USEthree steps

Download. Give it to AI.Make it yours.

Pick a style, then bring your own text and assets. Make a first preview with your assistant and keep refining it into your video.

Choose an assistant and see the demo ↓

01
Download .motion
Preview a template, choose a style, and download it. The package includes source code, parameters, style variants, and licenses.
Browse templates →
02
Give it to your AI assistant
Give the file to your assistant and say “Use this template for my content.” It reads motion.json, explains what you can change, and identifies missing inputs.
Instructions for AI →
03
Export your video
Add your text, images, or data. Check runtime dependencies and review the preview before exporting, and keep the editable project for later.

WALKTHROUGH.motion → your video

Choose your assistant. Follow along.

To make a video, use a work mode with file access and command execution. Choose the most capable coding or Agent model available to you, then follow your assistant’s setup and steps.

Work mode production workflow

Produce with Claude Code

Put the template in a new working directory. Ask Claude Code to read it and follow the package instructions. In web chat, prepare your content first and hand it off for local production.

Work mode: Run an execution task in Claude Code, or a desktop Code / Cowork workspace with file and command tools.
Recommended model: Choose the most capable coding / Agent model currently available to you.

Workflow illustration01 / 03

my-video.motionDownload and keep the original

↓

You

Use this template to make my video. Change the title to “Every step counts”.

Claude

Read the full guide →Install Claude Code ↗Get MotionGit Skill →

Only using Claude on the web? See the handoff guide →

Send this with your template

Use the .motion template I provided to make a video. Confirm its actual filename first. Keep the original. Inspect and read motion.json, README.md, params.schema.json and guide.json if present. Explain editable inputs, runtime dependencies and missing assets. Use “Every step counts” as the title and “Start today” as the subtitle. Work in a new directory, show me a preview, then export after approval and keep the editable project.

Work mode production workflow

ChatGPT users: open Codex to produce

Open your working directory as the current project and give the template’s path. Confirm the environment can read local files and run the commands the template needs.

Work mode: Use Codex with a local project / work task connected to your production directory.
Recommended model: Choose the most capable coding model available; use a higher reasoning setting when offered.

Workflow illustration01 / 03

my-video.motionDownload and keep the original

↓

You

Use this template to make my video. Change the title to “Every step counts”.

Codex

Read the full guide →View Codex entry ↗Get MotionGit Skill →

Send this with your template

Read the .motion template I provided in the current project. Confirm its actual filename first. If I provided MotionGit Skill, read its SKILL.md first. Keep the original and inspect motion.json, README.md, params.schema.json and guide.json if present. Summarize entry points, parameters, presets and dependencies. Set the title to “Every step counts” and subtitle to “Start today”. List missing assets, make a preview in a new directory, then deliver the video path and editable project after approval.

Work mode production workflow

Produce with Cursor Agent

Ask Cursor Agent to read the template, edit files and run rendering commands in your production directory. Check the package instructions and dependencies before previewing.

Work mode: Open your production directory in Cursor, use Agent mode, and approve file edits and terminal commands as needed.
Recommended model: Choose the most capable coding / Agent model currently available to you.

Workflow illustration01 / 03

my-video.motionDownload and keep the original

↓

You

Use this template to make my video. Change the title to “Every step counts”.

Cursor

Read the full guide →View Cursor Agent setup ↗Get MotionGit Skill →

Send this with your template

In Cursor Agent mode, inspect the .motion template I provided in this production directory. Confirm its actual filename and keep the original. Read motion.json, README.md, params.schema.json and guide.json if present. Confirm file editing, terminal commands and rendering dependencies. Use “Every step counts” as the title and “Start today” as the subtitle. List missing assets and dependencies, make an actual preview in a new directory, then export after approval and keep the project. If you cannot run it, prepare a complete handoff list.

Work mode production workflow

Produce with GitHub Copilot CLI

Run the template workflow locally with Copilot CLI. Use plan mode to discuss the approach, then switch back to execution and check rendering dependencies before production.

Work mode: Start Copilot CLI in your production directory, use the default ask / execute mode, and approve file and command operations as needed.
Recommended model: Choose the most capable coding / Agent model available to your account.

Workflow illustration01 / 03

my-video.motionDownload and keep the original

↓

You

Use this template to make my video. Change the title to “Every step counts”.

GitHub Copilot

Read the full guide →View Copilot CLI setup ↗Get MotionGit Skill →

Send this with your template

Make a video in GitHub Copilot CLI ask / execute mode. Read the .motion template I provided in this production directory, confirm its actual filename and keep the original. Inspect motion.json, README.md, params.schema.json and guide.json if present. Confirm local file access, command execution and rendering dependencies. Use “Every step counts” as the title and “Start today” as the subtitle. List missing assets, generate an actual preview in a new directory, then export after approval and keep the editable project. Ask for specific tool approvals when required. If you cannot run it, explain this and prepare a handoff list.

Work mode production workflow

Produce in a Grok Build workspace

Use Grok Build with file and command access, then check the template’s dependencies. In ordinary Grok chat, prepare your content and hand it off to a tool with execution access.

