Skip to main content
skill CX Codex

subcontractor-prequalification — Claude Code skill

subcontractor-prequalification evaluates subcontractors by safety, financials and experience, filters qualified ones and exports a register.

MIT 123 installs ★ 434 updated 2026-10-19

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill subcontractor-prequalification -a claude-code
Open on GitHub

What subcontractor-prequalification does

The skill accepts an application with company name, trade, revenue, bonding capacity and EMR (Experience Modification Rate), assigns it an ID and pending status. Six criteria (Safety Record, Financial Stability, Experience, References, Capacity, Insurance/Bonding) are then scored: each has a weight and a minimum threshold; the total must reach 60 for qualified or 50 for conditionally_qualified. If any criterion falls below its minimum, the application receives not_qualified.

The SubcontractorPrequalification class stores applications in a dictionary, filters by trade and exports the register to Excel via pandas. Requires Python 3; pandas must be installed separately as the skill imports it directly.

What it helps with

  • filter out subcontractors with low EMR or insufficient bonding
  • list qualified electricians or plumbers for a project
  • export an application register to Excel with scores and statuses
  • verify whether a company passed all safety and financial criteria

Example prompts for the agent

  • Create a prequalification register for the Office Tower project and add an application from ABC Electric
  • Score application PQ-001 across six criteria and show its status
  • Export the qualified subcontractor register to qualified_subs.xlsx

How to install subcontractor-prequalification

1Skills CLI (Vercel)

npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill subcontractor-prequalification -a claude-code

2Manually: put the files in place

~/.claude/skills/subcontractor-prequalification/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/subcontractor-prequalification/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about subcontractor-prequalification

How to install subcontractor-prequalification in Claude Code?

Run npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill subcontractor-prequalification -a claude-code, then open ~/.claude/skills/subcontractor-prequalification/SKILL.md.

What does subcontractor-prequalification do?

Accepts subcontractor applications, evaluates them by safety, financials and experience, assigns a status (qualified, conditionally qualified, not qualified) and exports the register to Excel.

What does the skill require?

Python 3 and the pandas library — the skill imports it to export to Excel.

Source text

SKILL.md · MIT
---
name: "subcontractor-prequalification"
description: "Prequalify subcontractors based on safety, financial, and performance criteria."
homepage: "https://datadrivenconstruction.io"
metadata: {"openclaw": {"emoji": "🛒", "os": ["darwin", "linux", "win32"], "homepage": "https://datadrivenconstruction.io", "requires": {"bins": ["python3"]}}}
---
# Subcontractor Prequalification

