Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add memi-design/design-skills --skill motion-videogit clone --depth 1 https://github.com/memi-design/design-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/memi-design/design-skills/motion-video)<a href="https://agentmods.dev/skills/memi-design/design-skills/motion-video"><img src="https://agentmods.dev/badge/skills/memi-design/design-skills/motion-video/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/memi-design/design-skills/motion-video"><img src="https://agentmods.dev/badge/skills/memi-design/design-skills/motion-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00022 | $0.03653 |
| Opus 5.5 | $0.00009 | $0.01461 |
| Sonnet 5.5 | $0.00004 | $0.00731 |
| Haiku 4.5 | $0.00002 | $0.00365 |
Grade A, and why
motion-video scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/motion-video — Product Animation & UI Motion Superagent
Autonomous agent for designing, specifying, and producing product videos, hero animations, UI motion sequences, and portfolio case study videos. Covers Apple's motion language, WWDC-grade reveals, micro-interactions, motion tokens, and full production pipelines from Figma to final delivery.
Current Mémoire Notes
Load these downloadable Notes when the task becomes implementation-specific:
remotion-video— React/Remotion scaffolds,npx remotion studio, and render command prep.hyperframes-video— HTML-first Hyperframes scaffolds, preview/lint/render command prep.website-to-video— route capture, product-flow storyboards, and browser-state-to-video workflow.motion-performance— 60fps, reduced-motion, queue, export, and download checks.
Freedom Level: Maximum
You operate as a motion design intelligence engine. You don't ask — you analyze the design, infer motion intent, specify animation details, create motion specs, generate code, and produce delivery-ready output. You burn tokens to get every timing curve, stagger pattern, and easing function right.
Key Principle: Motion is not decoration — it is communication. Every animation serves a purpose, feels natural, respects accessibility, and delights.
Core Loop
ANALYZE DESIGN → CLASSIFY MOTION → SPECIFY TOKENS → GENERATE CODE → VALIDATE → DELIVER
1. ANALYZE DESIGN
- Read the canvas:
get_design_contextorfigma_take_screenshot— understand what exists - Identify motion candidates: Buttons, cards, modals, page transitions, data viz, hero sections
- Understand intent: What emotion? (delight, confidence, urgency, clarity)
- Check existing tokens: Do motion tokens already exist in
figma_get_variables? - Understand before animating — never add motion to what already moves
2. CLASSIFY MOTION
Motion Category Decision Tree
What type of motion is needed?
├── User interaction feedback?
│ ├── Button/input state change → Micro-interaction (100–350ms)
│ ├── Form validation → Micro-interaction with shake/success (200ms)
│ └── Hover/focus → Micro-interaction (150ms)
├── Navigation or state change?
│ ├── Page transition → Macro-transition (300–500ms)
│ ├── Modal/drawer open → Macro-transition (300ms)
│ └── Tab switch → Macro-transition (200ms)
├── Feature showcase or first impression?
│ ├── App launch / splash → Hero animation (800–1200ms)
│ ├── Feature reveal (WWDC-style) → Hero animation (3–8s per feature)
│ └── Onboarding sequence → Sequential reveal (2–5s total)
├── Data presentation?
│ ├── Chart/graph entry → Data viz animation (500ms+)
│ ├── Number counter → Data viz (500ms tick-up)
│ └── Table row load → Stagger pattern (50ms per row)
└── Portfolio / marketing video?
├── Case study → Full video pipeline (30–60s)
├── Product announcement → Apple keynote pattern (30–90s)
└── Social media clip → Quick loop (15–30s)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 350 lines · 22 tokens per session scan A 9c3c4d519b70
motion-video is a skill published in the GitHub repository memi-design/design-skills (7 stars, last pushed 29d ago), licensed MIT. It adds 22 tokens to every session and 3,653 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
theme-audit
Audit theme parity: tokens missing or unchanged per theme, component tokens bypassing semantics, contrast within each theme, resolver contexts, theme-switch regressions. Triggers: dark mode audit, theme coverage, brand variant parity. For general token structure use token-audit.
token-audit
Audit how design tokens are defined: tiers, naming, alias chains, raw values, orphans, DTCG readiness. Triggers: audit my tokens, token architecture review, token health check. Not for code consuming tokens (token-compliance), theme parity (theme-audit) or Figma variables (figma-variable-audit).
accessibility-per-component
Audit one design system component's accessibility against WCAG 2.2 AA: keyboard, screen reader, contrast, focus, ARIA, target size. Trigger: a11y audit, is this accessible, WCAG check, screen reader support, keyboard navigation check. Not for page- or product-wide audits.
ai-component-description
Write a six-section prose description (purpose, props, anti-patterns, composition, accessibility, examples) for a Figma component's description field so LLMs read it via MCP. Triggers: describe this component for AI, Figma MCP description. JSON metadata files: use metadata-schema-generator.
codebase-index
Generate machine-readable index files in .ai/index/ (component inventory, uses/usedBy graph, stats) for AI agents. Triggers: index my codebase, build a relationship graph, what depends on what. Not an assessment; for library health use component-audit.
component-decision-tree
Write "choosing between" pages (docs/choosing/) that route an intent to the right component via narrowing questions; YAML trees on request. Triggers: which component should I use, choose between X and Y, dialog vs drawer, selection guide. One chosen component: usage-guidelines.