Agent skill · data analytics · datadrivenconstruction
etl-pipeline
Build automated ETL (Extract-Transform-Load) pipelines for construction data. Process PDFs, Excel, BIM exports. Generate reports, dashboards, and integrate with other systems. Orchestrate with Airflow or n8n.
Why this skill is useful
Provides specific Python scripts for building ETL pipelines that automate data extraction, transformation, and loading from various sources.
What it needs
Requires python3 installed locally. About 6k tokens when loaded. Last updated 2026-02-14. 265 stars on the source repository.
What this skill does
ETL Pipeline for Construction Data Overview Based on DDC methodology (Chapter 4.2), this skill enables building automated data pipelines that extract information from various sources, transform it into useful formats, and load it into target systems or generate reports. Book Reference: "ETL и автоматизация процессов" / "ETL and Process Automation" "ETL: переход от ручного управления к автоматизации позволяет компаниям обрабатывать данные без постоянного человеческого вмешательства." — DDC Book, Chapter 4.2 ETL Components Quick Start Extract: Data Sources From Multiple Excel Files From PDF Documents From API From Database Transform: Data Processing Data Cleaning Data Validation Data Aggregation Data Enrichment Load: Output Generation Generate Excel Report Generate PDF Report Load to Database Complete ETL Pipeline Scheduling with Airflow Quick Reference Stage Task Tool/Method ------- ------ ------------- Extract Read Excel pd.readexcel() Extract Read CSV pd.readcsv() Extract Read PDF pdfplumber Extract Read API requests.get() Transform Clean df.dropna(), df.str.strip() Transform Validate Custom validation functions Transform Calculate df['new'] = df['a'] df['b'] Transform Aggregate df.groupby().agg() Load Excel df.toexcel() Load PDF reportlab Load Database df.tosql() Load API requests.post() Resources Book: "Data-Driven Construction" by Artem Boiko, Chapter 4.2 Website: https://datadrivenconstruction.io Airflow: https://airflow.apache.org n8n: https://n8n.io Next Steps See bim-validation-pipeline for BIM data validation See pdf-report-generator for advanced PDF generation See workflow-automation for n8n integration
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills datadrivenconstruction/etl-pipeline