From skind-skills
Creates animated explainer videos with Kurzgesagt-inspired style using Remotion. Handles storyboarding, SVG animation, narration generation via edge-tts, and video rendering.
How this skill is triggered — by the user, by Claude, or both
Slash command
/skind-skills:educational-video-creatorThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Create professional educational videos with Kurzgesagt/回形针 visual style using Remotion.
assets/common-icons.tsxassets/design-tokens.tsassets/progress-template.mdassets/scene-template.tsxassets/subtitle-sequence-template.tsxreferences/animation-guide.mdreferences/audio-guide.mdreferences/quality-checklist.mdreferences/requirements-guide.mdreferences/script-and-narration.mdreferences/storyboard-template.mdreferences/style-guide.mdreferences/svg-components.mdreferences/visual-principles.mdscripts/generate-tts.tsscripts/rebuild-timeline.tsscripts/render-keyframes.tsscripts/shared.tsscripts/style-scan.tsCreate professional educational videos with Kurzgesagt/回形针 visual style using Remotion.
This skill requires remotion-best-practices for Remotion technical implementation.
Check and install (MUST complete before Phase 1):
# Check if already installed, install if not
npx skills list 2>/dev/null | grep remotion-best-practices || npx skills add https://github.com/remotion-dev/skills --skill remotion-best-practices
Once installed, read the remotion-best-practices skill to load Remotion API details into context. This is essential — without it, Phase 4 code will have incorrect Remotion API usage.
External dependencies (needed for Phase 4.5 audio generation):
# ffmpeg (provides ffprobe for audio duration measurement)
brew install ffmpeg # macOS
# apt install ffmpeg # Linux
# edge-tts (Python TTS engine for narration generation)
pip install edge-tts
This skill creates videos in a dedicated remotion_video subdirectory within the current workspace.
First-time setup (recommended — non-interactive):
# Create video project directory
mkdir -p remotion_video
cd remotion_video
# Initialize without interactive prompts
npm init -y
npm install remotion @remotion/cli @remotion/google-fonts @remotion/transitions react react-dom
npm install -D typescript @types/react
# Create minimal project structure
mkdir -p src public/audio/narration
Then create the required entry files:
src/Root.tsx — Main composition registrysrc/index.ts — Remotion entry point with registerRoot(Root)remotion.config.ts — Remotion configurationtsconfig.json — TypeScript configAlternative (interactive — may block in automated environments):
mkdir -p remotion_video && cd remotion_video
npx create-video@latest --blank
npm install
Note:
npx create-videomay prompt for project name, package manager, etc. In CLI/automation contexts, use the non-interactive method above to avoid blocking.
Existing project:
cd remotion_video
npm install # Ensure dependencies are installed
Project structure:
your-workspace/
├── remotion_video/ # Video project root
│ ├── src/
│ │ ├── Root.tsx # Main composition registry
│ │ └── YourVideo/ # Video-specific components
│ │ ├── index.tsx
│ │ ├── scenes/
│ │ └── components/
│ ├── public/ # Static assets
│ └── package.json
└── ... (other workspace files)
remotion_video directory if neededEvery conversation turn may follow a context loss (compaction, new session). Before doing ANY work:
remotion_video/PROGRESS.md exists
remotion_video/script.md (if Phase 1.5+ completed)remotion_video/storyboard.md (if Phase 2+ completed)src/<Composition>/constants.ts (if Phase 3+ completed — contains COLORS, SCENES, NARRATION, AUDIO_SEGMENTS)Skipping this protocol causes repeated work or file corruption. Always run it first.
⚠️ This protocol is NON-NEGOTIABLE. Skipping updates causes context loss and repeated work.
Maintain remotion_video/PROGRESS.md using progress-template.md. Create it at Phase 1 start. Log decisions in the Decisions table and add every created file to "Files Created".
Every time you complete a checkbox item in PROGRESS.md, you MUST immediately:
[x] and add brief notesDo NOT batch multiple items. One item done → one update → next item.
Before starting any new Phase, you MUST:
PROGRESS.md and verify ALL items in the previous phase are [x]⚠️ First: Complete the Prerequisites section (install remotion-best-practices skill and read it). Then create
remotion_video/PROGRESS.mdfrom progress-template.md and fill in Project Info.
