Ai In Construction | AI Final Year Project Report

Complete Technical Paper Content — Ai In Construction

1. Executive Abstract, Problem Formulation & Background

👷‍♂️ ConstructionAI – AI Innovation in Construction 🚀 Welcome! I’m Mohamed Ashour, a Chartered Quantity Surveyor deeply passionate about applying Data Analytics and Artificial Intelligence to the construction industry. Here, you’ll find a collection of cutting-edge AI initiatives, each aiming to redefine how we approach construction and project management. My work explores the powerful synergy between construction expertise and machine learning —turning concepts into scalable, production-ready solutions. 🌐 Let’s Connect! Website : www.apcmasterypath.co.uk APC Mastery Path Blog : All Blog Posts LinkedIn : Personal LinkedIn | APC Mastery Path LinkedIn YouTube Channel : APC Mastery Path on YouTube 📌 My Focus Areas Data Analytics for Construction : Transforming raw data into actionable insights. Machine Learning & AI Integration : Developing algorithms tailored for construction applications. Optimization & Scalability : Ensuring AI solutions are not just innovative but production-ready. Open-Source Large Language Models : Exploring and expanding the boundaries of LLMs in construction. 🛠️ Featured Projects 1. 📈 RAG Chatbot Development Leveraging Retrieval-Augmented Generation (RAG) techniques to create intelligent, contextually aware chatbots. Key Focus : Enhancing user interaction in construction management software. 2. 🧠 Finetuning Large Language Models (LLMs) Customizing open-source LLMs to handle construction-specific language and queries. Scalability : Deploying these models on a large scale for robust field applicability. 3. 🌐 Crawl4AI - Web Scraping Framework A comprehensive web scraping tool built with Streamlit to gather essential construction data. Showcased in : YouTube Video (explaining the code, components, and deployment details) 4. 🎙️ Podcast Creation with AI Combining NLP and audio processing to automate podcast production on industry topics. Outcome : Increasing outreach and education on AI in construction. 🌟 Why Follow My Work? I’m committed to bridging the gap between traditional construction methods and modern AI. Each project is an opportunity to push boundaries, learn something new, and contribute to a more efficient, intelligent construction future. My mission is to make AI accessible, impactful, and production-ready for real-world challenges. 📌 Want to Know More? Explore my projects, share your feedback, or collaborate! AI has the potential to revolutionize construction, and we’re just scratching the surface. Whether you’re a fellow AI enthusiast, a construction professional, or simply curious, I invite you to join the journey.

Welcome! I’m Mohamed Ashour, a Chartered Quantity Surveyor deeply passionate about applying Data Analytics and Artificial Intelligence to the construction industry. Here, you’ll find a collection of cutting-edge AI initiatives, each aiming to redefine how we approach construction and project management. My work explores the powerful synergy between construction expertise and machine learning —turning concepts into scalable, production-ready solutions.

I’m committed to bridging the gap between traditional construction methods and modern AI. Each project is an opportunity to push boundaries, learn something new, and contribute to a more efficient, intelligent construction future. My mission is to make AI accessible, impactful, and production-ready for real-world challenges.

Explore my projects, share your feedback, or collaborate! AI has the potential to revolutionize construction, and we’re just scratching the surface. Whether you’re a fellow AI enthusiast, a construction professional, or simply curious, I invite you to join the journey.

This repository contains projects developed to showcase how to apply Generative AI and open-source LLMs in the construction industry

