Agent Skills

claude-typer

Render a Claude-style prompt typing animation video by calling Remotion CLI against the remote site https://www.laosunwendao.com. Use when the user asks for "做一个 claude 的提示词打字机动画", "做 Claude 打字动画", "创建提示词动画", or similar requests that convert a text prompt into a typing-animation video.

Install

npx skills add https://github.com/vibe-motion/skills --skill claude-typer
SKILL.md

Claude Typer

Workflow

  1. Extract the text that should be typed in the animation as prompt.
  2. Run:
    • skill_dir=""
      for base in "${AGENTS_HOME:-$HOME/.agents}" "${CLAUDE_HOME:-$HOME/.claude}" "${CODEX_HOME:-$HOME/.codex}"; do
        if [ -d "$base/skills/claude-typer" ]; then
          skill_dir="$base/skills/claude-typer"
          break
        fi
      done
      [ -n "$skill_dir" ] || { echo "claude-typer skill not found under ~/.agents, ~/.claude, or ~/.codex"; exit 1; }
      /usr/local/bin/python3 "$skill_dir/scripts/render_claude_typer.py" "<prompt>"
      
    • Example with explicit size and scale:
      /usr/local/bin/python3 "$skill_dir/scripts/render_claude_typer.py" \
        "claude-typer skill可以让智能体做出提示词打字机动效视频,快来试试吧" \
        --video-width 1080 \
        --video-height 600 \
        --claude-width 600 \
        --scale 2
      
    • Example matching custom runner + remotion params passthrough:
      /usr/local/bin/python3 "$skill_dir/scripts/render_claude_typer.py" \
        "vibe-motion/skills:一个面向智能体的MG动画/视频技能仓库." \
        --runner-prefix "npx -y -p @remotion/cli@4.0.440 -p @remotion/tailwind-v4@4.0.440 remotion" \
        --composition Typer30fps \
        --output-file Typer30fps.mov \
        --codec prores \
        --prores-profile 4444 \
        --pixel-format yuva444p10le \
        --image-format png \
        --audio-codec aac \
        --video-width 1080 \
        --video-height 1080 \
        --claude-width 880
      
  3. Return the generated video path in the current working directory.

Rendering Behavior

  • Render remote composition Typer30fps from https://www.laosunwendao.com.
  • Use @remotion/cli (not remotion package name).
  • Prefer bunx @remotion/cli first.
  • Fall back to npx -y -p @remotion/cli@4.0.440 -p @remotion/tailwind-v4@4.0.440 remotion if bunx is unavailable.
  • Keep transparent MOV defaults:
    • --fps=30
    • --codec=prores
    • --prores-profile=4444
    • --pixel-format=yuva444p10le
    • --image-format=png
    • --scale=2
  • Keep defaults for stability:
    • --timeout=300000
    • --concurrency=1
    • Auto-detect local Chrome/Chromium and pass --browser-executable when found.
  • Keep default props from the project; replace prompt, and allow overriding videoWidth / videoHeight / claudeWidth through script args.
  • Unknown CLI args are passed through to remotion render directly (for advanced flags).
  • --runner-prefix lets you fully control the runner command (for pinned versions, global resolution behavior, etc.).
  • Exposed Remotion props for this skill are scalar fields only: prompt, typingSpeedMs, model, videoWidth, videoHeight, claudeWidth, tiltStartX, tiltStartY, tiltEndX, tiltEndY, tiltDurationRatio.

Output File Naming

  • Save into the current directory as xxx.mov.
  • Build xxx by condensing the prompt:
    • Remove common request wrappers like 帮我, 请, 做一个, 生成一个, 制作, 创建 at the start.
    • Remove illegal filename characters.
    • Keep Chinese/English letters and digits.
    • If result is empty, use claude-typer.
  • Example:
    • Prompt: 帮我做一个web画板
    • Output: web画板.mov

Notes

  • On a clean machine, Node.js + npx is enough for this fallback path, as long as network access to npm and https://www.laosunwendao.com is available.
  • If both bunx and npx are unavailable, install one of them and retry.
  • If the output name already exists, Remotion overwrite behavior applies.
  • If you hit delayRender() timeout, keep --concurrency=1 and raise --timeout-ms as needed.

Related skills

video-editgenmedia-labs715KEdit existing video on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Wan 2.7 Edit-Video (general restyle / background swap / packaging swap, identity + motion preservation), Kling 2.6 Pro Motion Control (transfer precise motion from a reference video to a target character), or Lucy Edit Restyle (lightweight identity-stable restyle / outfit swap). Bundles each model's documented prompting patterns so the skill gets shai-video-generationgenmedia-labs714KGenerate AI videos on RunComfy via the `runcomfy` CLI — a smart router across the full video-model catalog: HappyHorse 1.0 (Arena #1, native in-pass audio), Wan-AI Wan 2-7 (open weights, audio-driven lip-sync), ByteDance Seedance v2 / 1-5 / 1-0 (multi-modal cinematic), Kling 3.0 / 2-6, Google Veo 3-1, MiniMax Hailuo 2-3, ByteDance Dreamina 3-0. Covers text-to-video (t2v), image-to-video (i2v), and Veo's video-extend endpoint. The skill picks the right model for the user's intent (Arena-#1 qualitai-musicgenmedia-labs714KGenerate AI music on RunComfy via the `runcomfy` CLI — a smart router across the music-model catalog. Routes to ElevenLabs AI Music Generation (premium 44.1 kHz stereo vocal tracks, 5 s–5 min, $0.0083/s) and ACE Step / ACE Step 1.5 (StepFun-AI open-weights, tag-driven composition, multilingual lyrics, $0.0002–0.0003/s, ~27× cheaper), plus ACE Step audio-inpaint (regenerate a time range inside an existing track) and ACE Step audio-outpaint (extend a track before or after). Picks the right model fimage-to-videogenmedia-labs713KAnimate any still image on RunComfy — this skill is a smart router that matches the user's intent to the right i2v model in the RunComfy catalog. Picks HappyHorse 1.0 I2V (Arena #1, native audio, identity preservation) for general animations, Wan 2.7 with `audio_url` for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal animation from image + reference video + reference audio. Bundles each model's documented prompting patterns so the caller gets sharper output without burning iterat

Search skills and MCP servers

Fuzzy search across 23,137 skills and servers