An AI-powered market research agent that mines user demand and pain points from major Chinese social and e-commerce platforms to drive product innovation.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install china-demand-mining
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install china-demand-mining using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is China Demand Mining?
China Demand Mining is a sophisticated technical agent designed to tap into the authentic voices of users across the Chinese public domain. By monitoring platforms such as Xiaohongshu, Douyin, Taobao, and Weibo, the skill identifies unmet needs, functional gaps, and product dissatisfaction. It is a vital component of the Openclaw Skills ecosystem for developers and product managers looking to enter or optimize their presence in the Chinese market.
The skill goes beyond simple scraping by implementing a rigorous data cleaning and classification workflow. It specifically targets negative feedback and complaints, which are often the richest sources of innovation. With a mandatory requirement for large sample sizes, it ensures that the resulting research reports are statistically significant and provide a high level of confidence for strategic decision-making.
China Demand Mining Use Cases
- Discovering market gaps by analyzing competitor complaints on Taobao and JD.
- Researching pain points for new physical products using Xiaohongshu and Douyin feedback.
- Validating service or content ideas through sentiment analysis on Weibo and Zhihu.
- Generating high-volume user research reports (2000+ entries) for product iteration.
- Monitoring industry-wide shifts in user expectations and emotional triggers.
How China Demand Mining Works
- Target Definition: The user specifies a product, brand, or industry domain for investigation.
- Source Selection: The agent automatically chooses platforms based on whether the demand is for a physical product or a service/content.
- Multi-dimensional Search: It executes complex search patterns focusing on keywords like bug, hard to use, or expectations.
- Data Acquisition: Scraping 3000-5000 raw entries to ensure at least 2000 high-quality, cleaned data points.
- Classification: AI labels data by category (functionality, experience, performance, etc.) and sentiment intensity.
- Prioritization: Feedback is ranked from P0 to P3 based on frequency and impact.
- Report Generation: A structured Markdown report is produced, including an opportunity matrix and actionable product suggestions.
China Demand Mining Setup
To deploy this skill within your Openclaw Skills environment, ensure your crawler configurations are optimized for Chinese network protocols.
# Install the demand mining skill
openclaw install china-demand-mining
# Configure platform-specific parameters
openclaw config set demand_mining_sample_size 2000
Users should ensure that the search query targets the correct demand type (physical vs. non-physical) to activate the appropriate platform routing logic.
China Demand Mining Data Schema & Taxonomy
The skill maintains a structured taxonomy for all mined feedback to ensure clarity in the final report:
| Attribute | Description |
|---|---|
| Source Platform | Origin of data (e.g., Xiaohongshu, Douyin, Taobao) |
| Demand Category | Classified as Functional, Experience, Performance, Pricing, or Competition |
| Sentiment Strength | Rated as Strong (Aggressive), Moderate (Disappointed), or Mild (Suggestive) |
| Frequency | Quantitative count of unique users reporting the same issue |
| Actionability | High, Medium, or Low based on technical feasibility |
| Priority | P0 (Urgent) to P3 (Long-term) |
China Demand Mining Advanced Features
- Intelligent Platform Routing: Automatically prioritizes e-commerce sites for goods and social media for services.
- High-Confidence Statistical Threshold: Enforces a 2000-entry minimum for 95% confidence intervals.
- Advanced Deduplication: Filters out repetitive content with over 80% similarity to ensure unique insights.
- Opportunity Matrix: Maps raw user pain points directly to short-term 'Quick Wins' and long-term product roadmaps.
- Negative Feedback Bias: Specifically weights 1-star reviews and critical social posts (min 40%) to highlight the most urgent issues.
SKILL.md
Loading
Related Openclaw Skills
Smart Search
An automated search utility that intelligently toggles between Bing and DuckDuckGo based on language detection to provide the most relevant results.
Bing Search
A high-precision Microsoft Bing search integration providing filtered, ranked, and summarized web results without requiring an API key.
Openclw Translation Skill
A high-efficiency command-driven translation utility for Openclaw Skills that provides intelligent bidirectional Chinese-English translation and multi-language support.
WeChat Article Writer
A professional AI writing assistant for WeChat Official Accounts that automates everything from viral title generation to long-form content and AI-powered illustrations.
browser-use-local
A local browser automation powerhouse designed for persistent sessions, AI agent orchestration, and advanced data extraction within the OpenClaw environment.
Gemini Web Search
Perform deep web research and fact-finding with sourced summaries using the Gemini CLI.