A specialized AI agent skill designed to automatically classify and grade data fields and SQL DDL files according to national and financial industry standards.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install 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 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 Data Classification Skill?
The Data Classification skill is a robust tool for developers and data officers who need to align their datasets with strict regulatory frameworks. It intelligently analyzes single field names, field lists, or entire SQL/DDL files to suggest security levels and categories. By leveraging Openclaw Skills, users can ensure their data architecture adheres to the GB/T 43697-2024 general data rules and the JR/T 0197-2020 financial security standards.
This skill goes beyond simple keyword matching by implementing a dual-label system for financial contexts, providing both general and industry-specific security levels. It serves as a high-efficiency first-pass auditor, generating detailed classification reports that highlight high-risk data and items requiring manual business review.
Data Classification Skill Use Cases
- Automatically grading database schemas during the migration or audit process.
- Implementing financial dual-labeling for banking and fintech data compliance.
- Identifying sensitive personal information (PII) within large SQL DDL files.
- Validating data security levels against the GB/T 43697-2024 general data grading rules.
- Streamlining data governance workflows by providing machine-readable classification suggestions.
How Data Classification Skill Works
- The agent identifies the input type, whether it is a raw field name string or a path to a SQL/DDL file.
- For SQL files, the system parses table names, column types, and metadata comments to build context.
- The skill invokes a specialized Python helper script to perform a heuristic-based first pass.
- It references machine-readable compliance tables (like JR/T 0197 Appendix A) to find exact matches.
- A dual-label logic is applied for financial scenarios, calculating the minimum security level required.
- A coverage check is performed to ensure every single input field is accounted for in the output.
- The results are delivered as an inline table or a downloadable CSV file depending on the field count.
Data Classification Skill Setup
To use this skill within your environment, ensure you have the classification scripts and reference data available. You can run the helper script directly via the CLI:
# Classify a single field in financial mode
python3 skills/data-classification/scripts/classify_data.py --field "customer_id" --mode finance
# Classify an entire SQL schema and output as Markdown
python3 skills/data-classification/scripts/classify_data.py --sql path/to/schema.sql --mode finance --format markdown
Data Classification Skill Data Schema & Taxonomy
The skill produces a structured output mapping each input field to its regulatory metadata.
| Column | Description |
|---|---|
| Field Name | The original identifier from the input. |
| General Category | Industry domain and data subject classification. |
| General Level | Security grade (General, Important, or Core). |
| Financial Label | Recommended JR/T 0197 sub-category (for financial mode). |
| Security Level | Minimum security level (1-5) according to financial standards. |
| Confidence | The certainty of the AI's suggestion. |
Data Classification Skill Advanced Features
- Financial Dual-Labeling: Simultaneously assigns general national labels and industry-specific financial labels.
- Heuristic Fallbacks: Intelligent logic to handle ambiguous fields when exact matches in regulatory appendices aren't found.
- Automated CSV Export: Smart routing that generates downloadable CSV files for datasets exceeding 20 fields.
- Strict Coverage Validation: Internal verification system that ensures zero missing fields in the final report.
- Context-Aware Parsing: Utilizes SQL comments and table relationships to improve classification accuracy over raw field names.
SKILL.md
Loading
Related Openclaw Skills
Subscription Audit & Cancel Kit
An organizational tool that guides users through auditing recurring charges and executing a structured cancellation plan for unused services.
Job Offer Evaluation Kit
A structured decision-support framework for comparing multiple job offers across compensation, benefits, career growth, and lifestyle impact.
Home Repair Contractor Hiring Kit
A professional planning tool for homeowners to define project scopes, compare contractor estimates, and organize repair documentation without legal complexity.
Academic Thesis Workflow
A standardized, reproducible four-step workflow that transforms research themes into complete, peer-review-ready academic theses.
Medical Bill Review Kit
A specialized tool for organizing medical billing documents, identifying common errors, and preparing structured scripts for insurance and provider negotiations.
AI Cardiac Rehab Management System
A clinical-grade cardiac rehabilitation web application designed for automated risk stratification and personalized recovery planning.
Featured*
