Agent skill · data analytics · datadrivenconstruction
llm-data-automation
Automate construction data processing using LLM (ChatGPT, Claude, LLaMA). Generate Python/Pandas scripts, extract data from documents, and create automated pipelines without deep programming knowledge.
Why this skill is useful
Generates specific Python/Pandas scripts for construction data processing that the AI wouldn't reliably create on its own.
What it needs
Requires python3 installed locally. About 4k tokens when loaded. Last updated 2026-02-14. 265 stars on the source repository.
What this skill does
LLM Data Automation for Construction Overview Based on DDC methodology (Chapter 2.3), this skill enables automation of construction data processing using Large Language Models (LLM). Instead of manually coding data transformations, you describe what you need in natural language, and the LLM generates the necessary Python/Pandas code. Book Reference: "Pandas DataFrame и LLM ChatGPT" / "Pandas DataFrame and LLM ChatGPT" "LLM-модели, такие как ChatGPT и LLaMA, позволяют специалистам без глубоких знаний программирования внести свой вклад в автоматизацию и улучшение бизнес-процессов компании." — DDC Book, Chapter 2.3 Quick Start Option 1: Use ChatGPT/Claude Online Simply describe your data processing task in natural language: Option 2: Run Local LLM (Ollama) Option 3: Use LM Studio (GUI) 1. Download from lmstudio.ai 2. Install and select a model (e.g., Mistral, LLaMA) 3. Start chatting with your local AI Core Concepts DataFrame as Universal Format LLM Prompts for Construction Tasks Data Import: Data Filtering: Data Aggregation: Report Generation: Common Use Cases 1. Extract Data from PDF Documents 2. Process BIM Element Data 3. Cost Estimation Pipeline 4. Schedule Data Processing Local LLM Setup (No Internet Required) Using Ollama Using LlamaIndex for Company Documents IDE Recommendations IDE Best For Features ----- ---------- ---------- Jupyter Notebook Learning, experiments Interactive cells, visualizations Google Colab Free GPU, quick start Cloud-based, pre-installed libs VS Code Professional development Extensions, GitHub Copilot PyCharm Large projects Advanced debugging, refactoring Quick Setup with Jupyter Best Practices 1. Start Simple: Begin with clear, specific prompts 2. Iterate: Refine prompts based on results 3. Validate: Always check generated code before running 4. Document: Save working prompts for reuse 5. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills datadrivenconstruction/llm-data-automation