Agent skill

Animated Video

by asgeirtj in asgeirtj/system_prompts_leaks

“Timeline-based motion design”

— description from SKILL.md by asgeirtj
CC0-1.0Auto-check passedMedia & Creative

Install Animated Video

skills CLI
$ npx skills add asgeirtj/system_prompts_leaks --skill animated-video -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install asgeirtj/system_prompts_leaks animated-video --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/asgeirtj/system_prompts_leaks.git skills-src && mkdir -p .claude/skills && cp -r skills-src/Anthropic/claude-design/skills/animated-video .claude/skills/animated-video && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
animated-video
GitHub stars
69k
Token cost
~2.5k tokens
SKILL.md length
1,486 words
Files
1
Skills in repo
128
Repo updated
First seen
Licence
CC0-1.0

At a glance

  • Works in 3 steps: Write the OM_SCENES literal FIRST — it… → One helper component per section for… → Define exactly three motion helpers up…
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

About this skill

Animated Video is a skill in asgeirtj/system_prompts_leaks (69k stars). Its SKILL.md is about 2.5k tokens. Licence: CC0-1.0.

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Write the OM_SCENES literal FIRST — it is the piece's outline. Get {T, CUES} from useComposition() and key ALL choreography to T and…
  2. One helper component per section for readability, but ALL of them render ALL the time inside the one tree, keyed to cues — never…
  3. Define exactly three motion helpers up front (e.g. MOTION = {enter, draw, pop} wrapping Easing curves) and use no easing or transform…

What it can do on your machine

Read from SKILL.md and the folder at commit 60d44cc. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Animated Video loads about 2.5k tokens when it runs. Until then it costs about 11 tokens; SKILL.md has 1,486 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~11
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from asgeirtj/system_prompts_leaks at commit 60d44cc, republished under its CC0-1.0 licence (© asgeirtj). 1,486 words, ~2,530 tokens.

Download SKILL.mdSave it as .claude/skills/animated-video/SKILL.md (or your agent's skills folder).
name
animated-video
description
Timeline-based motion design
user-invocable
true

Animated video

Create an animated video or motion design piece rendered as an HTML page. Build a timeline-based animation with smooth transitions. Design frame-by-frame sequences with playback controls (play/pause, scrubber). Focus on visual storytelling with the Anthropic brand palette. Export-ready at a fixed aspect ratio (16:9 or 9:16). If you need to know the position of an element (eg to move a cursor or character between elements) use refs to grab the position.

ALWAYS build on the animations_v3.jsx starter for ANY animation piece — including one hosted on a design-components page (the helmet-script + x-import structure IS the starter case, not an exemption). The only exemptions: a minor animated accent inside a larger non-animation design, or the user explicitly asking you not to use the starter. Skipping the starter silently removes the user's timeline editor — scene trims, speed changes, and video export only exist when the page builds on the engine. Do NOT load animations.jsx or animations-v2.jsx alongside it (the engines share window globals — last wins). A project that already uses an older starter keeps it; don't migrate existing animations.

START by calling copy_starter_component with kind: "animations_v3.jsx" — the continuous-composition engine: the whole animation is ONE element tree rendered from one authored-time clock, so elements move, morph, and persist across section boundaries by ordinary interpolation — nothing mounts or unmounts at a boundary. It gives you <CompositionStage>, useComposition() (→ {T, CUES}), <Shot>, <Captions>, an Easing library, and interpolate() / animate() tweens. Read the file after copying.

THE AUTHORING CONTRACT (it's in the file's usage block; follow it exactly): declare the scene list as a JSON string literal in a plain inline <script> of the MAIN document — <script>window.OM_SCENES = '[{"name":"Opening","dur":3},…]';</script> (exact JSON.stringify formatting, no spaces) — NOT in a text/babel script and NOT in a sibling .jsx (only vanilla inline script literals are addressable for the editor's write-back); declare window.OM_PLAYBACK the same way; pass both through untouched as <CompositionStage scenes={window.OM_SCENES} playback={window.OM_PLAYBACK}> wrapping ONE component — the whole piece. The scene list is the user-control view (names, order, playback durations); the engine derives the cue table from it, so the literal is the single source of structure. The user edits timing on the host timeline — trim a scene's edge, or set a section's speed — and every edit writes back into your literal and reflows the composition live.

