screencast-to-viral
Transform long screen recordings into viral short-form videos with AI-powered editing, subtitles, and packaging. Designed for 10x content production velocity.
#video #automation
Install
npx skills add https://github.com/AIPMAndy/Andy-Video-Skill/tree/main/02-recording-to-video/andy-screencast-to-viral
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install aipmandy-andy-video-skill@llmmart
git clone https://github.com/AIPMAndy/Andy-Video-Skill.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole aipmandy/andy-video-skill collection as a plugin from our marketplace. Git is the plain clone.
README
Andy's Screencast-to-Viral Pipeline
目标: 将42个录屏素材自动转化成100+爆款短视频,达到10万粉丝
🎯 现状
✅ 已完成(2026-08-09):
- 完整的技术方案设计
- 智能分析器(提取高光时刻)
- 智能剪辑器(生成30/60/90秒短视频)
- 批量处理系统
- 平台适配(抖音/B站/小红书)
- 已成功测试:从120秒录屏生成30秒抖音短视频
✅ 测试结果:
输入: GPT做电脑壁纸.mp4 (120.4秒, 45.4MB)
输出: 30秒抖音短视频 (1080×1920, 1.3MB)
+ 5个标题变体
+ Hook文案
+ 完整元数据
🚀 快速开始
1. 检查依赖
cd ~/.claude/skills/andy-screencast-to-viral
python3 viral.py doctor
需要安装:
- ✅ ffmpeg(已安装)
- ✅ ffprobe(已安装)
- ⚠️ whisper(推荐安装):
pip install openai-whisper
2. 处理单个视频
# 分析视频
python3 viral.py analyze "/Users/andy/Documents/Andy录屏素材库/GPT做电脑壁纸.mp4"
# 生成30秒抖音短视频
python3 viral.py generate \
"/Users/andy/Documents/Andy录屏素材库/GPT做电脑壁纸.mp4" \
"./analysis/GPT做电脑壁纸_analysis.json" \
30 \
douyin
3. 批量处理(推荐)
# 处理前10个视频(测试)
python3 viral.py batch \
"/Users/andy/Documents/Andy录屏素材库" \
--limit 10 \
--durations 30,60 \
--platforms douyin
# 处理全部42个视频
python3 viral.py batch \
"/Users/andy/Documents/Andy录屏素材库" \
--durations 30,60 \
--platforms douyin,bilibili
📊 Pipeline工作流
录屏素材 (2-10分钟)
↓
[Stage 1: 分析]
- 提取元数据
- 语音转文字 (Whisper)
- 提取关键帧
- 识别高光时刻
↓
[Stage 2: 剪辑]
- 提取精华片段
- 删除冗余部分
- 智能变速
↓
[Stage 3: 包装]
- 添加开场Hook
- 生成字幕
- 混合背景音乐
↓
[Stage 4: 适配]
- 平台格式转换
- 生成标题变体
- 制作封面
↓
短视频 (30-90秒) + 元数据
🎬 输出结构
batch_output/
├── 视频01/
│ ├── analysis/
│ │ ├── 视频01_analysis.json
│ │ ├── 视频01_audio.mp3
│ │ └── frames/
│ └── clips/
│ ├── 30s_douyin/
│ │ ├── 视频01_30s_base_douyin.mp4
│ │ └── 视频01_30s_base_douyin_metadata.json
│ └── 60s_douyin/
│ └── ...