DDC Skills Collection for AI Coding Assistants AI Tools for Construction Company Automation Works with any AI coding assistant: What is this? A collection of 238 skills for automating construction company processes with AI coding assistants. What is a "Skill"? A skill is a SKILL.md file — structured instructions that an AI coding assistant can read and execute. Each skill describes a specific task: what problem it solves, what code to generate, and what tools are needed. You open a skill folder in your AI assistant, and it helps you implement the described functionality. Collection Structure Skills are organized by source and complexity level: Category What's inside Skills Start here if... 1_DDC_Toolkit Production-ready tools: CWICR database, CAD converters, analytics 85 You need a working tool now 2_DDC_Book Skills mapped to book chapters: data evolution, types, estimation, ML 67 You want to follow a structured learning path 3_DDC_Insights Practical workflows: n8n automation, AI agents, field tools 20 You need workflow automation 4_DDC_Curated Document generation (PDF, Excel, DOCX, PPTX), quality checks 20 You need document or report templates 5_DDC_Innovative Advanced: computer vision, IoT, digital twins, risk assessment, AI agents, ESG, EU AI Act, circular construction, generative design 34 You're ready for AI/ML experimentation 6_OpenConstructionERP Work with the OpenConstructionERP platform: load cost bases, BOQ & estimating, BIM takeoff, 4D/5D, cost browser, MCP, field ops, tendering, validation, geo/coordination, property development 12 You build on the open-source construction ERP mindmap root((DDC Skills 238 skills)) 1_DDC_Toolkit CWICR Database 8 national bases 30 markets · 26 languages CAD Converters RVT → Excel IFC → Excel DWG → Excel Analytics KPI Dashboard Cost Analysis 2_DDC_Book Part I: Data Evolution Part II: Data Types Part III: Estimation Part IV: Analytics & ML Part V: Threats & Strategy 3_DDC_Insights n8n Workflows Daily Reports Photo Reports AI Agents 2026 Field Automation 4_DDC_Curated Document Generation PDF, Excel DOCX, PPTX Quality Assurance 5_DDC_Innovative AI/ML Skills Defect Detection Risk Assessment IoT & Sensors Advanced BIM Digital Twin AI Agent Orchestration Embodied Carbon & ESG EU AI Act Material Passports Generative Design 6_OpenConstructionERP Load Cost Bases TR · ZH · BR · ES · IT VN · ID · GR · 30 markets BOQ & Estimating BIM & CAD Takeoff 4D/5D Scheduling Cost Browser MCP Integration Field Ops · Tendering Validation · Geo Hub Property Development Loading Where to Start If you manage or lead a construction company: Step 1. Read GETTING_STARTED.md — a non-technical overview of what can be automated and how to prioritize. Step 2. Download the Data-Driven Construction book (free, 31 languages) — it explains the methodology behind these skills: how to assess your company's data maturity, identify bottlenecks, and plan digital transformation. Step 3. Identify your biggest pain point in the table below and start with the corresponding skill. If you are a developer or IT lead: Step 1. Install prerequisites (see Prerequisites ). Step 2. Pick a skill from the table below, open its folder in your AI assistant, and follow the SKILL.md . Step 3. Adapt the generated code to your data and deploy. What Can You Automate? Examples of common problems and which skills address them: Your problem What the skill does Skill to run Folder Searching for work item rates takes too long Semantic search across 78,228 national + 55,719 global items in 26 languages semantic-search-cwicr 1_DDC_Toolkit/ Estimators spend days building estimates manually Generates estimates from historical data and templates estimate-builder 1_DDC_Toolkit/ BIM models contain data but it's locked in RVT/IFC files Extracts quantities and properties to Excel ifc-to-excel , rvt-to-excel 1_DDC_Toolkit/ Daily/weekly reports take hours to compile Automated data collection and report generation n8n-daily-report 3_DDC_Insights/ Site photos pile up with no organization AI classifies and tags site photos automatically n8n-photo-report 3_DDC_Insights/ Data is scattered across Excel files, emails, PDFs Finds all data sources and maps dependencies data-silo-detection 2_DDC_Book/ No visibility into project KPIs Dashboard with real-time metrics from your data kpi-dashboard 1_DDC_Toolkit/ Budget overruns discovered too late Scheduled budget vs. actual comparison budget-tracker 1_DDC_Toolkit/ PDF specifications need to be searchable Extracts text and tables from PDFs into structured data specification-extractor 2_DDC_Book/ Schedule delays are hard to predict Statistical analysis of schedule variance patterns schedule-delay-analyzer 3_DDC_Insights/ This is