CUE-FIRST DISCIPLINE (this is what makes a piece read as one continuous video):

  1. Write the OM_SCENES literal FIRST — it is the piece's outline. Get {T, CUES} from useComposition() and key ALL choreography to T and CUES.SectionName (authored seconds) — never to your own clock, never to wall-clock time.
  2. One helper component per section for readability, but ALL of them render ALL the time inside the one tree, keyed to cues — never conditionally mounted per section. A shared element crossing a boundary is just motion whose start and end straddle a cue.
  3. Define exactly three motion helpers up front (e.g. MOTION = {enter, draw, pop} wrapping Easing curves) and use no easing or transform outside them; one caption element, one visible at a time (<Captions> has this built in).

TIMING IS USER-EDITABLE (time-stretch): when the user trims or speeds a section, the engine replays that section's SAME authored slice over the new playback length — choreography keyed to T retimes, never cuts off. Authored hard cuts are content now, not structure: wrap a shot's elements in <Shot from={CUES.X} to={CUES.Y}> (visibility flips at the cues; children stay mounted so images and videos hold their readiness). A looping piece shows its last authored frame immediately before its first — make them match.

Give every motion project a tweaks panel (kind: "tweaks_panel.jsx") whose TWEAK_DEFAULTS include "motionEditor": true with a <TweakToggle label="Motion editor"> wired to it. That key is the host timeline editor's visibility gate: the user flips it in the Tweaks panel to hide or show the editor bar, and the animation, its timing data, and export are untouched either way. Declare the TWEAK_DEFAULTS literal in a plain inline <script> of the MAIN document (the /EDITMODE-BEGIN/ convention), so the flip persists.

The stage renders inside <svg><foreignObject>; if a screenshot of it comes back black, that's a capture artifact — trust the live preview.

WATCH the video before calling it done: stills at hand-picked timestamps hide exactly the boundary bugs (pops, mistimed motion) that make a piece feel disjointed. Build a filmstrip with ONE multi_screenshot call — in each step's code, seek by dispatching new CustomEvent('data-om-seek-to-time-frame', {detail: {time: T, sync: true}}) on document.querySelector('[data-om-exportable-video-with-duration-secs]'), with T values straddling every scene boundary (boundary ±0.15s; boundaries are the running sums of your OM_SCENES durs) plus a mid-scene anchor or two (12-step cap per call — on long pieces spend the steps on boundaries). Two adjacent captures that don't visually match are a discontinuity to fix.

Animations are complex code! Make reusable JSX components for each visual element and each section. Invest in tweaking the timeline iteratively.

Animation tips:

  • Storytelling is KEY! Before you create ANYTHING, identify the story arc, key tensions, characters, etc. Align on the message you want to convey. Run it by the user.
  • Use good animation principles... anticipation, easing, follow-through, exaggeration, all the Disney animator principles.
  • Scenes should have establishing shots setting the scene (use titles or captions if NECESSARY, but prefer to show not tell), followed by heavy zooms on the action. (either hard cuts, or ken-burns-style zooms, or mouse-follows.) Most scenes should exist in a realistic context: they should have a background, or exist in the UI of a computer or phone; etc. Elements should generally not float in the aether.
  • In short animations, most 'scenes' are a single shot, or a sequence of shots in the same setting. Scenes may be slides (e.g. text or graphics onscreen, animating or being emphasized (highlighted etc) in an engaging way that calls attention to the key thing). Decide what the shot is going to be. Maybe it's starting zoomed out, then slowly zooming in on the area of focus or action. Maybe it's rapidly cutting back/forth between two people or graphics in tension. Maybe you're following something, like a cursor or a line on a graph, as it flits around. Be creative!
  • Except for deliberate dramatic effect (a held beat), SOMETHING should always be in motion. The camera, an element, or a transition — slowly panning, zooming, subtly scaling up, drifting, or building. A truly static frame reads as a bug. Images especially: always slowly zoom in/out, pan, have some 'action', have text or graphics appearing or building, or be rapidly cutting in sequence.
  • Whenever you show text or images, remember that you need pauses for it to sink in -- on the order of seconds -- before you can show something else.
Show full SKILL.md (389 more words)Show less

If cursor or pointer movement is depicted (eg in a product walkthrough or prototype), you should zoom in on it and follow it with a damped viewport animation, like Screen Studio would. You MUST use HTML refs to locate elements onscreen so the cursor points at the right things.

