1/2/3 写清;时长 5–8s(动效跑完还要停)。

第 5 步 · 生成画面(用户确认分镜后)—— 见第四节「真正出片」

四、真正出片:调用视频模型

每一帧走两小步:① 生成手绘线稿静帧 → ② 用视频模型做「手绘生长」动效,最后拼接。

① 生成每帧的手绘线稿静帧

按分镜表的画面描述 + 第一节风格,用图像模型出这一帧动效跑完后的最终静态图(白底、黑线稿、一处蓝、留白)。走用户的 image-studiofrontend-design(HTML 画好截图亦可)。命名 frames/f01.png…

② 用视频模型把静帧变成「手绘生长」动效

两条通道任选(需对应 key):

通道 A · 火山引擎 Seedance 2.0scripts/seedance.py

bash
export ARK_API_KEY=xxx      # 火山方舟 API Key
python3 scripts/seedance.py \
  --image frames/f01.png \
  --prompt "白底手绘白板动画:画面中的黑色线稿图标和曲线箭头,像被一支看不见的笔按顺序一笔一笔画出来(draw-on 生长),箭头沿路径延伸;中心蓝色实心主体轻微弹入;画完后完全静止。镜头固定不动,无粒子无光效无转场。" \
  --ratio 4:3 --duration 6 --resolution 720p --out clips/f01.mp4

通道 B · libtv Agentscripts/libtv_i2v.sh,复用 libtv-skill)

bash
export LIBTV_ACCESS_KEY=xxx
bash scripts/libtv_i2v.sh --image frames/f01.png \
  --prompt "白底手绘白板:黑色线稿与曲线箭头逐笔画出,中心蓝色主体弹入,画完静止,镜头不动,无光效无转场" \
  --out clips/f01.mp4

对每一帧重复。动效 prompt 要点:逐笔 draw-on、箭头沿路径生长、蓝主体弹入、画完静止、镜头固定、无粒子无光效无转场

③ 拼接 + 配乐

bash
bash scripts/concat.sh broll.mp4 clips/f01.mp4 clips/f02.mp4 ...   # 硬切拼接
# 配无人声氛围乐(压低):走 space-video-audio
bash ~/.claude/skills/space-video-audio/scripts/mix.sh --video broll.mp4 --bgm bgm.mp3 --out broll_final.mp4 --bgm-db -22

五、安全区(垫在口播下方)

画面下方 1/4 保持干净(留给口播人像和字幕),图解主体放上方 3/4,标题固定顶部,正下方不放关键信息。

六、默认参数

画幅 4:3 | 总时长 40–60s | 白底 | 黑色单线手绘 | 蓝色实心每帧一处 | 中文为主 | 无人声氛围乐压低 | 硬切转场。

七、依赖与配置

  • python3ffmpegcurl
  • 视频模型二选一:ARK_API_KEY(Seedance) 或 LIBTV_ACCESS_KEY(libtv,且已装 libtv-skill)
  • 图像模型:image-studio / frontend-design
  • Seedance 模型 id 默认 doubao-seedance-2-0-260128,可用 ARK_SEEDANCE_MODEL 覆盖

八、输出前自查(任一不过就重出那帧)

  1. 背景纯白?无多余底纹渐变? 2. 本帧只有一处蓝、其余全黑线稿? 3. 图标只有轮廓无填充?没混进照片/3D/渐变? 4. 箭头是手绘曲线非直角折线? 5. 元素一个一个画出而非一次全出? 6. 每帧画完静止 ≥ 2s? 7. 一帧文字 ≤ 40 字、留白够? 8. 下方 1/4 干净? 9. 原文有效配图都用上了?

调通自测

配好 key 后,先用单帧跑通再批量:

bash
# Seedance:一句话文生视频测连通
python3 scripts/seedance.py --prompt "白底,一个黑色线稿灯泡被一笔笔画出来,画完静止" --duration 5 --out /tmp/test.mp4
# 或 libtv:
bash scripts/libtv_i2v.sh --prompt "白底,一个黑色线稿灯泡逐笔画出,画完静止" --out /tmp/test.mp4

出到 /tmp/test.mp4 且能播放,即通道打通,可正式批量出片。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Space Video Broll Sketch AI skill do?

文章转手绘图解 B-roll——输入公众号文章(正文或链接),优先抽取原文配图,把文章逻辑做成一支手绘线稿风格的动态图解视频,并调用真实视频模型(火山引擎 Seedance 2.0 或 libtv Agent)逐帧生成「手绘生长」动效,拼成成片。白底、黑色单线图标、单一蓝色强调、细曲线箭头,默认 4:3,垫在口播下方。当用户说「文章转图解视频」「手绘图解 B-roll」「白板动图」「把这篇文章做成动态图解」「Seedance 出 B-roll」时触发。

Why use Space Video Broll Sketch on TypingMind?

Because you install it once and use it with any model. Space Video Broll Sketch is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Space Video Broll Sketch in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/SpaceZephyr/creator-buddy/tree/main/video-Skills/space-video-broll-sketch. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Space Video Broll Sketch?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Space Video Broll Sketch?

As many as you like. As long as a model supports skills, you can use Space Video Broll Sketch with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Space Video Broll Sketch AI skill free?

It is published on GitHub by SpaceZephyr. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