H3 Camera Motion Lib

Q: Why use H3 Camera Motion Lib on TypingMind?

Because you install it once and use it with any model. H3 Camera Motion Lib 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.

Q: How do I install H3 Camera Motion Lib in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/swan7-py/MiniMax-H3-Skills-Local/tree/main/h3-camera-motion-lib. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Q: Which AI models can use H3 Camera Motion Lib?

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.

Q: How many AI models can I use with H3 Camera Motion Lib?

As many as you like. As long as a model supports skills, you can use H3 Camera Motion Lib with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Q: Is the H3 Camera Motion Lib AI skill free?

It is published on GitHub by swan7-py. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

Q: 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.

Q: 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.

Community

swan7-py

h3-camera-motion-lib

H3 运镜提示词库——要写推、拉、摇、移、升降、环绕、翻滚、子弹时间、甩镜、荷兰角、移焦、POV、顶拍、航拍、穿越、视差、过肩、正反打等**镜头运动的中文提示词**时使用。按运镜族给出**可直接粘贴进 `detailed_description` 的中文镜头句**，并附实测状态（成立 / 部分成立 / 失败）、推荐 LoRA、踩过的坑与写法纪律。**不依赖 camera DSL**：DSL 只作可选校验，且本库已把 DSL 的英文 negative clarifier 全部正向化（12 条穷举表）。当部分 DSL 官方等级与实测冲突时，以本库实测为准。与 `h3-video-prompt-cn` 配套使用：它管六段结构与规范，本库管镜头句本体。

Overview

Publisher	swan7-py
Repository	`MiniMax-H3-Skills-Local`
Skill name	`h3-camera-motion-lib`
Stars	66
Forks	5
Bundled files	10
Links	Skill source Repository

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.
10 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by swan7-py on GitHub. Read the source before you install it.

Installation

Install the H3 Camera Motion Lib AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/swan7-py/MiniMax-H3-Skills-Local/tree/main/h3-camera-motion-lib
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.

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/swan7-py/MiniMax-H3-Skills-Local.git /tmp/MiniMax-H3-Skills-Local
mkdir -p .claude/skills
cp -r /tmp/MiniMax-H3-Skills-Local/h3-camera-motion-lib .claude/skills/h3-camera-motion-lib

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable H3 Camera Motion Lib 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 H3 Camera Motion Lib 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 H3 Camera Motion Lib 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.

H3 运镜提示词库

来源：H3 运镜对照测试（A–G 七组 46 镜 · 约 100 条 480P 成片 + 29 条 1080P 双采成片 · Ref2VA · 中文提示词）校准版本：v2 · 2026-10-09（经用户逐条复核，旧版与被校准条目冲突的表述一律以本库为准）

这个库解决什么

写 H3 运镜提示词时，最花时间的是「这句镜头话到底该怎么写」。本库把 46 个已出片验证过的镜头按族整理成可直接粘贴的中文句子，并告诉你：这个镜头在 H3 上到底能不能做出来、要不要挂 LoRA、坑在哪。

三条定位（重要）：

本库是镜头句的权威，DSL 是可选校验。 你可以完全不装 cinematic-director-camera-dsl 就用本库写运镜提示词；装了也不必逐句核对——测试发现部分 DSL 官方等级与实测结果不一致（例如整圈环绕、摇镜落位），冲突时以本库「实测」一栏为准。
本库只管镜头句本体。 六段结构、参考图角色、否定式闸门、对白写法、交付格式归 h3-video-prompt-cn（用户级镜像：h3-prompt-writing-cn）。本库产出的句子一律粘贴进 detailed_description 的 [Shot N] 内。
所有句子都是中文、正向、可直接粘贴。 已按「否定式禁用令」处理过——DSL 里的英文否定句（stays in place / does not turn / no shake）在本库中已被转写为正向中文，不要改回否定式。

路由表：按你要的运镜查文件

你要写什么	读哪个文件
先读这份（镜头句放在哪、变量纪律、正向化替换表、时刻与配速、环境写法）	`references/00-core-discipline.md`
摇镜、变焦推 / 变焦拉	`references/01-pan-tilt-zoom.md`
推镜头 / 拉镜头 / 横移 / 升降（摇臂）	`references/02-dolly-truck-pedestal.md`
环绕（半圈 / 整圈 / 螺旋）、翻滚、子弹时间	`references/03-orbit-roll-bullettime.md`
希区柯克变焦、急推、甩镜、荷兰角、移焦、揭示、推+仰复合	`references/04-special-compound.md`
POV、顶拍、上摇、高角度俯视、SnorriCam	`references/05-viewpoint.md`
手持、斯坦尼康、跟拍、追逐、航拍 / 拉升、穿越、遮挡穿越、视差	`references/06-rig-and-device.md`
过肩、正反打、双人同框、双人环绕、双人横移、过肩推近	`references/07-two-person.md`
要不要挂 LoRA、挂哪个、触发词、权重	`references/08-lora-catalog.md`
Ref2VA 的现实边界：起手景别、双主体、闭环阈值、哪些指标测不了、首帧取舍	`references/09-reality-and-pitfalls.md`

三步用法

选族 → 查句：按上表打开对应文件，找到你的运镜，复制它的「镜头句」一段。
套进六段结构：按 h3-video-prompt-cn 的契约，把镜头句放进 detailed_description 的 [Shot N] 内，紧跟 opening 句之后（先写画面里先出现的东西，再写镜头运动）；summary 里只留一句层级概括（「一条连续长镜」「三镜交换」），不复述镜头变量。
交付前自检：① summary 与 detailed_description 两段里 <Picture 计数 = 0；② 无裸否定（对照 00-core-discipline.md 的 12 条替换表）；③ 整圈类同时写了圈数与起止时刻。

可信度声明（引用本库结论时必须一起写出）

每格单样本单种子（480P 全组同种子 20261005）→ 结论等级为初级，重复或换种子验证前不作定论；
实测跑的是中文提示词 + 864×480 横屏（480P 轮）与4:3 双采（1080P 轮），与 DSL 官方实测口径（竖屏 416×736 + 英文）不是一个 profile；
480P 素材只判运镜，不判画质、人脸与美感；
标注 🟡 / ❌ 的镜头是「这次没做成」或「只做成一半」，不代表 H3 永远做不到——换种子、换画幅、挂 LoRA 都可能改变结果（F10 就是例子：4:3 出双主体，1.8:1 不出）。

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 H3 Camera Motion Lib AI skill do?

Why use H3 Camera Motion Lib on TypingMind?

Because you install it once and use it with any model. H3 Camera Motion Lib 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 H3 Camera Motion Lib in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/swan7-py/MiniMax-H3-Skills-Local/tree/main/h3-camera-motion-lib. 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 H3 Camera Motion Lib?

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 H3 Camera Motion Lib?

As many as you like. As long as a model supports skills, you can use H3 Camera Motion Lib with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the H3 Camera Motion Lib AI skill free?

It is published on GitHub by swan7-py. 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

Gemini

openclaw

OrganizationPopular

Gemini CLI one-shot prompts, summaries, generation, skills, hooks, MCP, or Gemma routing.

Writing Skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Skill Host Compat

Lint ECC skills for Codex/Cursor-safe frontmatter and Claude-only substitutions before a skill PR.

Brand Voice

Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that profile across content, outreach, and social workflows. Use when the user wants…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

H3 运镜提示词库

这个库解决什么

路由表：按你要的运镜查文件

三步用法

可信度声明（引用本库结论时必须一起写出）

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now