An intelligent classification engine that categorizes construction data into structured, semi-structured, or unstructured types while recommending optimal storage and processing tools.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install data-type-classifier
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-type-classifier 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 Type Classifier?
The Data Type Classifier is a technical utility designed for Openclaw Skills that implements the Data-Driven Construction (DDC) methodology. It serves as a foundational tool for data engineers and developers working in the AEC (Architecture, Engineering, and Construction) industry, allowing them to systematically identify the nature of their data sources. Whether dealing with BIM models, project schedules, or legal contracts, this skill provides the necessary taxonomy to handle diverse datasets efficiently.
By leveraging specific format signatures and structural analysis, the skill goes beyond simple file identification. It evaluates data characteristics such as geometric properties, temporal sequences, and schema presence to suggest the most effective database architectures and software libraries for processing. This ensures that every piece of information in a project is routed to the correct part of a modern data stack, enhancing the overall utility of Openclaw Skills in complex engineering environments.
Data Type Classifier Use Cases
- Automating the initial audit of project folders to identify critical data formats like IFC, RVT, and MPP.
- Developing ETL pipelines by identifying which sources require OCR, NLP, or direct SQL ingestion.
- Strategic planning for data lake architectures by classifying sources into relational, document, or vector storage buckets.
- Enhancing BIM workflows by isolating geometric and spatial data for specialized processing with tools like IfcOpenShell.
How Data Type Classifier Works
- The skill receives a data source input, which can include filenames, file extensions, or raw sample data snippets.
- It performs a signature check against a comprehensive map of construction-specific formats and their associated data structures.
- A secondary analysis evaluates characteristics like the presence of a schema, binary vs. text content, and the existence of geometric or temporal data.
- The engine maps these findings to a storage recommendation, such as Relational DB for structured tables or Vector DB for unstructured text.
- Finally, it outputs a detailed DataClassification object or a project-wide ClassificationReport containing integration strategies and recommended processing tools.
Data Type Classifier Setup
This skill is primarily a Python-based logic engine. Ensure your environment is configured correctly to support the extended library recommendations provided by Openclaw Skills.
# Core requirements
pip install python-docx pdfplumber ezdxf pandas
# For BIM and geometry support (optional but recommended)
pip install ifcopenshell
Note: For processing unstructured images or complex PDFs, ensure Tesseract OCR is installed and available in your system path.
Data Type Classifier Data Schema & Taxonomy
The skill organizes analysis into a structured hierarchy defined by the following metadata taxonomy:
| Component | Description |
|---|---|
| DataStructure | Classification into categories: Structured, Semi-Structured, Unstructured, Geometric, Temporal, or Spatial. |
| DataFormat | Identification of specific industry formats (e.g., .ifc, .rvt, .mpp, .csv, .json). |
| StorageRecommendation | Guidance on the best storage backend (e.g., Graph DB, Time-Series DB, Object Storage). |
| Characteristics | Boolean flags for features like has_schema, has_geometry, and is_binary. |
| Confidence | A float value (0.0 to 1.0) representing the certainty of the classification. |
Data Type Classifier Advanced Features
- Batch processing capabilities to analyze hundreds of data sources simultaneously and generate a unified integration strategy.
- Context-aware storage logic that adjusts recommendations based on estimated data volume and update frequency.
- Intelligent tool mapping that suggests specific Python libraries (like ezdxf for CAD or xerparser for Primavera P6) based on the detected format.
- Seamless workflow transitions within Openclaw Skills to pass classified data directly to specialized SQL builders or PDF extractors.
SKILL.md
Loading
Related Openclaw Skills
Data Source Audit for Construction
A comprehensive auditing tool to map, analyze, and optimize data flows and systems within construction organizations.
Data Silo Detection
A specialized diagnostic tool that identifies, maps, and prioritizes the remediation of disconnected data repositories in construction organizations.
Construction Data Quality Checker
A Python-powered quality assessment engine designed to validate construction data against industry-standard metrics like completeness and accuracy.
Data Profiler for Construction
A comprehensive Python-based profiling engine designed to assess the quality, patterns, and distributions of construction industry datasets.
df-merger
A Python-based utility for merging disparate construction data sources into unified pandas DataFrames with intelligent schema reconciliation and fuzzy matching.
DGN to Excel Data Extractor
A specialized utility for converting legacy and modern DGN infrastructure CAD files into queryable Excel databases.
METADATA
Featured*
