Communitygithub.com

OneWave-AI/claude-skills

Generate animated videos and motion graphics from natural language descriptions. Creates a standalone Vite + React project with Framer Motion scenes that auto-play in the browser. Use when the user wants to create animations, motion graphics, video intros, animated presentations, or product demos.

claude-skills란 무엇인가요?

claude-skills is a Claude Code agent skill that generate animated videos and motion graphics from natural language descriptions. Creates a standalone Vite + React project with Framer Motion scenes that auto-play in the browser. Use when the user wants to create animations, motion graphics, video intros, animated presentations, or product demos.

지원 대상✓Claude Code~Codex CLI~Cursor✓Gemini CLI
npx skills add https://github.com/OneWave-AI/claude-skills/tree/HEAD/animate

즐겨 사용하는 AI에게 물어보기

이 에이전트 스킬이 미리 로드된 새 채팅을 엽니다.

문서

Animation Generator

Create animated videos and motion graphics from a natural language description. Outputs a standalone Vite + React + Framer Motion project that plays in the browser.

Workflow

Step 1: Parse the Request

Break the user's description into a scene plan:

  • 3-7 scenes, each 3-5 seconds long
  • Identify the story arc: hero/intro, problem, solution, features, CTA/outro
  • Pick a color palette and typography that fits the brand/mood
  • Use $ARGUMENTS for the user's animation description

Step 2: Choose the Animation Stack

Auto-detect the best approach based on the request:

Request TypeStackWhen to Use
Product intro, presentation, marketingFramer Motion (default)Scene-based with text, icons, transitions
Generative art, particles, patternsp5.jsCreative/algorithmic visuals
3D objects, environments, product rendersThree.js + react-three-fiber3D scenes needed
Simple text/logo animationCSS animations onlyMinimal, no heavy deps

Default to Framer Motion unless the request clearly needs something else.

Step 3: Scaffold the Project

  1. Create a directory: ~/animations/[project-name]/
  2. Run the scaffold script: bash ~/.claude/skills/animate/scripts/scaffold.sh [project-name] [stack]
  3. Copy template files from ~/.claude/skills/animate/assets/template-files/ into the project

Step 4: Generate Scene Components

Read the references for animation presets and scene patterns:

  • references/animation-presets.md — all available transitions, springs, easings
  • references/scene-patterns.md — example scene code patterns

For each scene, create a React component in client/src/components/video/video_scenes/:

  • Use motion.div with scene transition presets (fadeBlur, scaleFade, slideLeft, splitHorizontal, morphExpand, etc.)
  • Use containerVariants and itemVariants for staggered content reveals
  • Use vw units for responsive sizing (works at any resolution)
  • Use CSS variables for theming (var(--color-accent), var(--color-bg-dark), etc.)
  • Use Lucide icons for visual elements
  • Use .glass-panel class for frosted glass cards
  • Use .text-gradient and .text-gradient-accent for gradient text

Step 5: Generate the VideoTemplate

Create client/src/components/video/VideoTemplate.tsx:

  • Import all scene components
  • Define SCENE_DURATIONS object (scene name -> milliseconds)
  • Use useVideoPlayer hook to manage scene advancement
  • Wrap scenes in AnimatePresence mode="wait" for smooth transitions
  • Each scene renders conditionally based on currentScene index

Step 6: Customize Theme

Update client/src/index.css with the right colors:

  • If the user specified brand colors, update CSS variables
  • Choose fonts that match the mood (Space Grotesk for tech, Playfair Display for elegant, etc.)
  • Update gradient and glow styles to match the palette

Step 7: Gemini 3.1 Pro Enhancement (Optional)

If GEMINI_API_KEY environment variable is available:

  1. Read references/gemini-integration.md for API details
  2. Send the user's description to Gemini 3.1 Pro asking for:
    • Scene breakdown with descriptions and suggested transitions
    • Color palette as CSS variables
    • Copy/headlines for each scene
    • SVG graphics if applicable
  3. Use the Gemini output to inform scene generation
  4. If no API key, skip this step — Claude handles all creative decisions directly

Step 8: Build and Preview

cd ~/animations/[project-name]
npm install
npm run dev

Tell the user the animation is running at http://localhost:5173 and open it in the browser.

