Skip to content
Back to search

motion-prompt

MarketplaceWorks with Claude CodeGitHub

Marketplace for the Motion Prompt skill (gallery: showheyohtaki.github.io/motion-prompt)

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

Its scripts were only partly scanned.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/showheyohtaki/motion-prompt with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/showheyohtaki/motion-prompt'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/showheyohtaki--motion-prompt/badge.svg)](/listings/showheyohtaki--motion-prompt)

HTML

<a href="/listings/showheyohtaki--motion-prompt"><img src="/api/listings/showheyohtaki--motion-prompt/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

**With a prompt.** Paste this into Claude Code or Codex:

Read https://github.com/showheyohtaki/motion-prompt and install the motion-prompt skill in this environment. When it is installed, tell me how to use it in three lines.

**With a command.** This uses the `skills` installer, which works with Claude Code, Codex and other agents that read Agent Skills:

npx skills add showheyohtaki/motion-prompt

**As a Claude Code plugin.**

/plugin marketplace add showheyohtaki/motion-prompt
/plugin install motion-prompt@motion-prompt

**By hand.** Copy the `skills/motion-prompt` folder to one of these places:

| Location | Scope | |---|---| | `~/.claude/skills/` | Claude Code, all projects | | `~/.agents/skills/` | Codex and others, all projects | | `.claude/skills/` in a project | Claude Code, that project only | | `.agents/skills/` in a project | Codex and others, that project only |