a selection of examples. The full collection contains 221 skills covering estimation, reporting, BIM, document processing, analytics, and more. How to Use a Skill 1. Clone this repository git clone https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction.git 2. Open a skill folder in your AI assistant cd DDC_Skills_for_AI_Agents_in_Construction/1_DDC_Toolkit/CWICR-Database/semantic-search-cwicr/ 3. The assistant reads SKILL.md and generates the code for you 4. Review, adapt to your data, and run Example: ETL Pipeline # Automatic processing of all Excel files from a folder import pandas as pd from pathlib import Path # Extract all_data = [ pd . read_excel ( f ) for f in Path ( "./estimates/" ). glob ( "*.xlsx" )] df = pd . concat ( all_data ) # Transform df [ 'Total' ] = df [ 'Quantity' ] * df [ 'Unit_Price' ] summary = df . groupby ( 'Category' )[ 'Total' ]. sum () # Load summary . to_excel ( "summary_report.xlsx" ) Implementation Path A typical automation project follows these stages. You don't need to do all of them — start with what solves your most pressing problem. Stage What you do Which skills help 1. Audit List all data sources in your company (Excel files, databases, BIM models, PDFs, emails) data-silo-detection , data-source-audit 2. Classify Understand what data you have: structured, semi-structured, or unstructured data-type-classifier , data-profiler 3. Connect Build ETL pipelines to extract and normalize data etl-pipeline , ifc-to-excel , specification-extractor 4. Automate Set up recurring reports, alerts, and dashboards n8n-daily-report , kpi-dashboard , budget-tracker 5. Analyze Apply analytics and ML to find patterns and predict outcomes cost-prediction , schedule-forecaster , risk-assessment Each stage builds on the previous one, but you can enter at any point depending on your current state. How Does It Work? Each step in the implementation path corresponds to specific skills and tools: flowchart LR subgraph S1["STEP 1"] A[Audit Find Data Silos] end subgraph S2["STEP 2"] B[Classify Data Types] end subgraph S3["STEP 3"] C[Connect ETL Pipelines] end subgraph S4["STEP 4"] D[Automate Reports & Dashboards] end subgraph S5["STEP 5"] E[Analyze ML & Predictions] end A --> B --> C --> D --> E A1[data-silo-detection data-source-audit] -.-> A B1[data-type-classifier data-profiler] -.-> B C1[etl-pipeline ifc-to-excel] -.-> C D1[n8n-daily-report kpi-dashboard] -.-> D E1[cost-prediction schedule-forecaster] -.-> E style S1 fill:#ffebee style S2 fill:#fff3e0 style S3 fill:#e8f5e9 style S4 fill:#e3f2fd style S5 fill:#f3e5f5 Loading Data Types in Construction Construction data comes in three forms. Each requires a different processing approach, and each has corresponding skills: flowchart TB subgraph STRUCTURED["STRUCTURED"] S1[Excel] S2[SQL Database] S3[CSV] end subgraph SEMI["SEMI-STRUCTURED"] M1[IFC/BIM] M2[JSON] M3[XML] end subgraph UNSTRUCTURED["UNSTRUCTURED"] U1[PDF] U2[Photos] U3[Scans] end STRUCTURED -->|SQL queries, pandas| DB[(Central Database)] SEMI -->|ifcopenshell, parsers| DB UNSTRUCTURED -->|AI/OCR, pdfplumber| DB DB --> AUTO[Automation & Analytics] style STRUCTURED fill:#c8e6c9 style SEMI fill:#fff9c4 style UNSTRUCTURED fill:#ffcdd2 style DB fill:#e1f5fe style AUTO fill:#f3e5f5 Loading Data type Examples Skills that process it Structured Excel, CSV, SQL databases etl-pipeline , estimate-builder , budget-tracker Semi-structured IFC/BIM models, JSON, XML ifc-to-excel , rvt-to-excel , dwg-to-excel Unstructured PDF documents, photos, scans specification-extractor , n8n-photo-report , document-ocr Prerequisites Requirement Details Python 3.9+ Most skills use Python scripts AI Coding Assistant Claude Code, Cursor, Copilot, or similar Basic Python knowledge Ability to run scripts and install packages Your data Excel files, PDFs, or BIM models to process Optional for advanced skills: Docker (for n8n workflows) PostgreSQL or SQLite (for database skills) OpenAI API key (for LLM-based skills) Installation pip install pandas openpyxl ifcopenshell pdfplumber Data Flow in Construction Skills cover the typical data pipeline: from raw input files to processed, actionable outputs. flowchart LR subgraph INPUT["📥 YOUR DATA"] A1[Excel Estimates] A2[Revit/IFC Models] A3[Site Photos] A4[PDF Documents] end subgraph DDC["⚙️ DDC SKILLS"] B1[ETL Pipeline] B2[IFC Parser] B3[AI Analysis] B4[Document OCR] end subgraph OUTPUT["📤 RESULTS"] C1[Auto Reports] C2[Auto Estimates] C3[Progress Tracking] C4[Searchable Data] end A1 --> B1 --> C1 A2 --> B2 --> C2 A3 --> B3 --> C3 A4 --> B4 --> C4 style INPUT fill:#e1f5fe style DDC fill:#fff3e0 style OUTPUT fill:#e8f5e9 Loading Construction data comes in three forms. Each requires a different