├── 视频02/
└── batch_report_20260809_215500.json
💡 核心功能
1. 智能高光识别
- 语音密度分析: 识别激动时刻(>3词/秒)
- 关键词检测: "哇"、"太"、"真的"、"成功"等
- 结构化片段: 自动识别开场/过程/结果
2. MrBeast爆款原则
- ✅ CTR优化: 数字化标题 + 悬念感
- ✅ AVD优化: 前3秒Hook + 无废话剪辑
- ✅ 阶梯递进: 持续升级,不能平
3. 多平台适配
| 平台 | 尺寸 | 时长 | 特点 |
|---|---|---|---|
| 抖音 | 1080×1920 (9:16) | 30-90s | 完播率优先 |
| B站 | 1920×1080 (16:9) | 60-180s | 信息密度高 |
| 小红书 | 1080×1440 (3:4) | 30-60s | 视觉吸引力 |
4. 标题生成(MrBeast公式)
templates = [
"用AI{动作}{结果},只用了{N}秒",
"{之前}到{之后},差距惊人",
"终于发现{秘密}了...",
"{N}个{工具}同时{动作}会怎样",
]
📈 成功指标
短期目标(1个月)
- 处理完42个录屏素材
- 生成至少100条短视频
- 测试完3个平台
- 找到1-2个爆款模板(完播率>50%)
中期目标(3个月)
- 粉丝突破1万
- 单条播放量过10万
- 稳定日更(2-3条/天)
- 形成固定风格和IP
最终目标(6个月)
- 粉丝突破10万 ⭐
- 商业化(接广告/带货)
- 建立素材库和模板库
- 形成可复制的生产流程
⚙️ 配置选项
创建 viral-config.json:
{
"defaults": {
"duration": 60,
"platform": "douyin",
"hook": "question"
},
"audio": {
"bgm_volume": 0.25,
"voice_volume": 0.75
},
"subtitle": {
"font": "PingFang SC",
"size": 48,
"color": "#FFFFFF"
},
"quality": {
"video_bitrate": "6000k",
"audio_bitrate": "128k"
}
}
🐛 故障排除
问题: Whisper未安装
pip install openai-whisper
问题: ffmpeg未找到
# macOS
brew install ffmpeg
# Linux
sudo apt install ffmpeg
问题: 生成的视频文件过大
# 在editor.py中降低码率
--video-bitrate 4000k
问题: 语音识别不准确
# 使用更大的Whisper模型
whisper audio.mp3 --model large
📝 下一步计划
立即执行(本周)
- ✅ 完成核心pipeline开发
- ✅ 测试单个视频处理
- ⏳ 安装Whisper提升语音识别
- ⏳ 批量处理10个最优质素材
- ⏳ 发布到抖音测试反馈
本月计划
- 优化标题生成算法
- 添加自动字幕功能
- 集成背景音乐库
- 开发封面自动生成
- 处理全部42个素材
长期规划
- 建立爆款模板库
- 添加A/B测试系统
- 集成数据分析面板
- 开发自动发布功能
- 扩展到更多平台
🔗 相关资源
- 方案文档:
/Users/andy/Documents/AICode/09 Andy-Video-SKill/SCREENCAST_TO_VIRAL_PLAN.md - 录屏素材库:
/Users/andy/Documents/Andy录屏素材库(42个文件, 5.7GB) - MrBeast方法论:
~/.claude/skills/mrbeast-skill/ - 视频分析技能:
~/.claude/skills/video-content-analysis.md
📞 使用支持
遇到问题?
- 运行
python3 viral.py doctor检查环境 - 查看
batch_report_*.json了解处理状态 - 检查
output/目录下的日志文件
版本: 1.0.0 (MVP)
创建日期: 2026-08-09
状态: ✅ 核心功能已验证,可投入生产使用
目标: 10万粉丝
Skill manifest
Andy's Screencast-to-Viral Pipeline
🎯 Core Mission
Turn your 42+ screen recordings into 100+ viral short videos. Automated analysis → intelligent editing → viral packaging → batch publishing.
Target: 10万粉丝 through systematic content production.
