A robust batch-processing interface designed to identify, classify, and grade the sensitivity of database fields using AI-driven reasoning.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install shuyan-data-classification
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 shuyan-data-classification 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 Shuyan Data Classification?
The Shuyan Data Classification skill provides a specialized synchronization interface for managing large-scale data governance tasks. By leveraging this tool within the Openclaw Skills framework, developers can automate the identification of sensitive information, assign security levels from general to top secret, and retrieve detailed reasoning for every classification decision. It is specifically engineered to handle batch processing of field metadata, including English and Chinese names, comments, and real-world data samples.
This skill serves as a critical bridge for enterprises needing to maintain compliance and data security. It integrates seamlessly into existing workflows, allowing for high-confidence data tagging without the manual overhead typically associated with data audits. Whether you are migrating legacy systems or securing new applications, this addition to your Openclaw Skills library ensures your data remains structured and safe.
Shuyan Data Classification Use Cases
- Batch classify database fields during large-scale system migrations or audits.
- Identify and grade sensitive data like PII, financial records, and core business secrets.
- Automate the generation of data sensitivity reports with confidence scores and reasoning.
- Synchronize field-level classification labels across multiple business systems using Openclaw Skills.
How Shuyan Data Classification Works
- The user prepares a JSON payload containing field metadata such as column names, table comments, and sample data values.
- The skill authenticates with the Shuyan API using a Bearer Token configured in the environment.
- The batch request is processed synchronously, where the engine evaluates the context of the data against standard classification codes.
- The system assigns a sensitivity level ranging from 1 (General) to 5 (Top Secret) and provides a reasoning process for each field.
- The final results are returned as a structured array, allowing Openclaw Skills to pass the data to downstream automation or reporting tools.
Shuyan Data Classification Setup
To get started with this skill in the Openclaw Skills environment, configure your API credentials using environment variables:
# Add to your shell profile (~/.zshrc or ~/.bashrc)
export SHUYAN_API_KEY="your-api-key-here"
export SHUYAN_API_URL="http://localhost:8080"
Alternatively, you can enable it directly in your Openclaw Skills configuration file at ~/.openclaw/openclaw.json:
{
"skills": {
"entries": {
"shuyan-data-classification": {
"enabled": true,
"apiKey": "your-api-key-here",
"apiUrl": "http://localhost:8080"
}
}
}
}
Shuyan Data Classification Data Schema & Taxonomy
The skill processes a list of field objects and returns enriched classification data as follows:
| Attribute | Type | Description |
|---|---|---|
colNameEn |
string | The English name of the database column. |
sampleList |
array | Representative data samples used for AI inference. |
standardCode |
string | The classification standard code used for the request. |
sensitivityLevel |
integer | Output grade: 1 (General), 2 (Important), 3 (Core), 4 (Sensitive), 5 (Secret). |
confidence |
integer | The certainty score of the AI's classification result. |
reasoningProcess |
string | The logical explanation behind the assigned classification and grade. |
Shuyan Data Classification Advanced Features
- High-throughput batch processing supporting up to 100 records per synchronous request.
- Intelligent retry mechanisms for individual field failures within a batch operation.
- Support for custom sensitivity grading standards via Redis key integration.
- Detailed reasoning output for transparent data governance audits within the Openclaw Skills ecosystem.
SKILL.md
Loading
Related Openclaw Skills
Shulian Weather
A powerful integration for Openclaw Skills that provides real-time weather updates and multi-day forecasts via the WeatherAPI.com platform.
GitHub Trending Fetcher
A powerful tool to automatically fetch and monitor the most popular repositories on GitHub across various timeframes.
GitHub Trending Daily
An automated utility that fetches GitHub Trending repositories and pushes formatted reports to DingTalk groups.
DingTalk Group Saver
A background utility that automatically archives DingTalk group metadata and IDs to persistent storage whenever the agent is @mentioned.
ZenTao Analytics
An automated data analysis tool for ZenTao that evaluates team performance, task efficiency, and workload saturation through API and database integration.
Data Quality Operations
A systematic framework for automating data quality checks, anomaly detection, and incident reporting.
Featured*