Scene Transition Reference (Quick)

Pick transitions that match the story beat:

  • fadeBlur — Soft intro/outro, dreamy reveals
  • scaleFade — Confident reveals, product showcases
  • slideLeft/slideRight — Sequential progression, timeline flow
  • splitHorizontal/splitVertical — Dramatic reveals, before/after
  • morphExpand — Grand finale, CTA screens
  • clipCircle — Focus attention, spotlight effect
  • perspectiveFlip — Card flips, perspective changes
  • wipe — Clean transitions, directional flow
  • zoomThrough — Immersive, forward momentum
  • crossDissolve — Gentle, emotional transitions

Element Animation Reference (Quick)

  • popIn — Bouncy scale entrance for icons/badges
  • fadeUp/fadeDown — Subtle content reveals
  • slideInLeft/slideInRight — Directional content
  • blurIn — Soft focus reveals
  • elasticScale — Playful, energetic entrances
  • perspectiveRotateIn — 3D card reveals
  • pulse — Looping attention grab
  • float — Gentle hovering effect

Important Rules

  1. Always use vw units for sizing so animations look good at any resolution
  2. Keep scenes between 3-5 seconds each — total video 15-30 seconds
  3. Use AnimatePresence mode="wait" so one scene exits before the next enters
  4. Every scene must have a background treatment (gradient, image, or animated shape)
  5. Use staggered animations for lists and grids (staggerChildren: 0.1-0.2)
  6. Include a loading state if assets are heavy
  7. The project must be completely self-contained — no external dependencies beyond npm packages
  8. Do NOT use emojis anywhere in the generated code or content

Individual skills in this repo

This repo contains 13 individual skills — each has its own dedicated page.

OneWave-AI/claude-skills

Deploy a 2-layer parallel agent hierarchy for large, parallelizable work — big refactors, multi-file migrations, codebase-wide audits, bulk generation. A top-tier commander (Fable or Opus) orchestrates the swarms; the user picks a power level (Max Power / Heavy / Balanced / Economy) that sets the Opus/Sonnet/Haiku model mix per layer. Layer 1 is 3-50+ specialist agents, each with its own full context window; Layer 2 is 2+ sub-agents per member. Includes git safety, tiered sizing, a pre-deploy gate, phantom-completion checks, and multi-wave follow-up.

OneWave-AI/claude-skills

Post-mortem analysis when a client churns. Takes client history, engagement data, support tickets, usage logs, and exit feedback to produce a comprehensive churn autopsy with root cause classification, timeline of decline, and preventive measures.

OneWave-AI/claude-skills

Assemble 2-3 complementary experts to collaboratively analyze anything. Experts work together to explore topics from multiple expert angles.

OneWave-AI/claude-skills

Convert any topic into playable browser games. Types: trivia, matching, word puzzles, adventure games. Uses Phaser.js or Kaboom.js.

OneWave-AI/claude-skills

Audit a codebase for LLM calls that are really classifications in disguise, then produce a costed swap plan for a System One model. Use when asked to cut AI inference cost or latency, when scoping a performance engagement for a client, when reviewing an agent loop that feels slow, or when asked "where could we use Jev here". Produces a ranked table of candidates with measured latency and dollar deltas.

OneWave-AI/claude-skills

Build and run a labelled eval set for a System One model (Jev, Von, or any typed-decision config), then sweep criteria wordings and thresholds against it. Use when a Jev/Von classification is wrong or unreliable, when choosing between the hosted API and a local open model, when tuning noul thresholds, or before shipping any typed-decision feature. Produces an accuracy-by-wording matrix and a calibrated threshold.

OneWave-AI/claude-skills

Wire a System One model (Jev, or an open reproduction like Von) into a product feature — routing, guardrails, scoring, classification. Use when replacing an LLM call that returns a label rather than prose, when adding a typed decision to an agent loop, or when deciding between the hosted Jev API and a local open model. Covers question design, the eval-set-first workflow, threshold calibration, confidence gates, and the traps measured on real data.

OneWave-AI/claude-skills

Optimize landing pages for conversions, performance, and SEO. Use when improving landing pages, increasing conversions, or optimizing page performance.

OneWave-AI/claude-skills

TAM/SAM/SOM calculator with deep market research. Produces comprehensive market-sizing.md with top-down and bottom-up estimates, methodology, data sources, assumptions, sensitivity ranges, growth projections, competitive landscape, and Mermaid visualizations. Use when user needs market size estimates, addressable market analysis, go-to-market sizing, investor-ready market analysis, or business plan market validation.

OneWave-AI/claude-skills

Create multiple choice, true/false, fill-in-blank, matching quizzes. Auto-generate plausible distractors. Instant grading with explanations.

OneWave-AI/claude-skills

Enhanced skill navigator that maps conversation history, recommends multi-skill chains, identifies patterns from past usage, and learns from session outcomes. Goes beyond basic scout with deep context analysis and workflow orchestration.

OneWave-AI/claude-skills

Analyzes current conversation context to recommend the best skills and subagents for the task at hand. Use proactively when unsure which tool, skill, or agent to use.

OneWave-AI/claude-skills

Agent skill at social-repurposer/SKILL.md

관련 스킬