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 16 lines
  1. {
  2. "name": "motion-prompt",
  3. "description": "Marketplace for the Motion Prompt skill (gallery: showheyohtaki.github.io/motion-prompt)",
  4. "owner": {
  5. "name": "Shohei Ohtaki",
  6. "url": "https://x.com/showheyohtaki"
  7. },
  8. "plugins": [
  9. {
  10. "name": "motion-prompt",
  11. "source": "./",
  12. "description": "A library of names to use with AI (motion-graphics moves, camera moves and transitions, UI components, landing-page and web effects, photo looks and lighting, art styles for image generation, diagrams and charts for slides), each with a moving sample. Ask the agent to open the library, pick in the browser, and it applies your picks to your video, web or image project with the published timings and easing.",
  13. "category": "design"
  14. }
  15. ]
  16. }
README.md · README · 266 lines
  1. # Motion Prompt
  2. **English** | [日本語](README.ja.md)
  3. > 日本語の説明は [README.ja.md](README.ja.md) にあります。
  4. > 中文用户:所有名称一览都有简体中文和繁體中文版本,见 [`packs/`](packs/README.md)。
  5. > En español: todas las listas de nombres están en español en [`packs/`](packs/README.md).
  6. > The name lists are in English, Japanese, Spanish, Simplified Chinese and Traditional Chinese (see [`packs/`](packs/README.md)); the gallery is in English and Japanese. For another language, give [`make-your-own/prompts/en/01-translate.md`](make-your-own/prompts/en/01-translate.md) to a coding AI.
  7. A library of names for the things you ask an AI to make. Each name comes with a moving sample, a one-line meaning and an example of how to ask for it. Ten sets are in it now, 24 names each and 240 in all: motion-graphics moves (`motion`), camera moves (`camera`), UI component names (`ui`), landing page and web effects (`lp`), photo looks, lighting and styles (`photo`), motion-graphics moves, part 2 (`motion2`), landing page and web effects, part 2 (`lp2`), camera moves and transitions, part 2 (`camera2`), art styles for image generation (`artstyle`), and diagrams and charts for slides (`diagram`). It also comes with the prompts to make the same kind of library for your own field, in your own language.
  8. | Motion graphics | Camera moves |
  9. |---|---|
  10. | ![Motion graphics names 01–08](assets/preview-motion.gif) | ![Camera move names 01–08](assets/preview-camera.gif) |
  11. - Gallery (every sample, moving): https://showheyohtaki.github.io/motion-prompt/
  12. - Name lists you can read here on GitHub: [`packs/`](packs/README.md)
  13. - Examples from other people who share names with samples (embeds and links to their posts on X): https://showheyohtaki.github.io/motion-prompt/found.html
  14. ## Why I made this
  15. I posted a few short videos that put names to motion-graphics moves and camera moves, and over the next few days a lot of comments came in. One of them said, in essence, that what had been holding them back was not a lack of imagination. It was not knowing what this kind of movement is called.
  16. Reading that, I thought: if people who know their field, in many languages, laid out the "common language" you need to work well with AI as a library you can look through, it would be really useful. So I tried making that as a GitHub repository.
  17. This is not one style to copy. It is a place where you can use the prompts and instructions here to make motion graphics like these, and to make the same kind of name samples for your own field, in your own language, with whatever look you like.
  18. Another comment said: "this is how you become a creative director". Exactly. I think it would be a wonderful thing if there were more creative directors all over the world, doing great work together with AI.
  19. Shohei Ohtaki
  20. ## The names in here now
  21. | Numbers | Pack | Names | Lists |
  22. |---|---|---|---|
  23. | 001–024 | `motion`: motion graphics moves | 24 | [English](packs/motion/README.md) · [日本語](packs/motion/README.ja.md) · [Español](packs/motion/README.es.md) · [简体中文](packs/motion/README.zh-Hans.md) · [繁體中文](packs/motion/README.zh-Hant.md) |
  24. | 025–048 | `camera`: camera moves and transitions | 24 | [English](packs/camera/README.md) · [日本語](packs/camera/README.ja.md) · [Español](packs/camera/README.es.md) · [简体中文](packs/camera/README.zh-Hans.md) · [繁體中文](packs/camera/README.zh-Hant.md) |
  25. | 049–072 | `ui`: UI component names | 24 | [English](packs/ui/README.md) · [日本語](packs/ui/README.ja.md) · [Español](packs/ui/README.es.md) · [简体中文](packs/ui/README.zh-Hans.md) · [繁體中文](packs/ui/README.zh-Hant.md) |
  26. | 073–096 | `lp`: landing page and web effects | 24 | [English](packs/lp/README.md) · [日本語](packs/lp/README.ja.md) · [Español](packs/lp/README.es.md) · [简体中文](packs/lp/README.zh-Hans.md) · [繁體中文](packs/lp/README.zh-Hant.md) |
  27. | 097–120 | `photo`: photo looks, lighting and styles | 24 | [English](packs/photo/README.md) · [日本語](packs/photo/README.ja.md) · [Español](packs/photo/README.es.md) · [简体中文](packs/photo/README.zh-Hans.md) · [繁體中文](packs/photo/README.zh-Hant.md) |