When to Use
- You have raw screen recordings (2-10 minutes)
- Want to generate short-form videos (30-90 seconds)
- Need batch processing for multiple files
- Targeting Douyin/Bilibili/Xiaohongshu
Quick Start
# Analyze one recording to find highlights
/screencast-to-viral analyze --input "path/to/video.mp4"
# Generate short video (auto mode)
/screencast-to-viral generate --input "path/to/video.mp4"
# Batch process entire directory
/screencast-to-viral batch --input "/Users/andy/Documents/Andy录屏素材库"
# Preview without rendering
/screencast-to-viral preview --input "path/to/video.mp4"
Pipeline Stages
Stage 1: Analyze (智能分析)
What it does:
- Extract metadata (duration, resolution, audio)
- Transcribe speech with Whisper
- Extract key frames (0.5 fps)
- Identify "highlight moments"
- Generate cutting recommendations
Output:
{
"source": "video.mp4",
"duration": 206.5,
"transcription": "full text...",
"highlights": [
{
"start": 15.2,
"end": 45.8,
"score": 0.92,
"reason": "High visual change + excited speech",
"type": "result_reveal"
}
],
"recommendations": {
"best_30s": { "start": 15.2, "end": 45.2 },
"best_60s": { "start": 10.0, "end": 70.0 },
"best_90s": { "start": 5.0, "end": 95.0 }
}
}
Stage 2: Edit (智能剪辑)
What it does:
- Extract highlight segment
- Remove dead air and pauses
- Speed up non-critical parts (1.2-1.5x)
- Apply MrBeast "no dull moments" principle
Rules:
- Delete all silence >0.5s
- Delete all "um", "uh", "嗯", "啊"
- Speed up mouse movement/typing
- Keep all "wow moments"
Stage 3: Package (爆款包装)
What it does:
- Add viral hook (first 3 seconds)
- Generate auto-subtitles
- Add BGM (120-140 BPM)
- Apply visual effects
Hook Templates:
const hooks = {
question: {
text: "你见过{X秒}做出这个效果吗?",
visual: "flash_final_result"
},
challenge: {
text: "大家都说这个不可能...",
visual: "show_difficulty"
},
result_first: {
text: "直接看结果 →",
visual: "show_result_immediately"
}
}
Stage 4: Design (标题+封面)
What it does:
- Generate 5 title variants (MrBeast formula)
- Extract best frame for thumbnail
- Add text overlay to thumbnail
- Create A/B test versions
Title Templates:
templates = [
"用AI{动作}{结果},只用了{N}秒",
"{之前}到{之后},差距惊人",
"终于发现{秘密}了...",
"{N}个{工具}同时{动作}会怎样",
]
Stage 5: Export (批量导出)
What it does:
- Export to platform-specific formats
- Generate metadata.json for each video
- Create thumbnail variants
- Prepare upload checklist
Platform Specs:
| Platform | Ratio | Duration | Bitrate |
|---|---|---|---|
| Douyin | 9:16 | 30-90s | 6000k |
| Bilibili | 16:9 | 60-180s | 8000k |
| Xiaohongshu | 3:4 | 30-60s | 5000k |
Options Reference
--input <path> # Input video file or directory
--output <path> # Output directory (default: ./output)
--duration <seconds> # Target duration: 30, 60, or 90
--platform <name> # douyin, bilibili, xiaohongshu, or all
--style <template> # tech, tutorial, vlog, showcase
--hook <type> # question, challenge, result_first
--no-subtitle # Skip subtitle generation
--no-music # Skip background music
--speed <factor> # Speed multiplier (1.0-2.0)
--preview # Generate preview only
--batch # Process entire directory
--force # Overwrite existing outputs
Configuration File
Create viral-config.json in your project:
{
"defaults": {
"duration": 60,
"platform": "douyin",
"style": "tech",
"hook": "question"
},
"audio": {
"bgm_volume": 0.25,
"voice_volume": 0.75,
"bgm_library": "~/Music/BGM"
},
"subtitle": {
"font": "PingFang SC",
"size": 48,
"color": "#FFFFFF",
"outline": "#000000",
"position": "bottom_center"
},
"quality": {
"video_bitrate": "6000k",
"audio_bitrate": "128k",
"preset": "medium"
}
}
Dependencies
Required:
- ffmpeg >= 5.0
- ffprobe (bundled with ffmpeg)
- whisper (OpenAI) -
pip install openai-whisper - Python >= 3.9
Optional:
- yt-dlp (for reference video analysis)
- imagemagick (for thumbnail design)
Installation Check
# Check if all tools are available
/screencast-to-viral doctor
Expected output:
✓ ffmpeg found (version 6.0)
✓ ffprobe found
✓ whisper found
✓ Python 3.11 found
⚠ imagemagick not found (optional)
✓ All required dependencies satisfied
Workflow Example
Single Video Processing
# Step 1: Analyze
/screencast-to-viral analyze --input "李子柒01.mp4"
# Review analysis.json, then:
# Step 2: Generate
/screencast-to-viral generate \
--input "李子柒01.mp4" \
--duration 60 \
--platform douyin \
--hook question
# Output:
# - output/李子柒01_viral_60s.mp4
# - output/李子柒01_thumbnail.jpg
# - output/李子柒01_titles.txt
# - output/李子柒01_metadata.json
Batch Processing
# Process all recordings
/screencast-to-viral batch \
--input "/Users/andy/Documents/Andy录屏素材库" \
--output "./viral_output" \
--duration 60 \
--platform all
# Generates:
# - 42 source videos → 126 short videos (3 versions each)
# - Organized by platform
# - Ready-to-upload package
Quality Checklist
Before publishing, verify:
- Video plays smoothly (no stutters)
- Subtitles are accurate and readable
- Audio levels balanced (BGM not too loud)
- Hook grabs attention in first 3 seconds
- No dead air or long pauses
- Thumbnail has visual contrast
- Title uses numbers and curiosity gap
- Ends with clear CTA or cliffhanger
MrBeast Principles Applied
- CTR × AVD formula - Every decision optimizes click-through or watch time
- No dull moments - Delete everything boring
- Stair-stepping - Content escalates continuously
- Simple concept × extreme execution - Clear idea, flawless delivery
- First 30 seconds rule - Hook, promise, action
Success Metrics
Track these for every video:
{
"completion_rate": 0.65, // >50% = viral potential
"like_rate": 0.08, // >5% = high value
"comment_rate": 0.03, // >2% = engaging
"share_rate": 0.01, // >1% = exceptional
"follower_growth": 127 // per 10k views
}
Troubleshooting
Issue: Whisper transcription fails
Solution: Check audio track exists with ffprobe -show_streams video.mp4
Issue: Subtitles out of sync
Solution: Use --subtitle-offset <seconds> to adjust timing
Issue: Generated video too large
Solution: Lower bitrate with --video-bitrate 4000k
Issue: Hook doesn't match content
Solution: Manually specify highlight with --segment 15.2-45.8
Iteration Strategy
- Week 1: Process 10 best recordings → 30 test videos
- Week 2: Analyze metrics → identify winning patterns
- Week 3: Process remaining 32 recordings with winning template
- Week 4: Scale to daily publishing (2-3 videos/day)
Output Structure
