An automated data collection and processing engine designed for seamless integration within the OpenClaw ecosystem.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install openclaw-wealth-guide
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 openclaw-wealth-guide 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 Smart Data Harvester?
Smart Data Harvester is a professional-grade automation tool built to streamline the entire lifecycle of data acquisition. As a key entry in the Openclaw Skills library, it offers a unified interface for gathering data from disparate sources—including web pages, REST APIs, relational databases, and local files. It is specifically optimized for performance and ease of use, providing developers with a robust pipeline to transform raw information into actionable insights.
Beyond simple scraping, this skill emphasizes data integrity through an intelligent processing pipeline. Users can define custom rules for cleaning, deduplication, and aggregation, ensuring that the final output is structured and ready for analysis. Whether you are building a research database or a business intelligence dashboard, this tool integrates natively into OpenClaw to provide a high-efficiency experience.
Smart Data Harvester Use Cases
- Automating recurring web scraping tasks using CSS selectors or XPath.
- Synchronizing data between third-party REST APIs and local databases.
- Generating automated daily business reports in Excel or PDF formats.
- Cleaning and formatting large datasets for machine learning or analytics.
- Scheduling background data collection tasks that run without manual intervention.
How Smart Data Harvester Works
- Activate the skill within your OpenClaw environment to access the harvest command set.
- Configure the data source adapters by specifying target URLs, API endpoints, or database connection strings.
- Define the processing logic, including data cleaning rules, field transformations, and validation checks.
- Trigger the collection process manually or via the built-in task scheduler for periodic updates.
- Route the processed data to the exporter module to generate files in your preferred format such as JSON, CSV, or SQLite.
Smart Data Harvester Setup
The easiest way to get started with this member of the Openclaw Skills collection is via ClawHub:
npx clawhub install data-harvester
For manual installation and customization:
git clone https://gitee.com/du-xuegong/openclaw-wealth-guide.git
cd openclaw-wealth-guide
uv pip install -r requirements.txt
Smart Data Harvester Data Schema & Taxonomy
The skill organizes its operations through a modular architecture to ensure clear data lineage:
| Module | Functionality | Key Metadata |
|---|---|---|
| Adapters | Input connectivity | URLs, CSS Selectors, API Keys, SQL Queries |
| Processors | Logic & Cleaning | Formatting rules, Deduplication flags, Aggregation keys |
| Exporters | Output generation | Path, Format (JSON/Excel/PDF/SQLite) |
| Scheduler | Automation | Cron expressions, Job IDs |
Smart Data Harvester Advanced Features
- Native integration with APScheduler for complex, cron-based task automation.
- Support for multi-source aggregation, allowing you to join data from APIs and Web sources in one pass.
- High-fidelity PDF report generation with professional formatting.
- Comprehensive Python API for embedding harvesting logic into custom Openclaw Skills workflows.
- Enterprise-grade technical support and priority feature development for high-volume users.
SKILL.md
Loading
Related Openclaw Skills
Amazon Deep Selection V4 (Multi-Platform)
A high-precision Amazon product research automation skill that performs cross-platform data verification, image-based sourcing, and comprehensive financial margin analysis.
Xu Jiayin Perspective v2.0
A strategic simulation skill for analyzing high-leverage business models and identifying corporate risk signals through the lens of the Evergrande framework.
Xiong Xiaoge Perspective v2.0
A sophisticated cognitive operating system that emulates the investment logic, pioneering spirit, and strategic vision of IDG Capital founder Xiong Xiaoge.
Wang Wei Perspective v2.0 (SF Express Founder Mindset)
A strategic mindset simulation of S.F. Express founder Wang Wei, focusing on direct-management, technology-driven logistics, and long-term business value.
Multi-Stop Flight Planner
A professional CLI-driven travel agent that automates the discovery and booking of complex multi-city flight itineraries with real-time pricing.
Content Engine TK
A comprehensive content orchestration system that transforms single briefs into full content pyramids including blogs, social threads, and newsletters.
Featured*