  28. | 121–144 | `motion2`: motion graphics moves, part 2 | 24 | [English](packs/motion2/README.md) · [日本語](packs/motion2/README.ja.md) · [Español](packs/motion2/README.es.md) · [简体中文](packs/motion2/README.zh-Hans.md) · [繁體中文](packs/motion2/README.zh-Hant.md) |
  29. | 145–168 | `lp2`: landing page and web effects, part 2 | 24 | [English](packs/lp2/README.md) · [日本語](packs/lp2/README.ja.md) · [Español](packs/lp2/README.es.md) · [简体中文](packs/lp2/README.zh-Hans.md) · [繁體中文](packs/lp2/README.zh-Hant.md) |
  30. | 169–192 | `camera2`: camera moves and transitions, part 2 | 24 | [English](packs/camera2/README.md) · [日本語](packs/camera2/README.ja.md) · [Español](packs/camera2/README.es.md) · [简体中文](packs/camera2/README.zh-Hans.md) · [繁體中文](packs/camera2/README.zh-Hant.md) |
  31. | 193–216 | `artstyle`: art styles for image generation | 24 | [English](packs/artstyle/README.md) · [日本語](packs/artstyle/README.ja.md) · [Español](packs/artstyle/README.es.md) · [简体中文](packs/artstyle/README.zh-Hans.md) · [繁體中文](packs/artstyle/README.zh-Hant.md) |
  32. | 217–240 | `diagram`: diagrams and charts for slides | 24 | [English](packs/diagram/README.md) · [日本語](packs/diagram/README.ja.md) · [Español](packs/diagram/README.es.md) · [简体中文](packs/diagram/README.zh-Hans.md) · [繁體中文](packs/diagram/README.zh-Hant.md) |
  33. Each list gives the number, the name, what it means and an example of how to ask an AI for it, in English, Japanese, Spanish, Simplified Chinese and Traditional Chinese. The same names move in the [gallery](https://showheyohtaki.github.io/motion-prompt/).
  34. Each pack has its own look. The motion and motion2 packs are dark navy with four colors. The camera and camera2 packs are light gray with one blue. The ui pack is warm off-white with black and one blue, and a cursor sets each part moving. The lp and lp2 packs draw a white browser window on a pale gray desk, with a vermilion accent and blue for the pictures on the page. The photo pack has no shared palette: each card is painted in the colors of its own scene, and the effect fades in and back out so you can compare. The artstyle pack is the one pack with pictures instead of drawings: the same base sketch was given to an image model and redrawn in each style, and a diagonal wipe turns the sketch into the style. The diagram pack draws on pale gray in flat grays and three blues, and each card builds its diagram or chart piece by piece, holds it, and clears it again. That is on purpose. What a pack has to get right is the names, not a house style.
  35. ## Three ways to use it
  36. ### 1. Open the library, pick, and send your picks to your AI
  37. With the `motion-prompt` skill installed in Claude Code or Codex, asking is enough to open this gallery. You do not need to remember names or numbers. When you are not sure what something is called, have the library opened, the way you would look a word up in a dictionary.
  38. ```sh
  39. npx skills add showheyohtaki/motion-prompt
  40. ```
  41. 1. Ask your AI:
  42. ```text
  43. Open the motion-prompt library.
  44. ```
  45. 2. The gallery opens in your browser. Press "Pick" on the samples you want, as many as you like. The note field at the bottom of the screen takes a short line such as "for the opening title".
  46. 3. Press "Send to AI" and your picks reach the AI. Go back to it and say what you want done:
  47. ```text
  48. Edit the opening of this video like this.
  49. ```
  50. The agent uses only what you picked. It fetches their specs and reference code and builds them into your video or site the way your project works. Name a kind, as in "show me the camera moves", and the gallery opens filtered to that field's packs (part 1 and part 2 together where there is one).
  51. For an AI without the skill, pick in the gallery, press "Copy picks" at the bottom of the screen and paste the text into the chat. It includes the demo and spec URLs.
  52. **When you know the numbers**, you can skip the gallery and ask by number:
  53. ```text
  54. Use the motion-prompt skill with #012 and #045 to make this product video look professional.
  55. ```
  56. ```text
  57. Replace the part where the title appears with #005 from motion-prompt. Keep the length and the transitions before and after it.
  58. ```
  59. ```text
  60. Turn the camera move in motion-prompt #032 into an English prompt for Veo. The subject is a coffee cup on a desk.
  61. ```
  62. Other ways to install, and what the agent does, are in [Skill reference](#skill-reference) below.
  63. ### 2. Look up the name and say it to your AI
  64. Open a [list](packs/README.md) or the gallery, find the thing you have in mind, and use its name in your prompt. Adding how long, how strong and what moves makes the result closer to what you want.
  65. ```text
  66. Bring the title in with a mask reveal from below, 0.6 s, each line slightly after the one before.
  67. ```
  68. ```text
  69. Slow dolly in toward her face; move the camera, do not zoom.
  70. ```
  71. No install is needed for this. The names work in a coding AI, a video-generation model or a brief to a person.
  72. ### 3. Make a version for your own field or language