processing approach: Data type Examples How skills process it Structured Excel, CSV, SQL databases Direct queries and transformations Semi-structured IFC/BIM models, JSON, XML Parsing with specialized libraries Unstructured PDF documents, photos, scans AI/OCR extraction to structured format Folder Structure DDC_Skills/ │ ├── 1_DDC_Toolkit/ ← Production tools (85 skills) │ ├── CWICR-Database/ ← 8 national bases + 30 markets database │ ├── CAD-Converters/ ← Revit/IFC/DWG → Excel │ └── ... │ ├── 2_DDC_Book/ ← Skills from the book (67 skills) │ ├── 1.1-Data-Evolution/ ← Digital maturity assessment │ ├── 1.2-Data-Silos-Integration/ ← Find & connect data sources │ ├── 3.1-Cost-Estimation/ ← Build estimates from data │ ├── 4.2-ETL-Automation/ ← Automate data pipelines │ └── ... │ ├── 3_DDC_Insights/ ← Practical workflows (20 skills) │ ├── Automation-Workflows/ ← n8n automation │ ├── AI-Agents/ ← Multi-agent systems (2026) │ ├── Field-Automation/ ← Telegram bot, voice reports │ └── Open-Data-Transparency/ ← Uberization readiness │ ├── 4_DDC_Curated/ ← External skills (20 skills) │ ├── Document-Generation/ ← PDF/Excel/DOCX/PPTX generation │ └── Quality-Assurance/ ← Quality checks │ ├── 5_DDC_Innovative/ ← Advanced AI/ML skills (29 skills) │ ├── defect-detection-ai/ ← Computer vision for defects │ ├── digital-twin-sync/ ← Real-time BIM sync │ └── ... │ ├── Books/ ← Free book downloads (31 languages) ├── GETTING_STARTED.md ← START HERE └── README.md ← You are here Documentation Document Description Audience GETTING_STARTED.md Step-by-step automation guide Executives, beginners OPTIMIZER_GUIDE.md How to work effectively with AI assistants Developers IMPROVEMENT_ROADMAP.md Collection development plan Contributors Potential Time Savings Automation results vary depending on company size, data quality, and implementation effort: Process Manual approach With automation Find work item rate Search through price books Database query with filters Daily report compilation Collect data from multiple sources Pre-configured data aggregation IFC quantity extraction Open model, measure manually Script-based extraction to Excel Budget variance tracking Weekly spreadsheet updates Scheduled comparison reports Document organization Manual folder sorting Metadata-based classification Results depend on data preparation and workflow complexity. See GETTING_STARTED.md for implementation guidance. About the Book The majority of skills are based on the book "Data-Driven Construction" — a methodology for digital transformation in construction. The book explains the reasoning behind each skill category: why data silos matter, how to classify your data, and what to automate first. Book structure maps to skills: Part I — Data landscape assessment → 2_DDC_Book/1.1-* , 1.2-* Part II — Data types and classification → 2_DDC_Book/2.1-* through 2.6-* Part III — Estimation and scheduling → 2_DDC_Book/3.1-* through 3.3-* Part IV — Analytics and ML → 2_DDC_Book/4.1-* through 4.5-* Part V — Threats and long-term strategy → 2_DDC_Book/5.* Download Free in 31 Languages → Resources Resource Link Book (All Languages) https://datadrivenconstruction.io/books/ Website https://datadrivenconstruction.io CWICR Demo https://openconstructionestimate.com GitHub https://github.com/datadrivenconstruction CWICR Database https://github.com/datadrivenconstruction/OpenConstructionEstimate-DDC-CWICR CAD2Data Pipeline https://github.com/datadrivenconstruction/cad2data-Revit-IFC-DWG-DGN-pipeline-with-conversion-validation-qto Support the Project If you find these tools useful, please give the repository a star — it helps others discover these resources. Related repositories: Repository Description OpenConstructionEstimate-DDC-CWICR 8 national bases + 30 markets in 26 languages cad2data Pipeline Revit/IFC/DWG/DGN to Excel converter Contributing Contributions are welcome: Report issues — bugs, unclear documentation, broken links Suggest skills — describe the automation you need Submit PRs — new skills, improvements, translations Each skill should include a SKILL.md with clear instructions and working code examples. License CWICR Database : CC BY-NC 4.0 (non-commercial; separate DDC commercial license) DDC Tools : MIT License Skills : MIT License Trademarks All product names, logos, and brands mentioned in this repository are property of their respective owners. All company, product and service names used are for identification purposes only. Use of these names, logos, and brands does not imply endorsement. IFC is an open standard by buildingSMART International File format references (RVT, DWG, DGN, NWD, etc.) are used for technical interoperability purposes only Start here → GETTING_STARTED.md

