Analyze labor productivity by trade, activity, and location. Track efficiency and identify improvement opportunities.
npx skills add https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill labor-productivity-analyzer
import pandas as pd
from datetime import date
from typing import Dict, Any, List
from dataclasses import dataclass, field
from enum import Enum
class ProductivityStatus(Enum):
EXCEEDING = "exceeding"
ON_TARGET = "on_target"
BELOW_TARGET = "below_target"
CRITICAL = "critical"
@dataclass
class ProductivityEntry:
entry_id: str
date: date
trade: str
activity_code: str
activity_description: str
location: str
crew_size: int
hours_worked: float
quantity_installed: float
unit: str
target_productivity: float # units per hour
@property
def actual_productivity(self) -> float:
if self.hours_worked == 0:
return 0
return self.quantity_installed / self.hours_worked
@property
def productivity_factor(self) -> float:
if self.target_productivity == 0:
return 0
return self.actual_productivity / self.target_productivity
@property
def status(self) -> ProductivityStatus:
pf = self.productivity_factor
if pf >= 1.1:
return ProductivityStatus.EXCEEDING
elif pf >= 0.9:
return ProductivityStatus.ON_TARGET
elif pf >= 0.7:
return ProductivityStatus.BELOW_TARGET
return ProductivityStatus.CRITICAL
class LaborProductivityAnalyzer:
def __init__(self, project_name: str):
self.project_name = project_name
self.entries: List[ProductivityEntry] = []
self.targets: Dict[str, float] = {} # activity_code: target_productivity
self._counter = 0
def set_target(self, activity_code: str, target_productivity: float):
self.targets[activity_code] = target_productivity
def add_entry(self, entry_date: date, trade: str, activity_code: str,
activity_description: str, location: str, crew_size: int,
hours_worked: float, quantity_installed: float,
unit: str) -> ProductivityEntry:
self._counter += 1
entry_id = f"PROD-{self._counter:05d}"
target = self.targets.get(activity_code, 1.0)
entry = ProductivityEntry(
entry_id=entry_id,
date=entry_date,
trade=trade,
activity_code=activity_code,
activity_description=activity_description,
location=location,
crew_size=crew_size,
hours_worked=hours_worked,
quantity_installed=quantity_installed,
unit=unit,
target_productivity=target
)
self.entries.append(entry)
return entry
def get_productivity_by_trade(self) -> Dict[str, Dict[str, Any]]:
by_trade = {}
for entry in self.entries:
if entry.trade not in by_trade:
by_trade[entry.trade] = {'hours': 0, 'quantity': 0, 'entries': 0}
by_trade[entry.trade]['hours'] += entry.hours_worked
by_trade[entry.trade]['quantity'] += entry.quantity_installed
by_trade[entry.trade]['entries'] += 1
for trade in by_trade:
hours = by_trade[trade]['hours']
qty = by_trade[trade]['quantity']
by_trade[trade]['avg_productivity'] = qty / hours if hours > 0 else 0
return by_trade
def get_productivity_by_activity(self) -> Dict[str, Dict[str, Any]]:
by_activity = {}
for entry in self.entries:
code = entry.activity_code
if code not in by_activity:
by_activity[code] = {
'description': entry.activity_description,
'hours': 0, 'quantity': 0, 'target': entry.target_productivity
}
by_activity[code]['hours'] += entry.hours_worked
by_activity[code]['quantity'] += entry.quantity_installed
for code in by_activity:
hours = by_activity[code]['hours']
qty = by_activity[code]['quantity']
by_activity[code]['actual'] = qty / hours if hours > 0 else 0
by_activity[code]['factor'] = (
by_activity[code]['actual'] / by_activity[code]['target']
if by_activity[code]['target'] > 0 else 0
)
return by_activity
def get_low_performers(self) -> List[ProductivityEntry]:
return [e for e in self.entries
if e.status in [ProductivityStatus.BELOW_TARGET, ProductivityStatus.CRITICAL]]
def get_summary(self) -> Dict[str, Any]:
if not self.entries:
return {'total_entries': 0}
total_hours = sum(e.hours_worked for e in self.entries)
factors = [e.productivity_factor for e in self.entries]
avg_factor = sum(factors) / len(factors)
return {
'total_entries': len(self.entries),
'total_hours': total_hours,
'average_productivity_factor': round(avg_factor, 2),
'exceeding': sum(1 for e in self.entries if e.status == ProductivityStatus.EXCEEDING),
'on_target': sum(1 for e in self.entries if e.status == ProductivityStatus.ON_TARGET),
'below_target': sum(1 for e in self.entries if e.status == ProductivityStatus.BELOW_TARGET),
'critical': sum(1 for e in self.entries if e.status == ProductivityStatus.CRITICAL)
}
def export_report(self, output_path: str):
data = [{
'Date': e.date,
'Trade': e.trade,
'Activity': e.activity_code,
'Location': e.location,
'Crew': e.crew_size,
'Hours': e.hours_worked,
'Quantity': e.quantity_installed,
'Unit': e.unit,
'Target': e.target_productivity,
'Actual': round(e.actual_productivity, 2),
'Factor': round(e.productivity_factor, 2),
'Status': e.status.value
} for e in self.entries]
pd.DataFrame(data).to_excel(output_path, index=False)
analyzer = LaborProductivityAnalyzer("Office Tower")
# Set targets
analyzer.set_target("CONC-001", 2.5) # m3 per hour
# Add entry
entry = analyzer.add_entry(
entry_date=date.today(),
trade="Concrete",
activity_code="CONC-001",
activity_description="Pour concrete slab",
location="Level 3",
crew_size=8,
hours_worked=80,
quantity_installed=180,
unit="m3"
)
print(f"Productivity factor: {entry.productivity_factor:.2f}")
print(f"Status: {entry.status.value}")
Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
Take datadrivenconstruction/labor-productivity-analyzer from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.