
docx-construction
Word document generation for construction: contracts, proposals, reports, specifications, transmittals. Template-based with dynamic content insertion.
- Installs
- 117
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction --skill docx-construction- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads docx-construction automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Word Document Generation for Construction
Overview
Create professional Word documents for construction workflows using python-docx. Generate contracts, proposals, reports, and specifications from templates with dynamic data.
Construction Use Cases
1. Contract Generation
Generate construction contracts from templates with project-specific data.
from docx import Document
from docx.shared import Inches, Pt
from docx.enum.text import WD_ALIGN_PARAGRAPH
from datetime import datetime
def generate_subcontract(template_path: str, contract_data: dict, output_path: str) -> str:
"""Generate subcontract from template."""
doc = Document(template_path)
# Replace placeholders
replacements = {
'{{PROJECT_NAME}}': contract_data['project_name'],
'{{CONTRACT_NUMBER}}': contract_data['contract_number'],
'{{SUBCONTRACTOR_NAME}}': contract_data['subcontractor'],
'{{SCOPE_OF_WORK}}': contract_data['scope'],
'{{CONTRACT_VALUE}}': f"${contract_data['value']:,.2f}",
'{{START_DATE}}': contract_data['start_date'],
'{{END_DATE}}': contract_data['end_date'],
'{{RETENTION_PERCENT}}': f"{contract_data['retention']}%",
}
for paragraph in doc.paragraphs:
for key, value in replacements.items():
if key in paragraph.text:
paragraph.text = paragraph.text.replace(key, value)
# Also check tables
for table in doc.tables:
for row in table.rows:
for cell in row.cells:
for key, value in replacements.items():
if key in cell.text:
cell.text = cell.text.replace(key, value)
doc.save(output_path)
return output_path
2. Proposal Document
Create professional project proposals.
def create_proposal(project_info: dict, scope_items: list, pricing: dict) -> Document:
"""Create construction proposal document."""
doc = Document()
# Title
title = doc.add_heading('Project Proposal', 0)
title.alignment = WD_ALIGN_PARAGRAPH.CENTER
# Project Info
doc.add_heading('Project Information', level=1)
doc.add_paragraph(f"Project: {project_info['name']}")
doc.add_paragraph(f"Location: {project_info['location']}")
doc.add_paragraph(f"Client: {project_info['client']}")
doc.add_paragraph(f"Date: {datetime.now().strftime('%B %d, %Y')}")
# Scope of Work
doc.add_heading('Scope of Work', level=1)
for item in scope_items:
doc.add_paragraph(item, style='List Bullet')
# Pricing Table
doc.add_heading('Pricing Summary', level=1)
table = doc.add_table(rows=1, cols=3)
table.style = 'Table Grid'
# Headers
headers = table.rows[0].cells
headers[0].text = 'Description'
headers[1].text = 'Quantity'
headers[2].text = 'Amount'
# Add line items
for item in pricing['line_items']:
row = table.add_row().cells
row[0].text = item['description']
row[1].text = str(item['quantity'])
row[2].text = f"${item['amount']:,.2f}"
# Total row
total_row = table.add_row().cells
total_row[0].text = 'TOTAL'
total_row[2].text = f"${pricing['total']:,.2f}"
# Terms
doc.add_heading('Terms & Conditions', level=1)
doc.add_paragraph(f"Payment Terms: {pricing.get('payment_terms', 'Net 30')}")
doc.add_paragraph(f"Validity: {pricing.get('validity', '30 days')}")
return doc
3. Daily Report Generation
Generate daily construction reports.
def generate_daily_report(report_data: dict, output_path: str) -> str:
"""Generate daily construction report."""
