A sophisticated data validation tool that cross-references Xiaohongshu and Dianping reviews to generate high-confidence restaurant recommendations.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install clean-skill
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 clean-skill 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 Restaurant Review Cross-Check?
The Restaurant Review Cross-Check skill is a powerful utility designed to solve the problem of unreliable or biased dining recommendations. By leveraging the Openclaw Skills framework, this tool simultaneously queries Dianping for quantitative ratings and Xiaohongshu for qualitative social engagement, ensuring that a restaurant's popularity on social media is backed by consistent customer satisfaction.
This skill is particularly valuable for navigating the complex landscape of urban dining, where marketing hype often obscures actual food quality. It employs advanced data matching and sentiment analysis to provide a unified recommendation score, giving users a clear, objective view of the best dining options in any given district.
Restaurant Review Cross-Check Use Cases
- Finding top-rated restaurants in specific city districts like Shanghai Jing'an or Beijing Chaoyang.
- Filtering out viral internet-famous spots that lack consistent high ratings on professional review platforms.
- Conducting deep research into specific cuisine types with custom thresholds for ratings and review counts.
- Validating the authenticity of social media hype by comparing engagement metrics with long-term rating trends.
How Restaurant Review Cross-Check Works
- Data Collection: The skill triggers simultaneous searches on Dianping and Xiaohongshu based on user-defined location and cuisine parameters.
- Attribute Extraction: It extracts structured data including ratings, price ranges, and addresses from Dianping, alongside engagement metrics and sentiment from Xiaohongshu.
- Fuzzy Matching: Using thefuzz library, it calculates Levenshtein distance to match restaurants across platforms, accounting for name variations and chain store suffixes.
- Consistency Analysis: An algorithm calculates a consistency score based on how well the ratings and user sentiments align between the two platforms.
- Score Generation: A final recommendation score (0-10) is produced by weighting Dianping ratings, Xiaohongshu engagement, and the calculated consistency score.
Restaurant Review Cross-Check Setup
To integrate this capability into your environment, install the necessary Python dependencies:
pip install requests beautifulsoup4 pandas numpy thefuzz selenium lxml
Configuration is handled via scripts/config.py, where you can define proxy lists for anti-scraping protection and set default thresholds for minimum ratings. Note that Xiaohongshu data fetching requires active session cookies for full access within the Openclaw Skills ecosystem.
Restaurant Review Cross-Check Data Schema & Taxonomy
The skill structures validated restaurant data into a clear hierarchy for easy consumption:
| Field | Description |
|---|---|
| Recommendation Index | A final score out of 10 based on multi-platform validation. |
| Platform Ratings | Comparative view of Dianping (1-5) vs Xiaohongshu (sentiment-based). |
| Engagement Metrics | Review counts from Dianping and note counts/saves from Xiaohongshu. |
| Consistency Level | Qualitative indicator (High/Medium/Low) of data alignment. |
| Metadata | Address, average price per person, and platform-specific keyword tags. |
Restaurant Review Cross-Check Advanced Features
- Multi-Platform Sentiment Analysis: Uses NLP to categorize user feedback into food quality, service, and atmosphere mentions.
- Dynamic Proxy Rotation: Built-in support for residential proxies to bypass platform-specific rate limits and anti-scraping measures.
- Customizable Confidence Thresholds: Users can define specific criteria for high-confidence results to filter out low-data entries.
- Intelligent Error Handling: Includes exponential backoff and automated retry logic for platform timeouts.
SKILL.md
Loading
Related Openclaw Skills
PPT Generator
An automated tool that converts raw speaker scripts into sleek, Steve Jobs-inspired vertical HTML presentations with a minimalist tech aesthetic.
Claw Drive
An AI-managed personal drive that provides automated categorization, deduplication, and natural language retrieval for your local files.
SiYuan Note Task Management
A Python-based integration for managing structured tasks and databases within SiYuan Note via its HTTP API.
AI Drama Prompt Factory
A comprehensive end-to-end pipeline designed to transform novels or original story ideas into structured, production-ready AI prompt packages for video and audio generation.
Restaurant Review Cross-Check
A data-driven validation tool that cross-references restaurant ratings and social engagement across Xiaohongshu and Dianping to ensure recommendation accuracy.
Local File Reader
A powerful utility for AI agents to access, summarize, and search content across various local file formats.
Featured*