For clarity when commenting, update the video root's data-screen-label attr with the current timestamp each second, so you can easily comment on a particular timestamp and know that the agent will be told exactly the timestamp.

To make content the user can export as a video (Share → Export → Video):

IF YOU ARE BUILDING ON AN ANIMATIONS STARTER (animations_v3.jsx, or animations_v2.jsx in an older project; the normal case): the stage component (<CompositionStage> / <SceneStage>) ALREADY SATISFIES THIS ENTIRE CONTRACT — it owns the exportable attribute, the seek listener, the svg/foreignObject wrapper, and font inlining (animations_v2 additionally provides a <VideoSprite> helper for looped <video> clips). Do NOT add data-om-exportable-video-with-duration-secs to any element yourself. Adding it to a wrapper ABOVE the stage creates two nested exportable roots, and the export and timeline transport bind to the wrong (outer) one — playback control and export silently break.

Only for a page built WITHOUT the starter, implement the contract yourself:

  • Put data-om-exportable-video-with-duration-secs="<N>" on the ONE root element you want exported (N ≤ 300; longer is clamped). Exactly one element in the document may carry this attribute — never nest it.
  • That element MUST listen for the custom event data-om-seek-to-time-frame (detail: {time, frame}): on receipt, pause playback and synchronously render that exact timestamp so every visible child is at that point.
  • Nested <video> elements that should contribute audio must carry data-om-exportable-video-play-start, data-om-exportable-video-play-end (seconds into the source), and optionally data-om-exportable-video-play-speed; they loop within [start,end] at that speed and their audio is mixed into the export. Keep their visual frame in sync with the timeline yourself (set video.currentTime from the seek event / your clock).
  • For best results, make the root an <svg><foreignObject> wrapper and inline your @font-face rules into it once — the exporter then serializes the svg directly per frame (fast, pixel-perfect). A plain div works too, just slower (full-page snapshot per frame).

A page carrying this contract also gets a live timeline under the preview — the host scrubs and plays it by dispatching the same seek event, so treat every seek as pause-and-hold (don't resume your own clock until seeks stop arriving).

© asgeirtj, CC0-1.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in Anthropic/claude-design/skills/animated-video of asgeirtj/system_prompts_leaks.

Open the folder on GitHubat commit 60d44cc

Compare with similar skills

Animated Video next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Animated Video compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Animated Video this skillasgeirtj/system_prompts_leaks69k—~2.5kAutomated safety check: PassCC0-1.0
HyperFrames Animationheygen-com/hyperframes60k3 repos~2.1kAutomated safety check: PassApache-2.0
Slack GIF Creatoranthropics/skills180k29 repos~2kAutomated safety check: PassApache-2.0
Stitch to Remotion Walkthrough Videosgoogle-labs-code/stitch-skills8.5k6 repos~3.2kAutomated safety check: NotesApache-2.0
Faceless Explainer Videoheygen-com/hyperframes60k3 repos~7.7kAutomated safety check: NotesApache-2.0
Video ShotcraftVincentwei1021/video-shotcraft11k—~2.6kAutomated safety check: PassApache-2.0

Similar skills

  • HyperFrames Animation

    heygen-com/hyperframes

    Collects motion rules, scene blueprints, transitions and runtime adapters for HyperFrames video compositions, with GSAP as the default animation runtime.

    60k GitHub starsUsed in 3 repos~2.1k tokens
    Media & CreativeAuto-check passed
  • Slack GIF Creator

    anthropics/skills

    Official

    Provides Slack size and frame limits, Python animation helpers and validators for building animated GIFs sized for emoji and messages.

    180k GitHub starsUsed in 29 repos~2k tokens
    Media & CreativeAuto-check passed
  • Stitch to Remotion Walkthrough Videos

    google-labs-code/stitch-skills

    Official

    Builds walkthrough videos from Stitch design projects using Remotion, with transitions, zoom effects and text overlays on each screen.

    8.5k GitHub starsUsed in 6 repos~3.2k tokens
    Media & CreativeAuto-check: notes
  • Faceless Explainer Video

    heygen-com/hyperframes

    Turns an article, notes or a topic brief into an explainer video whose visuals are invented per scene, built frame by frame in HyperFrames with no footage.

