界面已本地化;技能介绍与说明文档按所选语言由 AI 自动翻译,代码、命令、路径和专业术语保留原文,以原作者文档为准。
探索技能
效率与协作 · SKILL.md

demo-video

demo-video

【效率与协作】Generate polished demo videos from a single prompt. Use when the user asks to create a demo video, product walkthrough, feature showcase, or animated presentation. Trigger with "make a demo video", "create a product video", "demo walkthrough", or "feature showcase video".

独立 GitHub 快照 · 自动分类 · 以原作者文档为准

技能说明

GitHub

name: demo-video description: 'Generate polished demo videos from a single prompt. Use when the user asks

to create a demo video, product walkthrough, feature showcase, or animated

presentation. Trigger with "make a demo video", "create a product video",

"demo walkthrough", or "feature showcase video".

' allowed-tools: Read, Write, Edit, Bash(uv:*), Glob version: 1.3.0 author: Srinivas Vaddisrinivas vaddisrinivas170497@gmail.com license: MIT tags:

  • video
  • demo
  • playwright
  • ffmpeg
  • edge-tts
  • mcp compatibility: Designed for Claude Code

Demo Video Generator

Overview

Generate 1920x1080 demo videos with voiceover, transitions, and CSS animations from a single prompt. Orchestrates Playwright (HTML-to-frame rendering), FFmpeg (compositing and transitions), and Edge TTS (neural voiceover) MCP servers.

Prerequisites

  • Python 3.11+ and uv package manager
  • FFmpeg installed (ffmpeg -version)
  • Playwright chromium browser (uv run playwright install chromium)
  • Internet connection for Edge TTS voice synthesis

Instructions

Install the framecraft plugin from the marketplace:

claude plugin marketplace add jeremylongshore/claude-code-plugins-plus-skills
claude plugin install framecraft@claude-code-plugins-plus

Quick Start

uv run python framecraft.py init my-demo        # scaffold a project
uv run python framecraft.py render scenes.json --auto-duration
uv run python framecraft.py validate output.mp4  # quality check

MCP Orchestration

When Playwright, FFmpeg, and Edge TTS MCP servers are available, framecraft orchestrates them directly for maximum control over each frame and audio segment.

Pipeline Fallback

When MCP servers are not available, framecraft runs an atomic CLI pipeline that handles everything in one call.

Workflow

  1. Story design -- Choose a narrative arc (problem-solution, hero journey, before-after)
  2. Scene authoring -- Write HTML scenes with CSS animations, or use built-in templates
  3. Rendering -- Playwright captures frames, Edge TTS generates voiceover, FFmpeg composites

Output

  • 1920x1080 MP4 video with voiceover and transitions
  • Individual scene previews for iteration
  • Validation report for quality assurance

Error Handling

ErrorCauseFix
ffmpeg: command not foundFFmpeg not installedInstall via brew install ffmpeg or system package manager
playwright._impl._errors.ErrorChromium not installedRun uv run playwright install chromium
edge_tts.exceptions.NoAudioReceivedTTS service unavailableCheck internet connection; retry after a few seconds
FileNotFoundError: scenes.jsonMissing scene configRun uv run python framecraft.py init my-demo first
Blank or black framesHTML scene rendering failedCheck HTML syntax and ensure assets are accessible

Examples

{
  "scenes": [
    {
      "title": "Meet YourApp",
      "subtitle": "The smarter way to manage tasks",
      "narration": "24 tasks. One dashboard. Zero stress.",
      "voice": "en-US-AndrewNeural",
      "bullets": ["Smart priorities", "Team sync", "One-click reports"],
      "duration": 0
    }
  ],
  "output": "demo.mp4",
  "width": 1920, "height": 1080,
  "voice": "en-US-AndrewNeural",
  "transition": "crossfade"
}

duration: 0 = auto-detect from TTS length + 1.5s buffer.

Resources

我的收藏