viral_output/
├── douyin/
│ ├── video_001/
│ │ ├── final.mp4
│ │ ├── thumbnail.jpg
│ │ ├── titles.txt
│ │ └── metadata.json
│ └── video_002/
├── bilibili/
└── xiaohongshu/
Next Steps
After skill creation:
- Test with 1 recording (李子柒01.mp4 or GPT做电脑壁纸.mp4)
- Iterate on hook templates
- Build title generation logic
- Create batch processing script
- Launch production pipeline
Status: 🚧 In Development Goal: Transform 42 recordings → 100+ viral videos → 10万粉丝 Deadline: 3 months from start
Files (andy-video-skill)
-
analyzer.py 13 KB
Loading… -
auto_publisher.py 10.6 KB
Loading… -
batch_processor.py 8.7 KB
Loading… -
complete_viral_system.py 16.7 KB
Loading… -
data_tracker.py 10.6 KB
Loading… -
editor.py 11.3 KB
Loading… -
fast_mass_production.py 10.5 KB
Loading… -
mass_production.py 6.9 KB
Loading… -
premium_editor.py 10.5 KB
Loading… -
premium_editor_v2.py 10.9 KB
Loading… -
premium_producer_v3.py 15.5 KB
Loading… -
README.md 5.9 KB
# Andy's Screencast-to-Viral Pipeline **目标**: 将42个录屏素材自动转化成100+爆款短视频,达到10万粉丝 ## 🎯 现状 ✅ **已完成**(2026-08-09): - 完整的技术方案设计 - 智能分析器(提取高光时刻) - 智能剪辑器(生成30/60/90秒短视频) - 批量处理系统 - 平台适配(抖音/B站/小红书) - **已成功测试**:从120秒录屏生成30秒抖音短视频 ✅ **测试结果**: ``` 输入: GPT做电脑壁纸.mp4 (120.4秒, 45.4MB) 输出: 30秒抖音短视频 (1080×1920, 1.3MB) + 5个标题变体 + Hook文案 + 完整元数据 ``` ## 🚀 快速开始 ### 1. 检查依赖 ```bash cd ~/.claude/skills/andy-screencast-to-viral python3 viral.py doctor ``` 需要安装: - ✅ ffmpeg(已安装) - ✅ ffprobe(已安装) - ⚠️ whisper(推荐安装): `pip install openai-whisper` ### 2. 处理单个视频 ```bash # 分析视频 python3 viral.py analyze "/Users/andy/Documents/Andy录屏素材库/GPT做电脑壁纸.mp4" # 生成30秒抖音短视频 python3 viral.py generate \ "/Users/andy/Documents/Andy录屏素材库/GPT做电脑壁纸.mp4" \ "./analysis/GPT做电脑壁纸_analysis.json" \ 30 \ douyin ``` ### 3. 批量处理(推荐) ```bash # 处理前10个视频(测试) python3 viral.py batch \ "/Users/andy/Documents/Andy录屏素材库" \ --limit 10 \ --durations 30,60 \ --platforms douyin # 处理全部42个视频 python3 viral.py batch \ "/Users/andy/Documents/Andy录屏素材库" \ --durations 30,60 \ --platforms douyin,bilibili ``` ## 📊 Pipeline工作流 ``` 录屏素材 (2-10分钟) ↓ [Stage 1: 分析] - 提取元数据 - 语音转文字 (Whisper) - 提取关键帧 - 识别高光时刻 ↓ [Stage 2: 剪辑] - 提取精华片段 - 删除冗余部分 - 智能变速 ↓ [Stage 3: 包装] - 添加开场Hook - 生成字幕 - 混合背景音乐 ↓ [Stage 4: 适配] - 平台格式转换 - 生成标题变体 - 制作封面 ↓ 短视频 (30-90秒) + 元数据 ``` ## 🎬 输出结构 ``` batch_output/ ├── 视频01/ │ ├── analysis/ │ │ ├── 视频01_analysis.json │ │ ├── 视频01_audio.mp3 │ │ └── frames/ │ └── clips/ │ ├── 30s_douyin/ │ │ ├── 视频01_30s_base_douyin.mp4 │ │ └── 视频01_30s_base_douyin_metadata.json │ └── 60s_douyin/ │ └── ... ├── 视频02/ └── batch_report_20260809_215500.json ``` ## 💡 核心功能 ### 1. 智能高光识别 - **语音密度分析**: 识别激动时刻(>3词/秒) - **关键词检测**: "哇"、"太"、"真的"、"成功"等 - **结构化片段**: 自动识别开场/过程/结果 ### 2. MrBeast爆款原则 - ✅ **CTR优化**: 数字化标题 + 悬念感 - ✅ **AVD优化**: 前3秒Hook + 无废话剪辑 - ✅ **阶梯递进**: 持续升级,不能平 ### 3. 多平台适配 | 平台 | 尺寸 | 时长 | 特点 | |------|------|------|------| | 抖音 | 1080×1920 (9:16) | 30-90s | 完播率优先 | | B站 | 1920×1080 (16:9) | 60-180s | 信息密度高 | | 小红书 | 1080×1440 (3:4) | 30-60s | 视觉吸引力 | ### 4. 