Before starting, confirm these essential details with the user:
For detailed question templates, see requirements-guide.md.
⚠️ Checkpoint Rule active: After completing EACH checkbox item for this phase, immediately update
PROGRESS.md. Do not batch updates.
Write a complete narrative script before designing the storyboard. This phase focuses purely on storytelling — what to say and how to say it well — without worrying about visual specs, frame numbers, or animation parameters.
IMPORTANT: Write the FULL narration text — every word that will be spoken. Do NOT write summaries, bullet points, or placeholders. The script is the final spoken content.
The script must include:
[.] (short), [..] (medium), [...] (long), [PAUSE] or [BEAT] (dramatic) — see script-and-narration.md Part 3 for duration semanticsQuality gate: Present the complete script to the user for approval. Do NOT proceed to Phase 2 until the user explicitly approves the narrative.
Why script first:
Output: Save the approved script as remotion_video/script.md
See script-and-narration.md for video structure templates, narrative techniques, writing techniques, and TTS notes.
⚠️ Checkpoint Rule active: After completing EACH checkbox item for this phase, immediately update
PROGRESS.md. Do not batch updates.
Convert the approved script into a production-ready storyboard. The script provides what to say; the storyboard defines how to show it.
Input: Completed script (approved in Phase 1.5)
Tasks:
The cognitive load is much lower than creating everything from scratch — the narrative is already decided, so you only need to focus on visual execution.
Output: Save the completed storyboard as remotion_video/storyboard.md for design traceability and iteration reference.
See storyboard-template.md for templates. See script-and-narration.md Part 4 for subtitle formatting and TTS notes.
⚠️ Checkpoint Rule active: After completing EACH checkbox item for this phase, immediately update
PROGRESS.md. Do not batch updates.
Apply the Kurzgesagt/回形针 style. Concrete steps:
constants.ts — Define COLORS, TYPOGRAPHY, SCENES, NARRATION, and estimated AUDIO_SEGMENTS following design-tokens.ts Section 3loadFont() from @remotion/google-fonts (see design-tokens.ts Section 2 for reference)Style principles:
See style-guide.md for complete visual standards. See visual-principles.md for composition and layout.
⚠️ Checkpoint Rule active: After completing EACH checkbox item for this phase, immediately update
PROGRESS.md. Do not batch updates. Log key file paths in "Files Created".
Implement scenes using Remotion:
useCurrentFrame() for all animationsSubtitle & narration rules (critical for Phase 4.5 compatibility):
NARRATION object in constants.ts — never hardcode text directly in scene TSX filesAUDIO_SEGMENTS in constants.ts with approximate timing. Phase 4.5 will overwrite it with real audio-based timingAUDIO_SEGMENTS.sceneKey — never use inline segment arrays with hardcoded frame numbersAUDIO_SEGMENTS 中的 startFrame/endFrame 必须使用场景本地帧号(每个场景从 SCENE_PAD=15 开始),不是全局帧号。因为 AudioLayer 和 SubtitleSequence 都在场景的 <Sequence> 内部运行,useCurrentFrame() 返回的是本地帧号。如果使用全局帧号,后续场景的字幕会延迟或完全不显示rebuild-timeline.ts --write in Phase 4.5 can update timing without modifying any scene filesVisual-narration alignment rules (prevents animation-subtitle desync):
startFrame 必须从 AUDIO_SEGMENTS 对应段的 startFrame 派生,不能凭"视觉节奏"硬编码const liftArrowStart = AUDIO_SEGMENTS.forces[0].startFrame;(升力箭头在旁白说"升力"时出现)const liftArrowStart = 30;(凭感觉写的帧数,和旁白无关)Element sizing rules (prevents "Thumbnail Syndrome" — tiny elements on a large canvas):
Background rules (prevents transparent/checkerboard frames during transitions):
<AbsoluteFill> background layer (using COLORS.background) that sits behind all scenes and never participates in transitionsfade() transitions, both scenes have reduced opacity — without a persistent background, transparent frames appear as a checkerboard pattern in preview and black in rendersVisual richness rules (prevents PPT-like output):
Color rules (critical for Phase 5 style-scan compliance):
COLORS object from constants.ts (e.g., COLORS.accent.rose) — never write hex values directly in TSX filesrgba() for opacity variations (e.g., rgba(0, 0, 0, 0.7) for subtitle backgrounds)See design-tokens.ts Section 3 for the complete constants.ts structure (COLORS, SCENES, NARRATION, AUDIO_SEGMENTS, font loading). See svg-components.md for component patterns. See animation-guide.md for timing and easing.