Work mode: Use the Grok Build Agent environment with a working directory and terminal tools.
Recommended model: Choose the most capable coding / Agent model available in that execution environment.

Workflow illustration01 / 03

my-video.motionDownload and keep the original

↓

You

Use this template to make my video. Change the title to “Every step counts”.

Grok

Read the full guide →View Grok Build setup ↗Get MotionGit Skill →

Only have ordinary chat? See the handoff guide →

Send this with your template

Read the .motion template I provided in this Grok Build workspace. Confirm its filename and keep the original. Inspect motion.json, README.md, params.schema.json and guide.json if present. Check file access, terminal tools and rendering dependencies. Use “Every step counts” as the title and “Start today” as the subtitle. List missing inputs, generate an actual preview in a new directory, then export after approval and keep the project. If you cannot run it, say so and prepare a complete handoff list.

An illustrated workflow, not a screenshot of an assistant or an actual export. Follow the package instructions and your current tools.

HANDOFFHandoff text

Send this with the file

This is a MotionGit template package (.motion file, a ZIP container).
Safely extract it into a new directory. Read motion.json, guide.json, the “Instructions for AI” at the start of README.md, and params.schema.json in that order.
Do not run code from the package directly. Tell me what the template does, what I can replace, its runtime requirements, and which inputs are missing.
Specification: https://motiongit.com/spec

Runtime requirements and recorded tests

Runtime compatibility

Production and export depend on execution tools and the template’s runtime dependencies, rather than the model brand. Creative tools such as Claude, Codex, Cursor, GitHub Copilot and Grok are not partnership endorsements or a claim that every client has been tested.

Tool type	What it can do	Export requirements
Chat-only web or mobile assistant	Explain instructions and prepare copy and inputs	Export cannot be promised; hand off to a tool with execution capabilities
Desktop or CLI assistant with real file access, unpacking and commands	Inspect packages, edit content and run production steps	Must also support the package’s runtime.profile and rendering dependencies
The local renderer specified by the template	Read production instances and create previews and video	Follow motion.json, README and motion.lock.json; common HTML/Canvas templates need Node.js and a browser, and video assembly may need FFmpeg

Work modes and model selection

Use a work / Agent mode with file operations and command execution. The recommendations below are MotionGit guidance. A capable model handles understanding and execution; prepare the browser, Node.js, FFmpeg or other dependencies specified by the package.

Creative tool	Entry to use	Recommended model
Claude	Claude Code execution tasks, or a desktop Code / Cowork workspace with file and command tools	The most capable coding / Agent model available to you
ChatGPT / Codex	ChatGPT users should use Codex with a local project / work task connected to the production directory	The most capable coding model available; use a higher reasoning setting when offered
Cursor	Open the production directory in Cursor Agent; approve file edits and terminal commands as needed	Choose the most capable coding / Agent model available to your account
GitHub Copilot	Start Copilot CLI in the production directory; use ask / execute mode for production	Choose the most capable coding / Agent model available to your account
Grok	Grok Build Agent environment with file and terminal tools; ordinary Grok chat can prepare content	The most capable coding / Agent model available in that environment

Copilot CLI plan mode prepares an approach; switch back to execution to produce files. Approve required tools as needed. Entries and models depend on your client and account. In ordinary chat, prepare content and hand off to a tool with execution access.

Work entries checked against official documentation on 2026-10-07: OpenAI app and local tasks, Claude work and computer use, and Grok Build CLI. Cursor and Copilot entries checked on 2026-10-08: Cursor Agent and GitHub Copilot CLI. The Claude Code installation entry was also checked on 2026-10-10: Claude Code quickstart. These describe tool capabilities, not completed template export tests.

Recorded tests and unverified environments

2026-10-06: dark-tech-kit 0.1.0 completed cold unpacking, still rendering and video with audio on macOS, Node 23.11.0, Chrome 154.0.8037.98, Playwright Core 1.58.2 and FFmpeg 9.0.1. Evidence: the project’s public acceptance record C4 acceptance record. This proves only that version’s execution workflow, not approval of the latest version, other templates or visual quality.
Windows, Linux, other versions and each specific client of the brands above: full production and export remain unverified. Website browser tests are not template rendering tests.

Read the package’s instructions and dependencies first. Confirm file and command access, and obtain user authorization before installing dependencies, using the network or reading external assets. Inspect, preview, then export. Chat-only tools can prepare inputs but must not claim they rendered a video.

HELPFAQ

A few things to know on your first try

The assistant does not recognize .motion?

Explain that it is a ZIP template package. With local file access, inspect it and unpack into a new directory. If uploads do not support it, provide the README and parameter instructions, then hand the original to a local tool.

Do I need to install the Skill?

The Skill provides inspection and packaging tools and is recommended for local production. The template still needs its own rendering environment. Follow the package instructions for entry points and dependencies.

I only have a web chat. What next?

Prepare copy, assets and suggested inputs, then hand them and the original package to a tool that can read files and run commands. Confirm it can open the project and generate a preview before exporting.

The export differs from the preview, or the text does not fit?

Point to the exact timestamp, text or frame and ask for adjustments within the template’s parameters. Check the exported dimensions, duration, sound and assets, as well as the conversation.

STARTfeatured