标题生成(MrBeast公式) ```python templates = [ "用AI{动作}{结果},只用了{N}秒", "{之前}到{之后},差距惊人", "终于发现{秘密}了...", "{N}个{工具}同时{动作}会怎样", ] ``` ## 📈 成功指标 ### 短期目标(1个月) - [ ] 处理完42个录屏素材 - [ ] 生成至少100条短视频 - [ ] 测试完3个平台 - [ ] 找到1-2个爆款模板(完播率>50%) ### 中期目标(3个月) - [ ] 粉丝突破1万 - [ ] 单条播放量过10万 - [ ] 稳定日更(2-3条/天) - [ ] 形成固定风格和IP ### 最终目标(6个月) - [ ] **粉丝突破10万** ⭐ - [ ] 商业化(接广告/带货) - [ ] 建立素材库和模板库 - [ ] 形成可复制的生产流程 ## ⚙️ 配置选项 创建 `viral-config.json`: ```json { "defaults": { "duration": 60, "platform": "douyin", "hook": "question" }, "audio": { "bgm_volume": 0.25, "voice_volume": 0.75 }, "subtitle": { "font": "PingFang SC", "size": 48, "color": "#FFFFFF" }, "quality": { "video_bitrate": "6000k", "audio_bitrate": "128k" } } ``` ## 🐛 故障排除 ### 问题: Whisper未安装 ```bash pip install openai-whisper ``` ### 问题: ffmpeg未找到 ```bash # macOS brew install ffmpeg # Linux sudo apt install ffmpeg ``` ### 问题: 生成的视频文件过大 ```bash # 在editor.py中降低码率 --video-bitrate 4000k ``` ### 问题: 语音识别不准确 ```bash # 使用更大的Whisper模型 whisper audio.mp3 --model large ``` ## 📝 下一步计划 ### 立即执行(本周) 1. ✅ 完成核心pipeline开发 2. ✅ 测试单个视频处理 3. ⏳ 安装Whisper提升语音识别 4. ⏳ 批量处理10个最优质素材 5. ⏳ 发布到抖音测试反馈 ### 本月计划 1. 优化标题生成算法 2. 添加自动字幕功能 3. 集成背景音乐库 4. 开发封面自动生成 5. 处理全部42个素材 ### 长期规划 1. 建立爆款模板库 2. 添加A/B测试系统 3. 集成数据分析面板 4. 开发自动发布功能 5. 扩展到更多平台 ## 🔗 相关资源 - **方案文档**: `/Users/andy/Documents/AICode/09 Andy-Video-SKill/SCREENCAST_TO_VIRAL_PLAN.md` - **录屏素材库**: `/Users/andy/Documents/Andy录屏素材库` (42个文件, 5.7GB) - **MrBeast方法论**: `~/.claude/skills/mrbeast-skill/` - **视频分析技能**: `~/.claude/skills/video-content-analysis.md` ## 📞 使用支持 遇到问题? 1. 运行 `python3 viral.py doctor` 检查环境 2. 查看 `batch_report_*.json` 了解处理状态 3. 检查 `output/` 目录下的日志文件 --- **版本**: 1.0.0 (MVP) **创建日期**: 2026-08-09 **状态**: ✅ 核心功能已验证,可投入生产使用 **目标**: 10万粉丝 -
SKILL.md 8.3 KB
--- name: screencast-to-viral description: Transform long screen recordings into viral short-form videos with AI-powered editing, subtitles, and packaging. Designed for 10x content production velocity. tags: [video, editing, viral, automation, short-form] version: 1.0.0 --- # Andy's Screencast-to-Viral Pipeline ## 🎯 Core Mission Turn your 42+ screen recordings into 100+ viral short videos. Automated analysis → intelligent editing → viral packaging → batch publishing. Target: **10万粉丝** through systematic content production. ## When to Use - You have raw screen recordings (2-10 minutes) - Want to generate short-form videos (30-90 seconds) - Need batch processing for multiple files - Targeting Douyin/Bilibili/Xiaohongshu ## Quick Start ```bash # Analyze one recording to find highlights /screencast-to-viral analyze --input "path/to/video.mp4" # Generate short video (auto mode) /screencast-to-viral generate --input "path/to/video.mp4" # Batch process entire directory /screencast-to-viral batch --input "/Users/andy/Documents/Andy录屏素材库" # Preview without rendering /screencast-to-viral preview --input "path/to/video.mp4" ``` ## Pipeline Stages ### Stage 1: Analyze (智能分析) **What it does:** - Extract metadata (duration, resolution, audio) - Transcribe speech with Whisper - Extract key frames (0.5 fps) - Identify "highlight moments" - Generate cutting recommendations **Output:** ```json { "source": "video.mp4", "duration": 206.5, "transcription": "full text...", "highlights": [ { "start": 15.2, "end": 45.8, "score": 0.92, "reason": "High visual change + excited