doc = Document()
# Header
doc.add_heading(f"Daily Construction Report", 0)
doc.add_paragraph(f"Project: {report_data['project_name']}")
doc.add_paragraph(f"Date: {report_data['date']}")
doc.add_paragraph(f"Report #: {report_data['report_number']}")
doc.add_paragraph(f"Weather: {report_data['weather']}")
# Workforce
doc.add_heading('Workforce On-Site', level=1)
workforce_table = doc.add_table(rows=1, cols=3)
workforce_table.style = 'Table Grid'
headers = workforce_table.rows[0].cells
headers[0].text = 'Trade'
headers[1].text = 'Company'
headers[2].text = 'Headcount'
for crew in report_data['workforce']:
row = workforce_table.add_row().cells
row[0].text = crew['trade']
row[1].text = crew['company']
row[2].text = str(crew['count'])
# Work Completed
doc.add_heading('Work Completed Today', level=1)
for item in report_data['work_completed']:
doc.add_paragraph(f"• {item}")
# Issues/Delays
if report_data.get('issues'):
doc.add_heading('Issues & Delays', level=1)
for issue in report_data['issues']:
p = doc.add_paragraph()
p.add_run(f"{issue['type']}: ").bold = True
p.add_run(issue['description'])
# Safety
doc.add_heading('Safety', level=1)
doc.add_paragraph(f"Incidents: {report_data.get('incidents', 'None')}")
doc.add_paragraph(f"Near Misses: {report_data.get('near_misses', 'None')}")
# Photos placeholder
if report_data.get('photos'):
doc.add_heading('Site Photos', level=1)
for photo in report_data['photos']:
doc.add_picture(photo['path'], width=Inches(5))
doc.add_paragraph(photo.get('caption', ''), style='Caption')
doc.save(output_path)
return output_path
4. Transmittal Letter
Generate transmittal documents for submittals.
def create_transmittal(transmittal_data: dict) -> Document:
"""Create transmittal letter for submittals."""
doc = Document()
# Header info
doc.add_paragraph(f"Date: {transmittal_data['date']}")
doc.add_paragraph(f"Transmittal No: {transmittal_data['number']}")
doc.add_paragraph()
# To/From
doc.add_paragraph(f"To: {transmittal_data['to']}")
doc.add_paragraph(f"From: {transmittal_data['from']}")
doc.add_paragraph(f"Project: {transmittal_data['project']}")
doc.add_paragraph(f"Subject: {transmittal_data['subject']}")
doc.add_paragraph()
# Items transmitted
doc.add_paragraph("We are transmitting the following:")
table = doc.add_table(rows=1, cols=4)
table.style = 'Table Grid'
headers = table.rows[0].cells
headers[0].text = 'No.'
headers[1].text = 'Description'
headers[2].text = 'Copies'
headers[3].text = 'Action'
for i, item in enumerate(transmittal_data['items'], 1):
row = table.add_row().cells
row[0].text = str(i)
row[1].text = item['description']
row[2].text = str(item.get('copies', 1))
row[3].text = item.get('action', 'For Review')
doc.add_paragraph()
# Remarks
if transmittal_data.get('remarks'):
doc.add_paragraph(f"Remarks: {transmittal_data['remarks']}")
return doc
5. Specification Section Writer
Generate specification sections.
def generate_spec_section(spec_data: dict) -> Document:
"""Generate CSI-formatted specification section."""
