tiktok-product-analysis
Parallel analysis pipeline for TikTok product campaigns. Handles image analysis, video analysis, and market synthesis using Gemini async MCP. Prepares all foundation data before script generation. Designed for batch processing multiple products simultaneously.
npx skills add majiayu000/claude-skill-registry --skill tiktok-product-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.
What it does
The skill orchestrates a parallel analysis pipeline for TikTok product campaigns. It handles image analysis, video analysis, and market synthesis, all to prepare foundation data before script generation. The executor is Gemini CLI MCP (async), enabling parallel tasks, and the output consists of analysis files that the script generator will reference (without duplicating content).
How it works
- Execution uses Gemini CLI MCP (async) to run tasks in parallel where appropriate.
- It processes TikTok product campaigns in a batch-oriented fashion, preparing analysis assets prior to any script generation step.
- The skill emphasizes producing analysis files (e.g., image analysis, video analyses, and video synthesis) that will be consumed by downstream script generation processes.
When to use it
- Use when you need to initialize analysis groundwork for multiple TikTok product campaigns and want to stage image analysis, video analysis, and market synthesis in parallel before generating scripts.
- Applicable when analysis outputs are intended to be referenced by a separate script generator rather than embedded in the analysis itself.
What it can touch
- Tools: claude-code
- It references analysis prompts and synthesis prompts as part of the workflow, with outputs stored as analysis files for later use by the script generator.
Caveats
- The skill relies on Gemini async MCP for parallelism and does not guarantee specific script content quality; outputs are foundation data for scripts.
- No outcomes beyond producing analysis files are stated; success is defined as producing the required analysis files for review by downstream steps.
# TikTok Product Analysis Skill **PURPOSE:** Prepare all analysis foundation before script generation **EXECUTOR:** Gemini CLI MCP (async for parallelism) **OUTPUT:** Analysis files that script generator will reference (not duplicate) --- ## Compliance & Policy Notes (DE Market) - ENHANCED ### Safety Matrix with Concrete Examples This skill should explicitly capture policy-sensitive claims so downstream scripts stay safe. | Risk Type | ❌ AVOID | ⚠️ USE CAREFULLY | ✅ SAFE | |:----------|:---------|:----------------|:--------| | **Price** | "nur €10!", "50% Rabatt" | "~€10" with disclaimer | "erschwinglich", "preiswert" | | **Waterproof** | "100% wasserdicht", "完全防水" | "IP67" (only if sourced) | "spritzwassergeschützt" | | **Medical** | "heilt", "Schmerzfreiheit" | "Entspannung" (no guarantees) | "angenehm", "komfortabel" | | **Tech Specs** | "4K Support" (ambiguous) | "4K Dekodierung" (if sourced) | "HD Qualität" | **Example format for analysis files:** ```markdown * **CRITICAL**: Das Produkt ist NICHT spülmaschinenfest. Darauf muss in Kommentaren hingewiesen werden. **关键**：该产品不可放入洗碗机。必须在评论中指出。 ``` Add these as explicit DO/DON'T bullets with concrete examples in the generated `ref_v
- Compliance & Policy Notes (DE Market) - ENHANCED
- Safety Matrix with Concrete Examples
- Bilingual Output Standards | 双语输出标准
- Agent Assignment
- ⚠️ Concurrency Limits | 并发限制
- Model Policy (MANDATORY)
- German Market Intelligence (MANDATORY in videosynthesis.md)
- The Real Bottleneck: Videos Per Product
- Why This Matters
- Pipeline Strategy Per Product
- Time Impact (8 Products Example)
- Workflow Overview
- Phase 1: Sequential Product Analysis Pipeline
- Complete Implementation
verify_analysis.sh echo "=== Analysis Verification: $product_id ===" Check 1: Image analysis (if images exist) if [ -d "$base/product_images" ]; then if [ "$img_count" -gt 0 ]; then if [ -f "$base/product_images/image_analysis.md" ]; then if [ "$lines" -ge 200 ]; then echo "✅ Image analysis: $lines lines" else echo "⚠️ Image analysis incomplete: $lines lines (need 200+)"
What does the tiktok-product-analysis skill do?
Parallel analysis pipeline for TikTok product campaigns. Handles image analysis, video analysis, and market synthesis using Gemini async MCP. Prepares all foundation data before script generation. Designed for batch processing multiple products simultaneously.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill tiktok-product-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.