Agent skill · research science · datadrivenconstruction
few-shot-examples
Curated few-shot examples for construction AI tasks: classification, extraction, analysis. Domain-specific examples for improved LLM performance.
Why this skill is useful
Provides domain-specific few-shot examples for construction tasks that improve LLM performance in classification and extraction.
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
Few-Shot Examples for Construction AI Overview Curated few-shot examples for construction industry AI tasks. These examples improve LLM performance by providing domain-specific context for classification, extraction, and analysis tasks. Few-Shot Framework Example Manager CSI Classification Examples RFI Classification Examples Cost Analysis Examples Schedule Analysis Examples BIM Data Examples `python BIMEXTRACTIONEXAMPLES = ExampleSet( name="bimextraction", description="Examples for BIM data extraction and interpretation", tasktype="extraction", examples=[ FewShotExample( input=json.dumps({ "elementtype": "IfcWall", "properties": { "Name": "Interior Partition", "IsExternal": False, "FireRating": "1 Hour", "PsetWallCommon.Width": 0.165, "BaseQuantities.GrossArea": 45.5, "BaseQuantities.NetArea": 42.3 } }), output=json.dumps({ "classification": "Interior wall", "firerated": True, "firerating": "1 Hour", "thicknessmm": 165, "thicknessin": 6.5, "grossaream2": 45.5, "grossareasf": 490, "netareasf": 455, "openingdeductionpct": 7.0 }), explanation="Extract and convert BIM properties to construction quantities", tags=["wall", "quantities", "ifc"], difficulty="medium"
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills datadrivenconstruction/few-shot-examples