A collection of 238 skills for automating construction company processes with AI coding assistants.

A skill is a SKILL.md file — structured instructions that an AI coding assistant can read and execute. Each skill describes a specific task: what problem it solves, what code to generate, and what tools are needed. You open a skill folder in your AI assistant, and it helps you implement the described functionality.

mindmap root((DDC Skills 238 skills)) 1_DDC_Toolkit CWICR Database 8 national bases 30 markets · 26 languages CAD Converters RVT → Excel IFC → Excel DWG → Excel Analytics KPI Dashboard Cost Analysis 2_DDC_Book Part I: Data Evolution Part II: Data Types Part III: Estimation Part IV: Analytics & ML Part V: Threats & Strategy 3_DDC_Insights n8n Workflows Daily Reports Photo Reports AI Agents 2026 Field Automation 4_DDC_Curated Document Generation PDF, Excel DOCX, PPTX Quality Assurance 5_DDC_Innovative AI/ML Skills Defect Detection Risk Assessment IoT & Sensors Advanced BIM Digital Twin AI Agent Orchestration Embodied Carbon & ESG EU AI Act Material Passports Generative Design 6_OpenConstructionERP Load Cost Bases TR · ZH · BR · ES · IT VN · ID · GR · 30 markets BOQ & Estimating BIM & CAD Takeoff 4D/5D Scheduling Cost Browser MCP Integration Field Ops · Tendering Validation · Geo Hub Property Development

Step 1. Read GETTING_STARTED.md — a non-technical overview of what can be automated and how to prioritize.