⚠️ Checkpoint Rule active: After completing EACH checkbox item for this phase, immediately update
PROGRESS.md. Do not batch updates.
完成动画编码后,生成视频音频并同步时间线:
generate-tts.ts 从 NARRATION 提取文本生成 mp3rebuild-timeline.ts --write 根据实际音频时长更新 constants.tsnewDuration / oldDuration 比例缩放public/audio/bgm.mp3详细步骤、命令参数、AudioLayer 模板见 audio-guide.md。
⚠️ Checkpoint Rule active: After completing EACH checkbox item for this phase, immediately update
PROGRESS.md. Do not batch updates.
完成编码后,执行自动质量检查流程:
详细检查步骤和规则见 quality-checklist.md。
After preview looks correct, render the final video:
cd remotion_video
npx remotion render src/index.ts <CompositionName> out/video.mp4
Options:
--codec h264 (default) or --codec h265 for smaller file size--quality 80 to 100 (default: 80)--scale 1 (1080p) — use --scale 2 for 4K if source assets support it--log verbose if debugging render issuesThe output file will be at remotion_video/out/video.mp4.
Standard educational video structure:
1. Hook (5-10s) - Attention-grabbing question or statement
2. Intro (10-20s) - Topic introduction
3. Content (main) - Core explanation, broken into segments
4. Summary (10-20s) - Key takeaways
5. Outro (5-10s) - Call to action or closing
See script-and-narration.md Part 1 for detailed structure templates.
| File | When to Use |
|---|---|
| requirements-guide.md | Starting a new video project (Phase 1) |
| script-and-narration.md | Video structure, script writing, narration, subtitle/TTS (Phase 1.5 + 2) |
| storyboard-template.md | Converting script into visual scenes (Phase 2) |
| style-guide.md | Designing visual elements (Phase 3 + 4) |
| visual-principles.md | Layout and composition decisions (Phase 3 + 4) |
| animation-guide.md | Implementing animations (Phase 4) |
| svg-components.md | Creating reusable components (Phase 4) |
| audio-guide.md | TTS 生成、时间线重建、AudioLayer 集成详细步骤 (Phase 4.5) |
| quality-checklist.md | Quality assurance + style check rules (Phase 5) |
| design-tokens.ts | Color palettes, typography presets, constants.ts template (Phase 3) |
| progress-template.md | 执行进度跟踪模板 (全流程) |
| scene-template.tsx | 场景组件模板 (Phase 4) |
| subtitle-sequence-template.tsx | 字幕序列组件模板 (Phase 4) |
| common-icons.tsx | 通用 SVG 图标组件 (Phase 4) |
| generate-tts.ts | 字幕提取 + TTS 音频生成脚本 (Phase 4.5) |
| rebuild-timeline.ts | 音频时长测量 + 时间线重建脚本 (Phase 4.5) |
| style-scan.ts | 代码样式扫描脚本 (Phase 5) |
| render-keyframes.ts | 关键帧批量截图脚本 (Phase 5) |
| shared.ts | 脚本共享函数(内部依赖,无需直接调用) |
npx claudepluginhub skindhu/skind-skills --plugin skind-skillsTransforms arbitrary text (articles, notes, topics) into faceless explainer videos with TTS narration, abstract graphics, diagrams, and data visualization. No product screenshots or website captures.
Generates MP4 motion graphics videos from a content brief using HTML/CSS animations rendered frame-by-frame in headless Chromium via Playwright, assembled with FFmpeg.
Builds reusable Manim explainers for technical concepts, graphs, system diagrams, and product walkthroughs. Use when a clean animated explainer is needed instead of a talking-head script.