speech", "type": "result_reveal" } ], "recommendations": { "best_30s": { "start": 15.2, "end": 45.2 }, "best_60s": { "start": 10.0, "end": 70.0 }, "best_90s": { "start": 5.0, "end": 95.0 } } } ``` ### Stage 2: Edit (智能剪辑) **What it does:** - Extract highlight segment - Remove dead air and pauses - Speed up non-critical parts (1.2-1.5x) - Apply MrBeast "no dull moments" principle **Rules:** - Delete all silence >0.5s - Delete all "um", "uh", "嗯", "啊" - Speed up mouse movement/typing - Keep all "wow moments" ### Stage 3: Package (爆款包装) **What it does:** - Add viral hook (first 3 seconds) - Generate auto-subtitles - Add BGM (120-140 BPM) - Apply visual effects **Hook Templates:** ```javascript const hooks = { question: { text: "你见过{X秒}做出这个效果吗?", visual: "flash_final_result" }, challenge: { text: "大家都说这个不可能...", visual: "show_difficulty" }, result_first: { text: "直接看结果 →", visual: "show_result_immediately" } } ``` ### Stage 4: Design (标题+封面) **What it does:** - Generate 5 title variants (MrBeast formula) - Extract best frame for thumbnail - Add text overlay to thumbnail - Create A/B test versions **Title Templates:** ```python templates = [ "用AI{动作}{结果},只用了{N}秒", "{之前}到{之后},差距惊人", "终于发现{秘密}了...", "{N}个{工具}同时{动作}会怎样", ] ``` ### Stage 5: Export (批量导出) **What it does:** - Export to platform-specific formats - Generate metadata.json for each video - Create thumbnail variants - Prepare upload checklist **Platform Specs:** | Platform | Ratio | Duration | Bitrate | |----------|-------|----------|---------| | Douyin | 9:16 | 30-90s | 6000k | | Bilibili | 16:9 | 60-180s | 8000k | | Xiaohongshu | 3:4 | 30-60s | 5000k | ## Options Reference ```bash --input <path> # Input video file or directory --output <path> # Output directory (default: ./output) --duration <seconds> # Target duration: 30, 60, or 90 --platform <name> # douyin, bilibili, xiaohongshu, or all --style <template> # tech, tutorial, vlog, showcase --hook <type> # question, challenge, result_first --no-subtitle # Skip subtitle generation --no-music # Skip background music --speed <factor> # Speed multiplier (1.0-2.0) --preview # Generate preview only --batch # Process entire directory --force # Overwrite existing outputs ``` ## Configuration File Create `viral-config.json` in your project: ```json { "defaults": { "duration": 60, "platform": "douyin", "style": "tech", "hook": "question" }, "audio": { "bgm_volume": 0.25, "voice_volume": 0.75, "bgm_library": "~/Music/BGM" }, "subtitle": { "font": "PingFang SC", "size": 48, "color": "#FFFFFF", "outline": "#000000", "position": "bottom_center" }, "quality": { "video_bitrate": "6000k", "audio_bitrate": "128k", "preset": "medium" } } ``` ## Dependencies **Required:** - ffmpeg >= 5.0 - ffprobe (bundled with ffmpeg) - whisper (OpenAI) - `pip install openai-whisper` - Python >= 3.9 **Optional:** - yt-dlp (for reference video analysis) - imagemagick (for thumbnail design) ## Installation Check ```bash # Check if all tools are available /screencast-to-viral doctor ``` Expected output: ``` ✓ ffmpeg found (version 6.0) ✓ ffprobe found ✓ whisper found ✓ Python 3.11 found ⚠ imagemagick not found (optional) ✓ All