claude-motion-design-skillsSAFE
Motion design skills for Claude Code: storyboards, UI motion, kinetic typography, seamless loops, animation code, and export review.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Six practical skills for planning, implementing, and reviewing motion design with Claude Code.
Build clearer storyboards, purposeful UI transitions, readable kinetic typography, seamless loops, and editable animations. Each skill focuses on a distinct production stage and includes checks that separate written plans, working source, and visually verified exports.
These are workflow skills, not a video-generation model or an After Effects integration. They use the tools available in your environment. Rendering may require a browser, FFmpeg, a project renderer, or the application you choose; the pack itself does not install those tools or provide assets, fonts, or music.
The skills
fc8863fca62eOBSERVED · 2026-10-10Install
Commands as the repository documents them. They are shown, not run.
git clone https://github.com/Kyyzen0/claude-motion-design-skills.git
Host compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| claude-code | mentioned |
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: code-motion-build description: "Implement motion graphics as editable code using the available project stack and render a verifiable preview. Use for programmatic animations in web, SVG, canvas, Python, or an existing video-rendering framework." --- # Code Motion Build Turn the approved concept or supplied brief into editable animation source and a viewable result. ## Choose the execution path Inspect the project stack, installed versions, existing render command, and available assets. Honor a requested tool. For an existing project, extend its animation approach before proposing another library. For a new project, choose the simplest available stack that can produce the requested deliverable and explain the choice briefly. Do not claim an After Effects, Blender, or browser integration exists without verifying it. If the requested application is unavailable, make useful tool-independent planning progress and ask before substituting a different deliverable. Consult official documentation for unfamiliar or version-sensitive APIs. ## Structure the animation Separate composition dimensions, palette, typography, timing, and asset paths from scene logic where this makes iteration easier. Keep parameters few and meaningful. Derive state from explicit time or frame indices so seeking and rendering reproduce the same frame. Seed randomness and avoid dependency on network requests or wall-clock time during frame generation. Load fonts and assets before capture. Choose one time authority: do not combine a renderer's frame clock with independently advancing CSS animation or timers unless synchronization is intentional and verified. Clean up listeners, timers, GPU resources, and temporary DOM on lifecycle changes. Read [the implementation guide](references/implementation.md) for preview and capture pitfalls. ## Produce and verify Run the project's actual preview or render path. Inspect start, reveal, peak, settled, and final states plus playback at normal speed. Check destination size and frame rate. Inspect the output file itself rather than assuming that an exit code establishes successful visual output. Deliver editable source, the requested preview or export, and concise run instructions. If rendering is blocked, preserve the runnable source and identify the exact missing capability. Do not call source code a finished video.
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
fc8863fca62efull audit observations/trust-audit/skill/kyyzen0__claude-motion-design-skills.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-10 | fc8863fca62e | SAFE | B | 89 | first audit |
Questions
What does the claude-motion-design-skills skill do?
Motion design skills for Claude Code: storyboards, UI motion, kinetic typography, seamless loops, animation code, and export review.
Is claude-motion-design-skills safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can claude-motion-design-skills access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does claude-motion-design-skills work with?
Its documentation mentions claude-code. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (fc8863fca62e), read on 2026-10-10. The repository is watched, and a new audit runs when it changes — this is the first audit.