  73. [`make-your-own/`](make-your-own/README.md) has copy-and-paste prompts for a coding AI, a script that renders the videos, and the two finished examples (HTML source, three videos and a cheat-sheet image each).
  74. | Goal | Prompt |
  75. |---|---|
  76. | The same videos in another language | [`01-translate.md`](make-your-own/prompts/en/01-translate.md) |
  77. | The names of your own field, with your own look | [`02-your-own-field.md`](make-your-own/prompts/en/02-your-own-field.md) |
  78. | The one-page cheat-sheet image | [`03-cheatsheet-image.md`](make-your-own/prompts/en/03-cheatsheet-image.md) |
  79. The field does not have to be video. Lighting, sound, UI, photography, cooking, architecture: any field where knowing the name is what lets you ask for the thing.
  80. ## Add the names of your field
  81. If you know a field well, please add its common language here, in your language. [CONTRIBUTING.md](CONTRIBUTING.md) explains how to add a pack or add a language to an existing pack, and what a name needs before it goes in. A coding AI can do most of the building with the prompts above.
  82. ## Original posts
  83. The videos this started from (X, in Japanese):
  84. - https://x.com/showheyohtaki/status/2108065874511077598
  85. - https://x.com/showheyohtaki/status/2109112248832503895
  86. - https://x.com/showheyohtaki/status/2109840044554891464
  87. The set from the first post (names of animations for websites and landing pages) is not in this repository yet. The `lp` pack is a different set. Some names overlap with that post (parallax, scroll snap and others), but the selection and the samples were made new for this repository. The `ui` pack is based on "UIパーツ名24" (24 UI part names), posted on X on October 10, and `photo` was also made new for this repository.
  88. ## Skill reference
  89. Node.js 18 or later is required.
  90. ### Install
  91. **With a prompt.** Paste this into Claude Code or Codex:
  92. ```text
  93. Read https://github.com/showheyohtaki/motion-prompt and install the motion-prompt skill in this environment. When it is installed, tell me how to use it in three lines.
  94. ```
  95. **With a command.** This uses the `skills` installer, which works with Claude Code, Codex and other agents that read Agent Skills:
  96. ```sh
  97. npx skills add showheyohtaki/motion-prompt
  98. ```
  99. **As a Claude Code plugin.**
  100. ```text
  101. /plugin marketplace add showheyohtaki/motion-prompt
  102. /plugin install motion-prompt@motion-prompt
  103. ```
  104. **By hand.** Copy the `skills/motion-prompt` folder to one of these places:
  105. | Location | Scope |
  106. |---|---|
  107. | `~/.claude/skills/` | Claude Code, all projects |
  108. | `~/.agents/skills/` | Codex and others, all projects |
  109. | `.claude/skills/` in a project | Claude Code, that project only |
  110. | `.agents/skills/` in a project | Codex and others, that project only |
  111. ### Install steps for agents
  112. This section is for an AI agent that received the prompt in "With a prompt".
  113. 1. Check that Node.js 18 or later is available with `node --version`.
  114. 2. In the user's project folder, run the command below. If it asks which agent to install for, choose the one you are.
  115. ```sh
  116. npx skills add showheyohtaki/motion-prompt -y
  117. ```
  118. 3. If step 2 is not possible, fetch the repository and copy the folder. Copy to `.claude/skills/` if you are Claude Code and to `.agents/skills/` otherwise (or to `~/.claude/skills/` or `~/.agents/skills/` for all projects).
  119. ```sh
  120. git clone --depth 1 https://github.com/showheyohtaki/motion-prompt.git /tmp/motion-prompt
  121. mkdir -p .claude/skills
  122. cp -R /tmp/motion-prompt/skills/motion-prompt .claude/skills/
  123. ```
  124. 4. Confirm the install. Replace `<skill-dir>` with the path where the skill was installed (the one with `SKILL.md` in it). It worked if the data source and the element count are printed.
  125. ```sh
  126. node <skill-dir>/scripts/motion-prompt.mjs info
  127. ```
  128. Exit code 3 means the data source could not be reached. Get network permission and run it again.
  129. 5. Read `<skill-dir>/SKILL.md` and tell the user how to use the skill in three lines. For example:
  130. - Say "open the motion-prompt library" and the gallery opens. Press "Pick" on what you want, then "Send to AI".
  131. - Then say what to do with them, for example "edit the opening of this video like this".
  132. - If you know the numbers, you can also ask directly: "use #012 and #045".
  133. Do not change existing settings files or other skills.
  134. ### What the agent does
  135. - When you ask for the library, it opens the gallery in your browser and waits (up to 15 minutes) until you pick and press "Send to AI".
  136. - It works out how your project produces video: Canvas, Remotion, CSS, After Effects, or prompts for a video-generation model.
  137. - It uses what you picked, or the numbers you gave, and nothing else. When you have not chosen, it suggests opening the gallery; if you ask it to choose, it searches the catalog for each scene.