doc = Document()
# Section header
doc.add_heading(f"SECTION {spec_data['number']}", 0)
doc.add_heading(spec_data['title'].upper(), level=1)
# Part 1 - General
doc.add_heading('PART 1 - GENERAL', level=1)
doc.add_heading('1.1 SUMMARY', level=2)
doc.add_paragraph(f"A. Section includes: {spec_data['summary']}")
doc.add_heading('1.2 RELATED SECTIONS', level=2)
for section in spec_data.get('related_sections', []):
doc.add_paragraph(f"A. Section {section['number']}: {section['title']}")
doc.add_heading('1.3 SUBMITTALS', level=2)
for submittal in spec_data.get('submittals', []):
doc.add_paragraph(f"A. {submittal}")
# Part 2 - Products
doc.add_heading('PART 2 - PRODUCTS', level=1)
doc.add_heading('2.1 MANUFACTURERS', level=2)
for mfr in spec_data.get('manufacturers', []):
doc.add_paragraph(f"A. {mfr}")
doc.add_heading('2.2 MATERIALS', level=2)
for material in spec_data.get('materials', []):
p = doc.add_paragraph(f"A. {material['name']}")
for prop in material.get('properties', []):
doc.add_paragraph(f" 1. {prop}", style='List Number')
# Part 3 - Execution
doc.add_heading('PART 3 - EXECUTION', level=1)
doc.add_heading('3.1 INSTALLATION', level=2)
for step in spec_data.get('installation', []):
doc.add_paragraph(f"A. {step}")
doc.add_heading('3.2 QUALITY CONTROL', level=2)
for qc in spec_data.get('quality_control', []):
doc.add_paragraph(f"A. {qc}")
return doc
Integration with DDC Pipeline
# Example: Generate contract from estimate data
import pandas as pd
# Load estimate
estimate = pd.read_excel("project_estimate.xlsx")
# Prepare contract data
contract_data = {
'project_name': 'Downtown Office Tower',
'contract_number': 'SC-2026-001',
'subcontractor': 'ABC Electrical Inc.',
'scope': 'Complete electrical installation per Division 26',
'value': estimate[estimate['division'] == '26']['total'].sum(),
'start_date': '2026-03-01',
'end_date': '2026-09-30',
'retention': 10
}
# Generate contract
generate_subcontract('templates/subcontract.docx', contract_data, 'contracts/SC-2026-001.docx')
Dependencies
pip install python-docx
Resources
- python-docx: https://python-docx.readthedocs.io/
- ConsensusDocs Templates: https://www.consensusdocs.org/
- AIA Contract Documents: https://www.aiacontracts.org/
FAQ
What does the docx-construction skill do?
Word document generation for construction: contracts, proposals, reports, specifications, transmittals. Template-based with dynamic content insertion.
How do I install docx-construction?
Run npx skills add https://github.com/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction --skill docx-construction in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/docx-construction/ (personal) or .claude/skills/docx-construction/ (project).
Which AI agents can use docx-construction?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is docx-construction safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains docx-construction?
It is published by datadrivenconstruction in datadrivenconstruction/ddc_skills_for_ai_agents_in_construction. It has 117 recorded installs.
More from datadrivenconstruction/ddc_skills_for_ai_agents_in_construction
warranty-tracker
datadrivenconstruction/ddc_skills_for_ai_agents_in_construction
Track and manage construction warranties. Monitor expiration dates, claims, and manufacturer documentation.
cad-to-data
datadrivenconstruction/ddc_skills_for_ai_agents_in_construction
Convert CAD/BIM files to structured data. Extract element data from Revit, IFC, DWG, DGN files.
dwg-to-excel
datadrivenconstruction/ddc_skills_for_ai_agents_in_construction
Convert AutoCAD DWG files (1983-2026) to Excel databases using DwgExporter CLI. Extract layers, blocks, attributes, and geometry data without Autodesk licenses.
drawing-analyzer
datadrivenconstruction/ddc_skills_for_ai_agents_in_construction
Analyze construction drawings to extract dimensions, annotations, symbols, and metadata. Support quantity takeoff and design review automation.
permit-tracking-automation
datadrivenconstruction/ddc_skills_for_ai_agents_in_construction
Automate construction permit tracking and management. Monitor application status, track renewal deadlines, manage document requirements, and integrate with municipal systems.
cost-estimation-resource
datadrivenconstruction/ddc_skills_for_ai_agents_in_construction
Calculate construction costs using resource-based method. Estimate project costs from work items, physical resource norms, and current prices.
Popular docs & writing skills
grill-with-docs
mattpocock/skills
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
lark-markdown
open.feishu.cn
飞书 Markdown:查看、创建、上传、编辑和比较飞书中的原生 Markdown 文件。当用户要操作飞书 Markdown 文件,或比较其远端版本及本地草稿时使用。纯本地 Markdown 文件操作不触发本 skill。不负责将 Markdown 导入为飞书在线文档,也不负责文件搜索、权限、评论、移动、删除等云空间管理操作。
writing-beats
mattpocock/skills
Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.
writing-shape
mattpocock/skills
Writing, exploit: shape raw material into an article, paragraph by paragraph.
writing-fragments
mattpocock/skills
Writing, explore: mine raw fragments, no structure yet.
writing-for-agents
mattpocock/skills
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.