Ui2v logo

Ui2v

CommunityPopular
Unclecheng-li
ui2v

Use when helping users discover, install, publish, share, sync, or update UI2V video motion assets and HyperFrames motion packages. Route video creation, preview, and rendering to HyperFrames skills.

Overview

PublisherUnclecheng-li
RepositoryAI_Animation
Skill nameui2v
Stars
1.6K
Forks
123
Bundled files
5
LicenseMIT
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.

  • 5 bundled files

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

  • Open source

    Published by Unclecheng-li on GitHub. Read the source before you install it.

Installation

Install the Ui2v 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/Unclecheng-li/AI_Animation/tree/master/skills/ui2v-motions/02_官方CLI与文档/skills/ui2v
  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.

Use it in TypingMind

Enable Ui2v 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 Ui2v 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 Ui2v 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.

ui2v Skill

UI2V 是面向 AI 工作流的 视频动效资源库。它帮助用户发现、安装、复用和分享 HyperFrames 动效包;实际的视频创作、预览和渲染由 HyperFrames 完成。

For project positioning, README copy, npm copy, website copy, or launch/promo text, read references/positioning.md.

Mental model

text
HyperFrames authoring -> package folder -> ui2v login -> ui2v motion publish -> ui2v.com
LayerTool
Author / preview / renderHyperFrames (/hyperframes and related skills)
Search / install / publish / syncui2v CLI (npm package @ui2v/cli, bin ui2v)

Do not use the abandoned @ui2v/cli@1.x JSON render/preview stack (doctor, validate, preview, render, animation.json, @ui2v/core, @ui2v/engine, @ui2v/producer). The current @ui2v/cli package is the registry client.

Task routing

Use this skill for registry work and CLI/package maintenance:

  • Publish/share/install/search a motion on ui2v.com → use this skill and the ui2v CLI.
  • Fix or extend the UI2V CLI → inspect packages/ui2v/src/cli, update focused tests, then run the repo verification commands below.
  • Fix registry package metadata or a publish failure → read references/package-format.md and references/publish.md.
  • Update website, README, npm, or promo copy → read references/positioning.md; keep package references as npm @ui2v/cli, bin command ui2v, and npx command npx @ui2v/cli@latest ....
  • Clean project structure → read references/cleanup.md; remove or route away from legacy JSON renderer examples/scripts; do not present them as current UI2V capabilities.
  • Prepare or explain a release → read references/release.md; verify versions, tests, build, and npm copy.

Route away from this skill when the user is not doing registry work:

  • Make / edit / preview / render a video composition → use HyperFrames skills, not this CLI.
  • Old JSON ui2v projects → do not revive the old JSON toolchain. Migrate to a HyperFrames package, then publish with ui2v.

CLI version gate

Before publish/install/sync that depends on current CLI behavior:

bash
ui2v --cli-version
npm view @ui2v/cli version
  • Missing CLI → install: npm install -g @ui2v/cli@latest (or bun install -g @ui2v/cli)
  • Behind latest → ui2v upgrade (alias self-update), or npm install -g @ui2v/cli@latest
  • Under --no-input, ui2v upgrade only prints the install command and exits non-zero when outdated

npm view is metadata only. Do not upgrade as a routine first step unless the CLI is missing, too old for the task, broken, or the user asks for latest.

From this monorepo before publishing:

bash
cd packages/ui2v && bun run build && node bin/ui2v.js --cli-version

Monorepo development workflow

For CLI source changes in this repository:

bash
bun install
bun run build
bun run test
bun run --filter "@ui2v/cli" verify
node packages/ui2v/bin/ui2v.js --help
node packages/ui2v/bin/ui2v.js --cli-version

Prefer the narrowest useful test first while iterating:

bash
cd packages/ui2v
bun run test:src
bun run verify:build
bun run test:artifact

Package shape

A motion folder must include:

  • registry-item.json with type: "hyperframes:block"
  • Entry composition HTML (index.html or listed composition file)
  • Optional assets/, README.md, thumbnail

Details: references/package-format.md.

Positioning

When introducing the project, use this core message:

text
让 AI 帮你发现、安装和分享 UI2V 视频动效资源:
搜索并安装现成动效,发布原创作品,让动画像依赖一样轻松复用。

Do not call UI2V a renderer. Keep the boundary crisp:

  • HyperFrames creates, previews, and renders motion.
  • UI2V distributes completed motion packages through search, install, publish, sync, and inspect workflows.

Publish flow

bash
ui2v login
ui2v motion publish ./my-motion --version 1.0.0
# optional: ui2v sync

Aliases: ui2v skill publish, legacy ui2v publish.

Full checklist: references/publish.md.

Release flow

For npm release preparation, use references/release.md. Do not publish or bump versions casually; first confirm the requested version and run local verification.

Common registry commands

bash
ui2v search "logo sting"
ui2v install <slug>
ui2v list
ui2v update --all
ui2v explore
ui2v inspect <slug>
ui2v upgrade

Install command shown on the site: npx @ui2v/cli@latest install <slug>.

Troubleshooting cookbook

  • CLI not found → install @ui2v/cli, then confirm ui2v --cli-version.
  • Outdated CLI → run ui2v upgrade or npm install -g @ui2v/cli@latest.
  • Auth failure → run ui2v login; for automation use ui2v login --token clh_... only when the user provides a token.
  • Publish rejects version → ensure --version is valid semver and is newer than the published release.
  • Missing entry HTML → check index.html, first files[] composition path, or {name}.html.
  • Manifest validation failure → check type: "hyperframes:block", dimensions, duration, and files[] using references/package-format.md.
  • Render/preview request appears → stop using UI2V commands and route to HyperFrames.

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 Ui2v AI skill do?

Use when helping users discover, install, publish, share, sync, or update UI2V video motion assets and HyperFrames motion packages. Route video creation, preview, and rendering to HyperFrames skills.

Why use Ui2v on TypingMind?

Because you install it once and use it with any model. Ui2v 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 Ui2v in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Unclecheng-li/AI_Animation/tree/master/skills/ui2v-motions/02_官方CLI与文档/skills/ui2v. 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 Ui2v?

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 Ui2v?

As many as you like. As long as a model supports skills, you can use Ui2v with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ui2v AI skill free?

Yes. It is published on GitHub by Unclecheng-li 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.

View all

Set up your own AI workspace now

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