TypingMindTypingMindThe best frontend for AI
Gbro Collage Info logo

Gbro Collage Info

Community
pyang5166
gbro-collage-info

半调纸拼贴风信息动画（HyperFrames）。给一份口播逐字稿，从中挑出适合做成信息动画的段落（数字冲击、流程结构、清单收敛、对比翻转、结果高光），经用户确认后出静态样帧，再确认后产出 1080×1920 竖屏带拟音的 mp4 动画。用户说「拼贴信息动画」「collage info」「gbro-collage-info」「信息动画挑段落」「逐字稿做信息动画」「半调纸拼贴动画」，或给逐字稿/分镜并想要这种米色纸场+卡纸剪片+定格动效的信息动画时，必须使用此 skill。本 skill 只做无角色的信息图动画（纯 HTML/CSS/GSAP，本机渲染）；情绪独白、隐喻类段落不做，建议归实拍或角色/隐喻动画。

Overview

Publisherpyang5166
Repositorygbro-collage-info
Skill namegbro-collage-info
Stars
55
Forks
6
Bundled files
23
LicenseMIT
Links
Skill sourceRepository
  • 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.

  • 23 bundled files

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

  • Open source

    Published by pyang5166 on GitHub. Read the source before you install it.

Installation

Install the Gbro Collage Info 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/pyang5166/gbro-collage-info/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/pyang5166/gbro-collage-info.git \
  .claude/skills/gbro-collage-info
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gbro Collage Info 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 Gbro Collage Info 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 Gbro Collage Info 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.

gbro Collage Info（半调纸拼贴 · 信息动画）

把逐字稿里"讲信息"的段落，做成 editorial 半调纸拼贴风的信息图动画：米色纸场、卡纸剪片、单一点色、半调截图、stop-motion 定格。

效果参考：仓库 README 里的 GIF 演示与末帧一览图。

三道确认门

text
Gate 1  选段 + 主动效分配 → 用户确认
Gate 2  静态样帧（headless Chrome 截图 + 拼图）→ 用户确认
Gate 3  HyperFrames 动画 + 拟音 + QA → 交付

每道门都停下来等确认，不跳门。用户在 Gate 1 改名单、在 Gate 2 改构图，都比在 Gate 3 改成片便宜。

Gate 1：选段

读逐字稿（或分镜脚本，只取其中标为动画的段），按下面的判据挑段落。

适合做信息动画的段落（一条至少命中一类）：

类型信号对应主动效
数字冲击台词里有具体数字（7 条、10 句、2 分钟、12 类）数字撞入 / 计时压缩
流程结构步骤、决策树、分类收敛（30 个→5 大类）从底部生长 / 抽屉抽出
清单收敛多个候选收敛到一个结果推焦收敛
对比翻转正面 vs 痛点、以前 vs 现在三联卡翻面
结果高光观众最想要的东西落地的那句推焦 + 点色描边
概念封装抽象论点第一次被看见（钩子落点）吸入 / 汇聚
系列标题卡"第一个…第二个…第三个…"的章节口同模板换色派生

不适合、要拦下来的：界面操作演示（归录屏）、需要实拍质感的（归实拍）、情绪独白和隐喻（归角色/隐喻动画，不在本 skill 范围）、在截图上画重点（归录屏+后期描边）。

数量与去重：

  • 默认精选 6–10 条独立设计；用户指定数量就按用户的。
  • 每条分配一个不重复的主动效（吸入 / 堆叠 / 撞入 / 景深 / 生长 / 抽屉 / 推焦收敛 / 翻面）。两条段落同形时合并或派生，不做两条同质动画。
  • 主动积极找派生机会：系列标题卡从一个模板换色导出；相邻的收拢/翻面/汇聚三段可以做成一条长 composition 分段切。落选段落写明去处（录屏/合并/派生），不是丢掉。

产出：一张表（段落原文落点 / 入选理由 / 主动效 / 需要的截图锚点），加落选段的降级说明。停，等确认。

Gate 2：样帧

确认名单后，每条先做静态 hero frame（不写动画代码）：

  1. 写单页 HTML（1080×1920），引用 skill 自带的 assets/collage.css，放在项目 style-plates/ 下。
  2. headless Chrome 截图（macOS 路径如下；Linux 用 google-chrome / chromium 可执行名）：
bash
"/Applications/Google Chrome.app/Contents/MacOS/Google Chrome" --headless=new \
  --disable-gpu --hide-scrollbars --force-device-scale-factor=1 \
  --window-size=1080,1920 --screenshot=<名>.png "file://<绝对路径>.html"
  1. 自己先看图 QA（读 PNG）：留白够不够、点色是否只有一处、信息是否都在 y≤1280、撕边地层是否只在底部。不合格先改再给用户。
  2. 拼 contact sheet 发给用户确认。