  138. - It rebuilds those moves in your project. Timings, easing and amounts stay as published, while the words, colors and images become yours.
  139. - Its reply ends with a list of the numbers it used, the scene each went into, what it changed, and a link to each sample.
  140. ### How it works
  141. - One element is one function, `cells[i](ctx, w, h, u)`. `ctx` is a Canvas 2D context, `w` and `h` are the card size, and `u` is the time in seconds within the cycle.
  142. - The picture depends only on `u`. The function does not read the clock or use random numbers when it draws, so live playback and frame-by-frame rendering give the same frames.
  143. - Colors, sizes, the cycle length and shared helper functions are collected in a "kit" for each pack. An element needs the kit of its pack.
  144. - There are no external libraries.
  145. Three files make up the skill: the instructions (`SKILL.md`), notes on moving an element into each kind of video project (`references/porting.md`), and a Node script that looks elements up (`scripts/motion-prompt.mjs`, standard library only).
  146. | Command | What it does |
  147. |---|---|
  148. | `pick` / `pick --pack camera` | opens the gallery and prints what arrives with "Send to AI": numbers, names, specs and your note. Waits up to 15 minutes |
  149. | `search typewriter text` / `search 文字 登場` | finds elements for a scene (English or Japanese words) |
  150. | `list` / `list --pack motion` | an overview of all packs, or one pack listed element by element |
  151. | `get 12 #045` | prints the spec and then the code for those numbers (8 at most in one call) |
  152. | `kit motion` | the shared code of a pack |
  153. | `prompt 12` | the copy-paste prompt for an element |
  154. | `info` | shows where data is coming from, how much there is, and where it is cached |
  155. The script makes GET requests for the text files below and nothing else. Nothing from your project is uploaded. `pick` also opens a temporary listener on your own machine (127.0.0.1) that receives only the numbers and note sent by "Send to AI" in the gallery.
  156. 1. `https://showheyohtaki.github.io/motion-prompt/api/v1/`
  157. 2. if that is unreachable: `https://raw.githubusercontent.com/showheyohtaki/motion-prompt/main/api/v1/`
  158. | File | Contents |
  159. |---|---|
  160. | `catalog.json` | version, count, packs, and every element's names, meaning, summary, spec and tags |
  161. | `{ja,en}/catalog.tsv` | the index as tab-separated text (id, pack, category, title, tags, summary) |
  162. | `{ja,en}/e/{id}.txt` | a single element: attribution line, what it shows, the spec, then its code |
  163. | `{ja,en}/p/{id}.txt` | the copy-paste prompt for one element |
  164. | `kit/{pack}.js` | the shared code of a pack |
  165. If you clone this whole repository, the CLI reads the local `api/v1` first and needs no network. Downloaded data is kept on disk, and the saved copy is used when the source cannot be reached.
  166. | Variable | Default |
  167. |---|---|
  168. | `MOTION_PROMPT_BASE` | read from here instead of the default sources: a local folder or a URL, several separated by commas |
  169. | `MOTION_PROMPT_CACHE` | where downloads are kept; `~/.cache/motion-prompt`, or the system temp folder when the home folder is read-only |
  170. | `MOTION_PROMPT_TTL` | how long a saved catalog is trusted, in seconds; `21600` (6 hours) |
  171. ### Run the gallery yourself
  172. ```sh
  173. git clone https://github.com/showheyohtaki/motion-prompt.git
  174. cd motion-prompt
  175. python3 -m http.server 8000
  176. ```
  177. Open `http://localhost:8000/` to see the gallery (`index.html`). In a clone, `node skills/motion-prompt/scripts/motion-prompt.mjs pick --local` opens your local copy of the gallery for picking. The file formats are described in [FORMAT.md](FORMAT.md).
  178. ## License
  179. [MIT](LICENSE) © 2026 Shohei Ohtaki
  180. Commercial use is allowed, for the code, the videos and the images. When you use an element's code, keep its first line (`// Motion Prompt #ID · MIT License (c) 2026 Shohei Ohtaki · …`).
  181. To ask for something to be removed or corrected, use the [removal or correction form](https://github.com/showheyohtaki/motion-prompt/issues/new?template=3-removal.yml). We act on it as soon as the request is confirmed.
  182. ## Acknowledgements
  183. The idea of pairing a gallery of live examples with an agent skill comes from [Lucian UX/UI Prompt](https://lucianlabs.dev/uxui-prompt/). The CLI's command set and the layout of the static data files follow that project too; see [THIRD-PARTY-NOTICES.md](THIRD-PARTY-NOTICES.md).
  184. The name lists in other languages began with translations from [@daddydanielt](https://github.com/daddydanielt) (Traditional Chinese), [@herberthcr](https://github.com/herberthcr) (Spanish) and [@xhonye](https://github.com/xhonye) (Simplified Chinese). Thank you.
  185. ## Author
  186. Shohei Ohtaki (株式会社デイトラ) / X [@showheyohtaki](https://x.com/showheyohtaki)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.