required dependencies satisfied ``` ## Workflow Example ### Single Video Processing ```bash # Step 1: Analyze /screencast-to-viral analyze --input "李子柒01.mp4" # Review analysis.json, then: # Step 2: Generate /screencast-to-viral generate \ --input "李子柒01.mp4" \ --duration 60 \ --platform douyin \ --hook question # Output: # - output/李子柒01_viral_60s.mp4 # - output/李子柒01_thumbnail.jpg # - output/李子柒01_titles.txt # - output/李子柒01_metadata.json ``` ### Batch Processing ```bash # Process all recordings /screencast-to-viral batch \ --input "/Users/andy/Documents/Andy录屏素材库" \ --output "./viral_output" \ --duration 60 \ --platform all # Generates: # - 42 source videos → 126 short videos (3 versions each) # - Organized by platform # - Ready-to-upload package ``` ## Quality Checklist Before publishing, verify: - [ ] Video plays smoothly (no stutters) - [ ] Subtitles are accurate and readable - [ ] Audio levels balanced (BGM not too loud) - [ ] Hook grabs attention in first 3 seconds - [ ] No dead air or long pauses - [ ] Thumbnail has visual contrast - [ ] Title uses numbers and curiosity gap - [ ] Ends with clear CTA or cliffhanger ## MrBeast Principles Applied 1. **CTR × AVD formula** - Every decision optimizes click-through or watch time 2. **No dull moments** - Delete everything boring 3. **Stair-stepping** - Content escalates continuously 4. **Simple concept × extreme execution** - Clear idea, flawless delivery 5. **First 30 seconds rule** - Hook, promise, action ## Success Metrics Track these for every video: ```json { "completion_rate": 0.65, // >50% = viral potential "like_rate": 0.08, // >5% = high value "comment_rate": 0.03, // >2% = engaging "share_rate": 0.01, // >1% = exceptional "follower_growth": 127 // per 10k views } ``` ## Troubleshooting ### Issue: Whisper transcription fails **Solution:** Check audio track exists with `ffprobe -show_streams video.mp4` ### Issue: Subtitles out of sync **Solution:** Use `--subtitle-offset <seconds>` to adjust timing ### Issue: Generated video too large **Solution:** Lower bitrate with `--video-bitrate 4000k` ### Issue: Hook doesn't match content **Solution:** Manually specify highlight with `--segment 15.2-45.8` ## Iteration Strategy 1. **Week 1**: Process 10 best recordings → 30 test videos 2. **Week 2**: Analyze metrics → identify winning patterns 3. **Week 3**: Process remaining 32 recordings with winning template 4. **Week 4**: Scale to daily publishing (2-3 videos/day) ## Output Structure ``` viral_output/ ├── douyin/ │ ├── video_001/ │ │ ├── final.mp4 │ │ ├── thumbnail.jpg │ │ ├── titles.txt │ │ └── metadata.json │ └── video_002/ ├── bilibili/ └── xiaohongshu/ ``` ## Next Steps After skill creation: 1. Test with 1 recording (李子柒01.mp4 or GPT做电脑壁纸.mp4) 2. Iterate on hook templates 3. Build title generation logic 4. Create batch processing script 5. Launch production pipeline --- **Status**: 🚧 In Development **Goal**: Transform 42 recordings → 100+ viral videos → 10万粉丝 **Deadline**: 3 months from start -
start.sh 7.5 KB
Loading… -
viral.py 4 KB
Loading… -
viral_editor.py 12.2 KB
Loading…
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.