风格规则读 references/style-system.md。核心六条：纸场底不用渐变；一件信息=一张卡纸剪片；真实截图=半调剪片、全帧只一处点色批注；一帧一个点色 + 一个出画大色块；3–6 个大组大留白；底部 640px 只放撕边地层。

截图锚点纪律：需要真实界面截图的位置，没拿到截图前一律用 .shot 抽象半调剪片（灰条+网点），绝不画假界面；不是原文就不框选放大。拿到截图后换 <img class="shot-img"> 一行即可。

Gate 3：动画

样帧确认后，搭 HyperFrames 项目并渲染。动效与拟音规则读 references/motion-grammar.md，环境与渲染命令读 references/production.md。

  1. 用 scripts/new_project.sh <项目名> 建项目（自动拷 collage.css / gsap / sfx，写 hyperframes.json）。
  2. 每条一个 compositions/<段号>-<名>.html，把样帧 DOM 原样搬进去，再加 paused GSAP timeline。样帧就是动画的收帧——动画结束时的画面必须和确认过的样帧一致。
  3. 加拟音 cue（每条 3–7 个，音量 ≤0.5，写在文件底部 <!-- SFX --> 区块）。
  4. lint → 逐条 render -q standard → 抽末帧拼 contact sheet 自查 → 交付 mp4 + 末帧一览，并问是否要拷贝到指定目录。

交付默认：1080×1920 / 30fps / 每条 5s / AAC 拟音音轨 / 无口播无字幕（剪辑台合成）。

色本

固定四组「纸场 + 点色」，按内容功能段分组使用，一个功能段锁一组色：

纸场点色默认给
奶白 #EEE7D6深绿 #1F5142第一个功能段
冷灰白 #E6E7E3墨蓝 #18334D第二个功能段
暖石灰 #D8D0BC珊瑚 #E0783C第三个功能段
暖石灰 #D8D0BC芥末 #D6A92B钩子与结尾（首尾闭环）

（可选集成）同一支片子里若还有其他拼贴风动画条目且带有自己的色本定义，继承其纸场/点色，让全片看起来是一家人；没有就用上表默认。功能段少于四段时优先保住"钩子结尾=芥末"的闭环。

写作纪律

  • 屏幕文字只用逐字稿里有的事实：数字、名称、原话。台词没给的内容（比如第 4 个候选的文案、5 大类的名字）用空白卡占位，不替内容编数据。
  • 中文短句，每帧一个论点；mono 小字只放编号 / 路径 / 单位。

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 Gbro Collage Info AI skill do?

半调纸拼贴风信息动画（HyperFrames）。给一份口播逐字稿，从中挑出适合做成信息动画的段落（数字冲击、流程结构、清单收敛、对比翻转、结果高光），经用户确认后出静态样帧，再确认后产出 1080×1920 竖屏带拟音的 mp4 动画。用户说「拼贴信息动画」「collage info」「gbro-collage-info」「信息动画挑段落」「逐字稿做信息动画」「半调纸拼贴动画」，或给逐字稿/分镜并想要这种米色纸场+卡纸剪片+定格动效的信息动画时，必须使用此 skill。本 skill 只做无角色的信息图动画（纯 HTML/CSS/GSAP，本机渲染）；情绪独白、隐喻类段落不做，建议归实拍或角色/隐喻动画。

Why use Gbro Collage Info on TypingMind?

Because you install it once and use it with any model. Gbro Collage Info 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 Gbro Collage Info in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/pyang5166/gbro-collage-info/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 Gbro Collage Info?

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 Gbro Collage Info?

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

Is the Gbro Collage Info AI skill free?

Yes. It is published on GitHub by pyang5166 under the MIT license. 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.

Related AI Skills

View all
affaan-m logo

Mle Workflow

affaan-m
CommunityPopular

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML…

40.4K
270.2K
1 files
View
mattpocock logo

Diagnosing Bugs

mattpocock
CommunityPopular

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

22.3K
264.4K
2 files
View
affaan-m logo

E2e Testing

affaan-m
CommunityPopular

Patrones de pruebas E2E con Playwright, Page Object Model, configuración, integración CI/CD, gestión de artefactos y estrategias para pruebas inestables.

39.1K
261.1K
Instructions
View
affaan-m logo

Eval Harness

affaan-m
CommunityPopular

Framework formal de evaluación para sesiones de Claude Code que implementa principios de desarrollo orientado a evals (EDD)

39.1K
261.1K
Instructions
View

Set up your own AI workspace now

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