tiktok-targeted-analysis
Analyzes user-provided TikTok URLs to generate comprehensive video breakdowns, 1 replication script (100% structure copy), and AI video generation prompts for Veo 3.1/Sora in copy-paste ready markdown code blocks
npx skills add majiayu000/claude-skill-registry --skill tiktok-targeted-analysis --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# TikTok Targeted Video Analysis Skill **PURPOSE:** Deep analysis of competitor/inspiration TikTok videos for exact structural replication **KEY DISTINCTION:** Unlike the product-based workflow (scrape → top 5 videos → 3 different scripts), this skill analyzes specific user-provided URLs to generate 1 exact replica script with AI-ready video generation prompts. --- ## What This Skill Does ### Input - **CSV file** with TikTok URLs or **single URL** via command line - CSV columns: `url`, `product_name`, `campaign_id` (optional) ### Output (per video) ``` targeted_analysis/YYYYMMDD/{video_id}/ ├── metadata.json # Creator, views, likes, duration ├── video.mp4 # Downloaded video ├── frames/ (every 2s) # Keyframes for analysis ├── audio.mp3 # Extracted audio ├── transcript.json # Hybrid transcription ├── analysis.md # Combined 3-part analysis ├── character_descriptions.md # Detailed casting guide ├── replication_script.md # Obsidian-ready script ├── ai_video_prompts.md # Shot-by-shot Veo/Sora prompts ├── processing_status.json # Phase completion tracking └── analysis.log # Debug log ``` --- ## 5-Phase Pipeline ### Phase 1: Metadata Extraction - Extract video ID from URL (regex + yt-dlp f
- What This Skill Does
- Input
- Output (per video)
- 5-Phase Pipeline
- Phase 1: Metadata Extraction
- Phase 2: Frame + Audio Extraction + Transcription
- Phase 3: Comprehensive Analysis (4 Sub-Phases)
- Phase 4: Replication Script Generation
- Phase 5: AI Video Prompts Generation
- Integration with Existing Workflow
- Key Technical Decisions
- 1. Frame Interval: 2s vs 3s
- 2. Three-Phase Gemini Analysis
- 3. AI Prompt Format
Ensure you're at repo root cd /Users/lxt/Movies/TikTok/WZ/lukas_9688 Virtual environment with dependencies cd scripts source venv/bin/activate Required tools which yt-dlp # Video downloading which ffmpeg # Frame/audio extraction which gemini # Analysis python -c "from faster_whisper import WhisperModel" # Transcription
What does the tiktok-targeted-analysis skill do?
Analyzes user-provided TikTok URLs to generate comprehensive video breakdowns, 1 replication script (100% structure copy), and AI video generation prompts for Veo 3.1/Sora in copy-paste ready markdown code blocks
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill tiktok-targeted-analysis --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.