Step 2. Download the Data-Driven Construction book (free, 31 languages) — it explains the methodology behind these skills: how to assess your company's data maturity, identify bottlenecks, and plan digital transformation.

2. Related Work, Literature Survey & Algorithmic Foundations

Step 3. Identify your biggest pain point in the table below and start with the corresponding skill.

Step 2. Pick a skill from the table below, open its folder in your AI assistant, and follow the SKILL.md .

This is a selection of examples. The full collection contains 221 skills covering estimation, reporting, BIM, document processing, analytics, and more.

1. Clone this repository git clone https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction.git 2. Open a skill folder in your AI assistant cd DDC_Skills_for_AI_Agents_in_Construction/1_DDC_Toolkit/CWICR-Database/semantic-search-cwicr/ 3. The assistant reads SKILL.md and generates the code for you 4. Review, adapt to your data, and run

# Automatic processing of all Excel files from a folder import pandas as pd from pathlib import Path # Extract all_data = [ pd . read_excel ( f ) for f in Path ( "./estimates/" ). glob ( "*.xlsx" )] df = pd . concat ( all_data ) # Transform df [ 'Total' ] = df [ 'Quantity' ] * df [ 'Unit_Price' ] summary = df . groupby ( 'Category' )[ 'Total' ]. sum () # Load summary . to_excel ( "summary_report.xlsx" )

A typical automation project follows these stages. You don't need to do all of them — start with what solves your most pressing problem.

Each stage builds on the previous one, but you can enter at any point depending on your current state.

flowchart LR subgraph S1["STEP 1"] A[Audit Find Data Silos] end subgraph S2["STEP 2"] B[Classify Data Types] end subgraph S3["STEP 3"] C[Connect ETL Pipelines] end subgraph S4["STEP 4"] D[Automate Reports & Dashboards] end subgraph S5["STEP 5"] E[Analyze ML & Predictions] end A --> B --> C --> D --> E A1[data-silo-detection data-source-audit] -.-> A B1[data-type-classifier data-profiler] -.-> B C1[etl-pipeline ifc-to-excel] -.-> C D1[n8n-daily-report kpi-dashboard] -.-> D E1[cost-prediction schedule-forecaster] -.-> E style S1 fill:#ffebee style S2 fill:#fff3e0 style S3 fill:#e8f5e9 style S4 fill:#e3f2fd style S5 fill:#f3e5f5

Construction data comes in three forms. Each requires a different processing approach, and each has corresponding skills:

flowchart TB subgraph STRUCTURED["STRUCTURED"] S1[Excel] S2[SQL Database] S3[CSV] end subgraph SEMI["SEMI-STRUCTURED"] M1[IFC/BIM] M2[JSON] M3[XML] end subgraph UNSTRUCTURED["UNSTRUCTURED"] U1[PDF] U2[Photos] U3[Scans] end STRUCTURED -->|SQL queries, pandas| DB[(Central Database)] SEMI -->|ifcopenshell, parsers| DB UNSTRUCTURED -->|AI/OCR, pdfplumber| DB DB --> AUTO[Automation & Analytics] style STRUCTURED fill:#c8e6c9 style SEMI fill:#fff9c4 style UNSTRUCTURED fill:#ffcdd2 style DB fill:#e1f5fe style AUTO fill:#f3e5f5

Skills cover the typical data pipeline: from raw input files to processed, actionable outputs.

3. Dataset Ingestion, Preprocessing & Stochastic Augmentations

flowchart LR subgraph INPUT["📥 YOUR DATA"] A1[Excel Estimates] A2[Revit/IFC Models] A3[Site Photos] A4[PDF Documents] end subgraph DDC["⚙️ DDC SKILLS"] B1[ETL Pipeline] B2[IFC Parser] B3[AI Analysis] B4[Document OCR] end subgraph OUTPUT["📤 RESULTS"] C1[Auto Reports] C2[Auto Estimates] C3[Progress Tracking] C4[Searchable Data] end A1 --> B1 --> C1 A2 --> B2 --> C2 A3 --> B3 --> C3 A4 --> B4 --> C4 style INPUT fill:#e1f5fe style DDC fill:#fff3e0 style OUTPUT fill:#e8f5e9

