Agent skill · marketing growth · datadrivenconstruction
contractor-matching-ai
AI-powered contractor matching and selection for construction projects. Analyze contractor capabilities, past performance, certifications, and project requirements to recommend optimal matches.
Why this skill is useful
Provides a domain-specific algorithm for contractor matching based on multiple criteria that the AI wouldn't 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
AI Contractor Matching Overview This skill implements AI-powered contractor matching for construction projects. Analyze project requirements against contractor capabilities, track historical performance, and generate recommendations based on multiple criteria. Matching Criteria: Technical capabilities & expertise Past performance scores Certifications & licenses Geographic availability Capacity & current workload Pricing competitiveness Safety records Quick Start Comprehensive Matching System Contractor Profile Management AI Matching Engine Bid Analysis and Prediction `python from sklearn.ensemble import RandomForestRegressor from sklearn.modelselection import traintestsplit import numpy as np class BidPredictor: """Predict contractor bid prices""" def init(self): self.model = RandomForestRegressor(nestimators=100, randomstate=42) self.istrained = False def train(self, historicalbids: pd.DataFrame): """Train bid prediction model Expected columns: contractorsize, worktype, region, projectvalue contractorperformance, contractorworkload winningbid, contractorbid """ features = ['projectvalue', 'contractorperformance', 'contractorworkload', 'durationmonths'] # One-hot encode categorical df = pd.getdummies(historicalbids, columns=['contractorsize', 'worktype', 'region']) # Features that exist Xcols = [c for c in df.columns if c not in ['winningbid', 'contractorbid']] X = df[Xcols] y = df['contractorbid'] self.featurecolumns = Xcols self.model.fit(X, y) self.istrained = True def predictbid(self, contractor: ContractorProfile, project: ProjectRequirements) -> Dict: """Predict expected bid from contractor""" if not self.istrained: # Simple estimation if not trained base = project.estimatedvalue variance = np.random.uniform(-0.1, 0.15) return { 'predictedbid': base (1 + variance), 'confidence': 'low', 'variancerange': (-15, 20) } # Build feature vector features = { 'projectvalue': project.estimatedvalue, 'contractorperformance': contractor.calculateperformancescore(), 'contr …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills datadrivenconstruction/contractor-matching-ai