Agent skill · operations · datadrivenconstruction
site-logistics-optimization
Optimize construction site logistics including material delivery scheduling, crane positioning, storage area allocation, and traffic flow using operations research and simulation.
Why this skill is useful
Provides domain-specific algorithms for optimizing construction logistics that the AI wouldn't reliably generate on its own.
What it needs
Requires python3 installed locally. About 7k tokens when loaded. Last updated 2026-02-14. 265 stars on the source repository.
What this skill does
Site Logistics Optimization Overview This skill implements optimization algorithms for construction site logistics. Minimize delays, reduce costs, and improve safety through data-driven planning of deliveries, equipment placement, and material storage. Optimization Areas: Material delivery scheduling Crane and equipment positioning Storage area allocation Site traffic flow Workforce routing Just-in-time delivery Quick Start Comprehensive Logistics Optimization Site Layout Model Delivery Scheduling Optimizer Storage Area Optimization Crane Positioning Optimizer `python from scipy.optimize import minimize import numpy as np class CranePositionOptimizer: """Optimize crane placement on site""" def init(self, site: SiteLogisticsModel): self.site = site def optimizesinglecrane(self, crane: Equipment, priorityzones: List[str], constraints: Dict = None) -> Tuple[float, float]: """Find optimal position for a single crane""" # Get zone positions zonepositions = [ self.site.zones[zid].position for zid in priorityzones if zid in self.site.zones ] if not zonepositions: return crane.position # Objective: minimize weighted distance to priority zones def objective(pos): totaldist = 0 for i, zonepos in enumerate(zonepositions): dist = np.sqrt((pos[0] - zonepos[0])2 + (pos[1] - zonepos[1])2) weight = len(zonepositions) - i # Higher weight for earlier zones totaldist += dist weight return totaldist # Initial position x0 = np.array([crane.position[0], crane.position[1]]) # Bounds (site boundaries) bounds = constraints.get('bounds', [(0, 100), (0, 100)]) if constraints else [(0, 100), (0, 100)] result = minimize(objective, x0, method='L-BFGS-B', bounds=bounds) return tuple(result.x) def optimizemultiplecranes(self, cranes: List[Equipment], zones: List[str]) -> Dict[str, Tuple[float, float]]: """Optimize positions for multiple cranes to maximize coverage""" positions = {} # Assignment problem: which crane covers which zones zonelist = list(zones) cranelist = list(cranes) # Create cost ma …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills datadrivenconstruction/site-logistics-optimization