Construction data comes in three forms. Each requires a different processing approach:

DDC_Skills/ │ ├── 1_DDC_Toolkit/ ← Production tools (85 skills) │ ├── CWICR-Database/ ← 8 national bases + 30 markets database │ ├── CAD-Converters/ ← Revit/IFC/DWG → Excel │ └── ... │ ├── 2_DDC_Book/ ← Skills from the book (67 skills) │ ├── 1.1-Data-Evolution/ ← Digital maturity assessment │ ├── 1.2-Data-Silos-Integration/ ← Find & connect data sources │ ├── 3.1-Cost-Estimation/ ← Build estimates from data │ ├── 4.2-ETL-Automation/ ← Automate data pipelines │ └── ... │ ├── 3_DDC_Insights/ ← Practical workflows (20 skills) │ ├── Automation-Workflows/ ← n8n automation │ ├── AI-Agents/ ← Multi-agent systems (2026) │ ├── Field-Automation/ ← Telegram bot, voice reports │ └── Open-Data-Transparency/ ← Uberization readiness │ ├── 4_DDC_Curated/ ← External skills (20 skills) │ ├── Document-Generation/ ← PDF/Excel/DOCX/PPTX generation │ └── Quality-Assurance/ ← Quality checks │ ├── 5_DDC_Innovative/ ← Advanced AI/ML skills (29 skills) │ ├── defect-detection-ai/ ← Computer vision for defects │ ├── digital-twin-sync/ ← Real-time BIM sync │ └── ... │ ├── Books/ ← Free book downloads (31 languages) ├── GETTING_STARTED.md ← START HERE └── README.md ← You are here

Automation results vary depending on company size, data quality, and implementation effort:

Results depend on data preparation and workflow complexity. See GETTING_STARTED.md for implementation guidance.

The majority of skills are based on the book "Data-Driven Construction" — a methodology for digital transformation in construction. The book explains the reasoning behind each skill category: why data silos matter, how to classify your data, and what to automate first.

If you find these tools useful, please give the repository a star — it helps others discover these resources.

Each skill should include a SKILL.md with clear instructions and working code examples.

All product names, logos, and brands mentioned in this repository are property of their respective owners. All company, product and service names used are for identification purposes only. Use of these names, logos, and brands does not imply endorsement.

221 AI skills for construction: BIM analysis, cost estimation, scheduling, document control, and automation with Claude Code

On a local terminal, or a non-TTY local process that can still reach a browser (for example, a desktop OS, or Linux with a display or browser signal), the default authentication mode is a browser-based web flow: the CLI opens your browser to authorize, then captures the result on a local loopback callback. On a remote terminal (for example, SSH, GitHub Codespaces, or a dev container) or in CI, the CLI defaults to the OAuth device code flow instead, since the browser typically can't reach the loopback port. Use --web-flow or --device-code to override the automatically selected flow.

4. Neural Network Backbone, Layer Specifications & Loss Formulations

After completion, an authentication token is stored securely in the system credential store. If a credential store is not found, the token is stored in a plain text configuration file under ~/.copilot/ (or the directory specified by COPILOT_HOME if set).

Alternatively, Copilot CLI will use an authentication token found in environment variables. The following are checked in order of precedence: COPILOT_GITHUB_TOKEN , GH_TOKEN , GITHUB_TOKEN . This method is most suitable for headless use such as automation.

Supported token types include fine-grained personal access tokens (v2 PATs) with the "Copilot Requests" permission, OAuth tokens from the Copilot CLI app, and OAuth tokens from the GitHub CLI ( gh ) app. Classic personal access tokens ( ghp_ ) are not supported.

