A Python-powered quality assessment engine designed to validate construction data against industry-standard metrics like completeness and accuracy.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install data-quality-check
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-quality-check 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 Construction Data Quality Checker?
This Openclaw Skills module implements the Data Driven Construction (DDC) methodology to audit technical project data. By focusing on the five pillars of data quality—completeness, accuracy, consistency, timeliness, and validity—it helps engineers and project managers avoid costly mistakes caused by erroneous BIM exports or manual data entry errors.
The skill provides a robust framework for assessing data health, generating letter-grade reports (from A+ to F), and flagging specific issues for remediation. It is particularly effective for teams looking to standardize their data governance using Openclaw Skills to ensure that every spreadsheet, CSV, or database entry meets the high precision required in the AEC industry.
Construction Data Quality Checker Use Cases
- Validating BIM exports from Revit or IFC for missing parameters or duplicate element IDs.
- Auditing construction cost and schedule data for logical consistency, such as ensuring end dates never precede start dates.
- Checking the validity of specialized strings like IFC GUIDs, cost codes, and grid references using industry-standard regex patterns.
- Monitoring data timeliness to ensure project dashboards are based on recent updates rather than stale information.
- Automating pre-flight checks before importing construction data into centralized analytics databases or ERP systems.
How Construction Data Quality Checker Works
- The user loads construction data from sources like Excel, CSV, or BIM exports into a Pandas DataFrame.
- The DataQualityChecker initializes the dataset and prepares a set of validation rules based on DDC standards and project-specific requirements.
- Automated checks are executed across the five dimensions: completeness (null checks), accuracy (range bounds), consistency (uniqueness), timeliness (age analysis), and validity (pattern matching).
- The engine calculates an overall quality score and assigns a technical grade based on predefined performance thresholds.
- A comprehensive report is generated in Excel or CLI format, highlighting specific row-level issues and providing an actionable summary for data cleaning.
Construction Data Quality Checker Setup
To use this tool within your Openclaw Skills environment, ensure you have Python 3 and the necessary libraries installed.
# Ensure Python 3 is installed
python3 --version
# Install required dependencies for data processing and reporting
pip install pandas numpy openpyxl
Construction Data Quality Checker Data Schema & Taxonomy
The skill organizes quality metrics into a structured taxonomy to simplify data governance. Below is the schema used for assessment within Openclaw Skills:
| Metric | Technical Logic | Standard Threshold |
|---|---|---|
| Completeness | Percentage of non-null values across required columns | ≥ 95% |
| Accuracy | Verification that numeric values fall within physical or financial bounds | ≥ 98% |
| Consistency | Validation of unique IDs and cross-field logical relationships | ≥ 99% |
| Validity | Regex matching for specialized formats like Revit IDs or IFC GUIDs | ≥ 95% |
| Timeliness | Analysis of record age based on the last modified timestamp | ≥ 80% |
Construction Data Quality Checker Advanced Features
- Custom Validation Rules Builder: Define project-specific constraints, range limits, and in-list checks with a fluent API.
- Automated Quality Pipeline: Establish continuous monitoring of data streams with historical score tracking to see quality trends over time.
- Construction-specific Regex Library: Pre-configured patterns for Revit IDs, IFC GUIDs, ISO dates, and Russian/English level naming conventions.
- Multi-sheet Excel Reporting: Generates detailed workbooks containing summary scores, issue logs, and missing value heatmaps.
- Cross-field Logic Support: Define complex rules, such as ensuring Gross Volume is always greater than or equal to Net Volume.
SKILL.md
Loading
Related Openclaw Skills
Data Profiler for Construction
A comprehensive Python-based profiling engine designed to assess the quality, patterns, and distributions of construction industry datasets.
Data Model Designer
A specialized tool for designing construction project data models, generating SQL schemas, and creating entity-relationship diagrams.
Data Lineage Tracker
A technical tool for tracking data origin, transformations, and logical flow across construction management systems.
Data Evolution Analysis
A specialized technical skill for analyzing data evolution patterns and assessing the digital maturity of construction organizations based on DDC methodology.
Data Silo Detection
A specialized diagnostic tool that identifies, maps, and prioritizes the remediation of disconnected data repositories in construction organizations.
Data Source Audit for Construction
A comprehensive auditing tool to map, analyze, and optimize data flows and systems within construction organizations.
METADATA
Featured*
