Archival Fragments logo

Archival Fragments

Community
ttfake92-lab
archival-fragments

从一个想法或一份文案,做出一条完整的「档案剪贴」风格短片——满幅象牙纸、单色印刷黑白、单一暗砖红,镜头用 MiniMax H3 首尾帧驱动,配音用 Fish Audio,成片用 ffmpeg 合成。当用户想用档案剪贴/编辑设计/纸质拼贴风格做视频,或要把一段文案、一个选题、一条新闻做成解说短片时使用。包含环境安装检查、拆故事拆画面拆节奏、逐镜生成、变速拼片的完整流程。

Overview

Publisherttfake92-lab
Repositoryskills
Skill namearchival-fragments
Stars
308
Forks
45
Bundled files
23
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.

  • 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 ttfake92-lab on GitHub. Read the source before you install it.

Installation

Install the Archival Fragments 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/ttfake92-lab/skills/tree/main/skills/archival-fragments
  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/ttfake92-lab/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/archival-fragments .claude/skills/archival-fragments
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Archival Fragments 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 Archival Fragments 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 Archival Fragments 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.

Archival Fragments

从零做出一条完整短片。用户可能只给你一个想法,也可能给一份写好的文案——两种都从下面的流程走。

三条硬约束(违反任何一条,成片必废)

1. 每一镜的画面必须不同

N 个镜头需要 N+1 张各不相同的关键帧。

"相邻两镜共用同一张图"的意思是:第 1 镜的尾帧 = 第 2 镜的首帧,这一张图被这两镜共用。 不是整片共用一张图。

绝对禁止:

  • 拿同一张图当所有镜头的输入
  • 拿一张结构图、示意图、信息图当所有镜头的参考
  • 把 assets/style-reference.png 当成生成输入——它是给人看的风格参考板,任何一次生成都不要挂它

这样做出来的片子几十个镜头长得一模一样,等于没拆镜,观众三秒划走。

自检(必须做,并把结果报给用户):

关键帧张数 == 镜头数 + 1      ✓/✗
任意两张关键帧的画面描述不重复  ✓/✗
每张关键帧都有自己独立的提示词  ✓/✗

2. 故事、画面、节奏必须由你亲自拆,且拆完要给用户过目

不要拿到文案就直接开生成。必须先产出一张逐镜表,包含:每镜的旁白、画面内容、首尾帧、时长。拆完先给用户看,让他有机会否掉——改一张表 5 分钟,跑完再改是 4 小时。

详见 01-script.md。

3. 具象优先,不要抽象图形

纸和红线是画面的地面,不是主体。每句话找一个观众不用想就懂的通用符号——世界地图+图钉、天平、台阶、一大堆实物。一条片子收敛到 2–3 个符号,各用几次。

用空白纸加一条线表达"这个位置是空的"、用三个方块表达"三家公司"——这类抽象图形观众看不懂,实测失败。

详见 style-guide.md 第零条。

流程

按顺序做,每一阶段有自己的文档:

阶段文档产出
0. 环境准备00-setup.md依赖装好、凭据可用、检查全绿
1. 想法 → 文案 → 拆故事/画面/节奏01-script.mdnarration.json + 逐镜表
2. 设计关键帧链02-keyframes.mdkeyframes.json
3. 写运动句03-shots.mdshots.json
4. 排节奏04-rhythm.md镜长分配表
5. 生成与合成05-produce.md关键帧 → 镜头 → 配音 → 成片

视觉基线随时查 style-guide.md。

三个必须停下来问用户的节点:

  1. 阶段 0 检查完 —— 告诉用户环境就绪,请他给想法或文案
  2. 阶段 1 拆完 —— 把逐镜表给用户过目
  3. 阶段 5 跑完 2–4 个样片 —— 确认方向再跑全量

默认参数

4:3 / 2K(1920×1440)/ 视频 Minimax H3 frames2video / 图片 Seedream 5.0 Pro / count=1 / 每镜生成 5 秒 / 并发上限 1,必须串行。

包里有什么

  • references/ —— 六份规则文档,就是上表那几份
  • examples/ —— 一条已完成 67.3 秒成片的完整配置:35 张关键帧提示词原文、34 条运动句、镜长分配表、17 句旁白、文案。照着改结构,不要照抄内容——那些符号是为特定题材设计的
  • assets/style-reference.png —— 风格参考板,只给人看
  • assets/example-01..08-*.jpg —— 八张连续的关键帧,展示同一条片子里画面是怎么一张一张推进的

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 Archival Fragments AI skill do?

从一个想法或一份文案,做出一条完整的「档案剪贴」风格短片——满幅象牙纸、单色印刷黑白、单一暗砖红,镜头用 MiniMax H3 首尾帧驱动,配音用 Fish Audio,成片用 ffmpeg 合成。当用户想用档案剪贴/编辑设计/纸质拼贴风格做视频,或要把一段文案、一个选题、一条新闻做成解说短片时使用。包含环境安装检查、拆故事拆画面拆节奏、逐镜生成、变速拼片的完整流程。

Why use Archival Fragments on TypingMind?

Because you install it once and use it with any model. Archival Fragments 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 Archival Fragments in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ttfake92-lab/skills/tree/main/skills/archival-fragments. 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 Archival Fragments?

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 Archival Fragments?

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

Is the Archival Fragments AI skill free?

It is published on GitHub by ttfake92-lab. 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 👇