## Technical Implementation

```python
import pandas as pd
from datetime import date
from typing import Dict, Any, List
from dataclasses import dataclass, field
from enum import Enum


class QualificationStatus(Enum):
    PENDING = "pending"
    QUALIFIED = "qualified"
    CONDITIONALLY_QUALIFIED = "conditionally_qualified"
    NOT_QUALIFIED = "not_qualified"


@dataclass
class PrequalificationCriteria:
    name: str
    weight: float
    min_score: int
    max_score: int = 10


@dataclass
class SubcontractorApplication:
    app_id: str
    company_name: str
    trade: str
    contact_email: str
    years_in_business: int
    annual_revenue: float
    bonding_capacity: float
    emr_rate: float  # Experience Modification Rate
    status: QualificationStatus
    scores: Dict[str, int] = field(default_factory=dict)
    documents_received: List[str] = field(default_factory=list)
    notes: str = ""

    @property
    def total_score(self) -> float:
        return sum(self.scores.values())


class SubcontractorPrequalification:
    def __init__(self, project_name: str):
        self.project_name = project_name
        self.applications: Dict[str, SubcontractorApplication] = {}
        self.criteria = self._default_criteria()
        self._counter = 0

    def _default_criteria(self) -> List[PrequalificationCriteria]:
        return [
            PrequalificationCriteria("Safety Record", 0.25, 6),
            PrequalificationCriteria("Financial Stability", 0.20, 5),
            PrequalificationCriteria("Experience", 0.20, 6),
            PrequalificationCriteria("References", 0.15, 5),
            PrequalificationCriteria("Capacity", 0.10, 5),
            PrequalificationCriteria("Insurance/Bonding", 0.10, 7)
        ]

    def add_application(self, company_name: str, trade: str, contact_email: str,
                       years_in_business: int, annual_revenue: float,
                       bonding_capacity: float, emr_rate: float) -> SubcontractorApplication:
        self._counter += 1
        app_id = f"PQ-{self._counter:03d}"

        app = SubcontractorApplication(
            app_id=app_id,
            company_name=company_name,
            trade=trade,
            contact_email=contact_email,
            years_in_business=years_in_business,
            annual_revenue=annual_revenue,
            bonding_capacity=bonding_capacity,
            emr_rate=emr_rate,
            status=QualificationStatus.PENDING
        )
        self.applications[app_id] = app
        return app

    def score_application(self, app_id: str, scores: Dict[str, int]):
        if app_id not in self.applications:
            return
        app = self.applications[app_id]
        app.scores = scores
        self._evaluate_qualification(app)

    def _evaluate_qualification(self, app: SubcontractorApplication):
        passed = True
        for criteria in self.criteria:
            score = app.scores.get(criteria.name, 0)
            if score < criteria.min_score:
                passed = False
                break

        if passed and app.total_score >= 60:
            app.status = QualificationStatus.QUALIFIED
        elif app.total_score >= 50:
            app.status = QualificationStatus.CONDITIONALLY_QUALIFIED
        else:
            app.status = QualificationStatus.NOT_QUALIFIED

    def get_qualified(self, trade: str = None) -> List[SubcontractorApplication]:
        qualified = [a for a in self.applications.values()
                    if a.status in [QualificationStatus.QUALIFIED,
                                   QualificationStatus.CONDITIONALLY_QUALIFIED]]
        if trade:
            qualified = [a for a in qualified if a.trade.lower() == trade.lower()]
        return qualified

    def export_register(self, output_path: str):
        data = [{
            'ID': a.app_id,
            'Company': a.company_name,
            'Trade': a.trade,
            'Years': a.years_in_business,
            'Revenue': a.annual_revenue,
            'EMR': a.emr_rate,
            'Status': a.status.value,
            'Score': a.total_score
        } for a in self.applications.values()]
        pd.DataFrame(data).to_excel(output_path, index=False)
```

## Quick Start

```python
prequal = SubcontractorPrequalification("Office Tower")

app = prequal.add_application("ABC Electric", "Electrical", "[email protected]",
                              years_in_business=15, annual_revenue=10000000,
                              bonding_capacity=5000000, emr_rate=0.85)

prequal.score_application(app.app_id, {
    "Safety Record": 8, "Financial Stability": 7, "Experience": 8,
    "References": 7, "Capacity": 8, "Insurance/Bonding": 9
})

qualified = prequal.get_qualified("Electrical")
```

## Resources
- **DDC Book**: Chapter 3.4 - Procurement

© datadrivenconstruction · MIT · datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction

Similar skills

All skills for Automation and no-code: n8n, Zapier, Make →

From the same set156

The whole set →
carbon-calculator carbon-calculator calculates embodied carbon for construction materials using emission factors. Use it to compare material options and prepare emissions data for reporting. CX Codex +1 123installs look-ahead-scheduler look-ahead-scheduler is a Claude Code skill that turns master schedules into rolling 2-, 3-, or 6-week work plans, analyzes constraints, and assigns crews. CX Codex +1 123installs schedule-forecaster schedule-forecaster is a Claude Code skill that predicts construction project completion dates and delay risk from progress and past project data. It activates for schedule forecasting requests. CX Codex +1 123installs rag-construction rag-construction builds construction-focused RAG systems for project documents and reports. Helps configure semantic retrieval over technical paperwork in Python. CX Codex +1 123installs unit-price-database-manager unit-price-database-manager keeps a construction unit price database current: price updates, vendor quotes, location factors, price history. Useful when an estimate has to match what suppliers actually charge. CX Codex +1 122installs co2-carbon-footprint co2-carbon-footprint calculates embodied carbon and CO2 emissions from BIM model quantities. It helps evaluate building materials and components across EN 15978 life cycle stages. CX Codex +1 122installs standards-compliance-checker standards-compliance-checker validates construction data against ISO 19650, IFC, COBie, UniFormat, and MasterFormat. Catches errors in filenames, status codes, GUIDs, and required fields. CX Codex +1 122installs digital-maturity-assessment digital-maturity-assessment assesses digital transformation readiness across data culture, technology stack, and process maturity. Scores gaps and plans next steps. CX Codex +1 121installs

Project sponsors

Companies that keep this analytics open