Eian Riso Broll logo

Eian Riso Broll

Community
YIAN6557
eian-riso-broll

孔版双色(Riso)风格的信息 B-roll 动画。给一份口播逐字稿(可附 SRT 字幕),挑出适合做成信息动画的段落,套用 10 个现成模板(数字冲击 / 流程 / 收敛 / 前后对比 / 连接密度 / 金句 / 多选一 / 误区翻转 / 章节卡 / 截图锚点),先出静态样帧确认,再渲染 1080×1920 竖屏 mp4(无音轨;可出透明底 ProRes)。用户说「Riso 动画」「孔版风 B-roll」「eian-riso-broll」「逐字稿做信息动画」「口播配信息动画」「信息图 B-roll」,或给出逐字稿、想要高对比杂志感的竖屏信息动画时,使用此 skill。纯 HTML/CSS/GSAP 本机渲染,不调用图片生成模型;只做无角色的信息动画 —— 情绪独白、隐喻、软件操作演示不做,建议归实拍 / 角色动画 / 录屏。

Overview

PublisherYIAN6557
Repositoryeian-riso-broll
Skill nameeian-riso-broll
Stars
328
Forks
23
Bundled files
52
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.

  • 52 bundled files

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

  • Open source

    Published by YIAN6557 on GitHub. Read the source before you install it.

Installation

Install the Eian Riso Broll 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.
    https://github.com/YIAN6557/eian-riso-broll/tree/main
  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/YIAN6557/eian-riso-broll.git \
  .claude/skills/eian-riso-broll
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Eian Riso Broll 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 Eian Riso Broll 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 Eian Riso Broll 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.

Riso B-roll · 孔版双色信息动画

风格一句话:一张纸,两种专色油墨。A 墨(深)负责所有要读的字和结构;B 墨(荧光)一帧只做一处重点;两墨重叠的地方自动出现第三色;B 版永远有 3px 的套印错位;所有“渐变”都用网点表达。动起来像一张海报正在被印出来:网点显影、套印“咔”地归位、盖章砸落、滚筒刷过。

效果参考:demo/(GIF + 末帧一览)。

文件地图

要做什么读哪里
挑段落、提炼屏幕文字references/copy.md
选模板、改 DATAreferences/templates.md
视觉规则(色本、版面、字体、禁区)references/style.md
改动效 / 写新模板(riso.js API)references/motion.md
渲染、质检、交付、排错references/production.md

模板在 templates/,每个都是能直接渲染的完整 composition,只改顶部的 DATA。

三道门

text
Gate 1  选段表(段落 → 模板 → 屏幕文字 → 时长)        → 停,等确认
Gate 2  样帧(每条的末帧海报 + contact sheet + QA)    → 停,等确认
Gate 3  成片(mp4 + QA)                               → 交付

每道门都停下来等用户。改名单在 Gate 1 最便宜,改构图在 Gate 2 最便宜。 快速通道:用户只给了一段、或明确说“直接出片 / 不用确认”时,可以合并门,但 QA 一步都不省。

Gate 1 · 选段

按 copy.md 读逐字稿,产出一张表:

#原话落点模板屏幕文字(提炼后)时长色本截图需求

外加“落选段 → 去处”(录屏 / 实拍 / 合并进第 N 条)。

  • 一条只讲一件“能被看见”的事:一个数字、一个结构、一次对比、一句结论。
  • 相邻两条不用同一模板;同一模板全片 ≤ 2 次(章节卡系列除外)。
  • quote(满版深底)全片 ≤ 2 条,放在钩子或结论,制造明暗节奏。
  • 时长用 scripts/timing.mjs 算(有 SRT 用 SRT,没有按 4.5 字/秒估),不要拍脑袋写 5 秒。

Gate 2 · 样帧

bash
P=$(node scripts/new_project.mjs 2026-10-07-主题)    # 建项目,assets 整份拷入
cp templates/number.html $P/compositions/01-xxx.html  # 每条一个文件,按 01- 02- 编号
# 只改 DATA → 渲样帧 → 质检
node scripts/render.mjs $P/compositions/*.html --still   # plates/*.png + plates/sheet.jpg
node scripts/qa.mjs     $P/compositions/*.html           # qa/*-audit.png;有 error 必须修

自己先读 plates/sheet.jpg 和有问题的 qa/*-audit.png,修完 error 再把 sheet 发给用户。样帧就是成片的最后一帧——样帧和成片同一个文件渲出来,天然一致。

Gate 3 · 成片

bash
node scripts/render.mjs $P/compositions/*.html           # renders/*.mp4(H.264,无音轨)
node scripts/qa.mjs     $P/compositions/*.html           # 再查一遍:时长、尺寸

交付:renders/*.mp4 + plates/sheet.jpg + STORYBOARD.md(填好分镜表)。问用户要不要:透明底版本(--alpha → ProRes 4444 .mov,叠在口播画面上用)、拷到指定目录。

不可违反

  1. 屏幕文字只来自逐字稿原话:数字、名词、原句的子串。台词没说的(第 4 个类别叫什么、具体百分比)就留空,不编。能做的只有“删字”和“换行”,不改写意思。
  2. 没有真截图就不画界面:shot 模板没图时只显示“截图 · xxx · 待替换”占位,不加批注框。
  3. 小于 100px 的字只用 A 墨;B 墨只给大数字、压条、色块。
  4. 信息只在 y 168–1330;下面是字幕床,只放网点地层。
  5. QA 有 error 不交付。
  6. 不做音效:成片只有画面、没有音轨;不加拟音、不配 BGM,声音统一在剪辑台处理。

常见坑(写新模板 / 改版面时)

  • 嵌套元素不会自动 position:absolute(只有 #stage 的直接子元素会)——容器里的子元素要自己写。
  • 先排版、后建时间轴:fit() / inkBox() 要在任何 tween 之前调用,否则量到的是动画初始态。
  • 数字按墨迹对齐(Riso.inkBox),不要按行框——数字字体的字形会超出行框。
  • 多行文本用 Riso.text(el, '第一行\n第二行[重点]'),不要直接 textContent,否则逐字升起不生效。

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 Eian Riso Broll AI skill do?

孔版双色(Riso)风格的信息 B-roll 动画。给一份口播逐字稿(可附 SRT 字幕),挑出适合做成信息动画的段落,套用 10 个现成模板(数字冲击 / 流程 / 收敛 / 前后对比 / 连接密度 / 金句 / 多选一 / 误区翻转 / 章节卡 / 截图锚点),先出静态样帧确认,再渲染 1080×1920 竖屏 mp4(无音轨;可出透明底 ProRes)。用户说「Riso 动画」「孔版风 B-roll」「eian-riso-broll」「逐字稿做信息动画」「口播配信息动画」「信息图 B-roll」,或给出逐字稿、想要高对比杂志感的竖屏信息动画时,使用此 skill。纯 HTML/CSS/GSAP 本机渲染,不调用图片生成模型;只做无角色的信息动画 —— 情绪独白、隐喻、软件操作演示不做,建议归实拍 / 角色动画 / 录屏。

Why use Eian Riso Broll on TypingMind?

Because you install it once and use it with any model. Eian Riso Broll 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 Eian Riso Broll in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/YIAN6557/eian-riso-broll/tree/main. 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 Eian Riso Broll?

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 Eian Riso Broll?

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

Is the Eian Riso Broll AI skill free?

It is published on GitHub by YIAN6557. 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 👇