# Authenticate with github.com copilot login # Authenticate with GitHub Enterprise Cloud (data residency) copilot login --host https://example.ghe.com # Force the device code flow, for example on a remote terminal copilot login --device-code # Force the browser (web) flow, for example on a local terminal copilot login --web-flow # Read a token from standard input, bypassing the OAuth flow entirely copilot login --with-token < mytoken.txt # Use a fine-grained PAT via environment variable COPILOT_GITHUB_TOKEN=github_pat_... copilot

The command copilot completion SHELL outputs a script for the specified shell (bash, zsh, or fish).

By sourcing this script (or writing it to your shell's completion directory) you can enable tab completion in your terminal for copilot subcommands, command options, and known value choices for command options. For copilot config , completion also covers setting keys, boolean and enum values, and files or directories for path-valued settings.

Zsh — write the output to a directory on your $fpath. Restart the shell after running this command:

Use copilot plugin to install, list, update, enable, disable, and uninstall plugins from the command line, without opening an interactive session. copilot plugins (plural) is a legacy alias for the same command. For the full command and option reference, see GitHub Copilot CLI plugin reference .

Run copilot config to read and change Copilot settings from the command line, outside an interactive session. This is the non-interactive counterpart to the /settings (or /config ) slash command. For more information about the settings file and its keys, see GitHub Copilot CLI configuration directory .

# Print a setting copilot config theme # Set a nested value (dot notation) copilot config footer.showQuota off # Append an item to a list setting (added only if not already present) copilot config allowedUrls github.com # Append an item that starts with a dash copilot config powershellFlags -- -NoProfile # Remove a key, or one list item copilot config -- rm theme copilot config -- rm allowedUrls github.com # List settings as key=value lines, or as JSON copilot config --list copilot config --repo --list --json

Values must match the setting's type: on / off or true / false for booleans, a number for numeric settings, or an accepted choice for enums. Reading a list prints one item per line; reading a group prints JSON. An unset key exits with status 1 . Secret values are redacted from output.

5. Training Protocol, Convergence Behavior & Experimental Evaluation

Commands use your user settings file ( settings.json in ~/.copilot , or in $COPILOT_HOME when set) by default. --repo and --local accept only the settings a repository can override—see GitHub Copilot CLI configuration directory . Run copilot help config for the available settings.

Run copilot instruction list to non-interactively list custom instruction sources discovered for the current working directory. This replaces the retired copilot plugins list --kind instruction .

Each --json entry has the shape { id, label, description?, location, type, sourcePath, defaultDisabled, applyTo? } . This listing resolves plugin-contributed instructions against your global user settings only—an instruction enabled by a trusted repository or by managed settings might not appear here even though a live session applies it.

Run copilot lsp list to non-interactively list configured language servers. This replaces the retired copilot plugins list --kind lsp . This command is inspect-only; use the /lsp slash command in an interactive session to start, stop, or reload a language server.

Custom agents and session-scoped hooks aren't covered by copilot instruction , copilot lsp , copilot plugin , copilot mcp , or copilot skill . All require a live session.

Use copilot memories import to validate and import user-level preferences and repository-level facts from a JSONL file.

If any line fails schema validation, no records are submitted. After validation succeeds, records are submitted individually, so a service failure can result in a partial import. Check the per-record results and retry only failed records. The --on-conflict skip option skips duplicate IDs within the input file and conflicts reported by the memory service. It does not guarantee that repeating an import will avoid duplicate memories. For the file format and examples, see Manually creating memories for GitHub Copilot .

Run a dynamic workflow provided by an extension, without opening an interactive session:

WORKFLOW-NAME is the name registered by the extension, not a path to an extension file. The command starts a run and waits for it to finish, pause, or otherwise stop.

Relative argument-file and result-file paths are resolved from the working directory. Without --silent , output includes phases and progress messages reported by the workflow.

The command uses the CLI's authentication, model, permission, and sandbox settings. Permission options such as --allow-tool and --allow-url apply to the workflow's agents. It does not display permission approval prompts.