    60k GitHub starsUsed in 3 repos~7.7k tokens
    Media & CreativeAuto-check: notes
  • Video Shotcraft

    Vincentwei1021/video-shotcraft

    Makes cinematic product videos with Remotion from shot recipe cards, a ready template, real page screenshots, camera moves and sound design, or builds a single animated shot.

    11k GitHub stars~2.6k tokensUpdated 6 days ago
    Media & CreativeAuto-check passed
  • Figma to HyperFrames

    heygen-com/hyperframes

    Imports Figma assets, brand tokens, components and motion into a HyperFrames video composition, using the Figma REST API with a connector or native export for shaders.

    60k GitHub starsUsed in 3 repos~4.5k tokens
    Media & CreativeAuto-check: notes

More from asgeirtj/system_prompts_leaks

All 125 skills in this repo
  • Fleet Manager for Agent Sessions

    asgeirtj/system_prompts_leaks

    Shows one digest of coding-agent sessions across your connected machines and lets you open, read, steer, approve, stop and close them, over Herdr, tmux or MSP.

    69k GitHub stars~2.5k tokensUpdated today
    Auto-check passed
  • Muse Code Product Doctor

    asgeirtj/system_prompts_leaks

    Diagnoses a Muse Code installation's own failures from binary and session evidence, instead of treating the report as an ordinary repository bug.

    69k GitHub stars~3.5k tokensUpdated today
    Auto-check passed
  • DOCX

    asgeirtj/system_prompts_leaks

    A skill your agent uses whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx).

    69k GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Agents Project Coordinator

    asgeirtj/system_prompts_leaks

    Runs a goal as a project in which the agent coordinates separate agent threads, judging when to split the work, and interviews you first when nothing can be verified.

    69k GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • Muse Plugin Creator

    asgeirtj/system_prompts_leaks

    Creates and validates a new native Muse plugin package in the current workspace, limited to five capability families, and leaves installation to you.

    69k GitHub stars~1.8k tokensUpdated today
    Auto-check passed
  • Deep Research

    asgeirtj/system_prompts_leaks

    A skill your agent uses when the user's prompt requires (1) researching a topic across multiple sources, comparing options or alternatives, analyzing trends or history, understanding markets or…

    69k GitHub stars~3.3k tokensUpdated today
    Auto-check passed

Questions about Animated Video

How do I install Animated Video in Claude Code?

Run `npx skills add asgeirtj/system_prompts_leaks --skill animated-video -a claude-code`. Or copy the skill folder (Anthropic/claude-design/skills/animated-video in asgeirtj/system_prompts_leaks) into .claude/skills/animated-video in your project. Claude Code loads it when a task matches its description.

How do I install Animated Video in Codex?

Run `npx skills add asgeirtj/system_prompts_leaks --skill animated-video -a codex`. Or copy the skill folder (Anthropic/claude-design/skills/animated-video in asgeirtj/system_prompts_leaks) into .agents/skills/animated-video in your project. Codex loads it when a task matches its description.

Can I use Animated Video in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add asgeirtj/system_prompts_leaks --skill animated-video -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/animated-video, .gemini/skills/animated-video, .github/skills/animated-video and .opencode/skills/animated-video in your project.

What does Animated Video need to run?

SKILL.md names no scripts, command-line tools or credentials: Animated Video is instructions for the agent only.

Does Animated Video access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Animated Video safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Animated Video use?

Animated Video is published under the CC0-1.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Animated Video use?

About 2.5k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Animated Video?

Skills that share tags, products or a category with Animated Video: HyperFrames Animation (heygen-com/hyperframes, 60k stars), Slack GIF Creator (anthropics/skills, 180k stars), Stitch to Remotion Walkthrough Videos (google-labs-code/stitch-skills, 8.5k stars) and Faceless Explainer Video (heygen-com/hyperframes, 60k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Animated Video?

asgeirtj (a GitHub user) maintains it in asgeirtj/system_prompts_leaks, which has 69,280 GitHub stars. The repository holds 128 skills in this directory. The repository was last updated on October 10, 2026.

Source: asgeirtj/system_prompts_leaks on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.