As Built Tracker logo

As Built Tracker

Community
datadrivenconstruction
as-built-tracker

Track as-built documentation and record drawings. Monitor submission status, manage revisions, and ensure completeness for handover.

Overview

Publisherdatadrivenconstruction
RepositoryDDC_Skills_for_AI_Agents_in_Construction
Skill nameas-built-tracker
Stars
365
Forks
91
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by datadrivenconstruction on GitHub. Read the source before you install it.

Installation

Install the As Built Tracker AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction/tree/main/1_DDC_Toolkit/Closeout/as-built-tracker
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction.git /tmp/DDC_Skills_for_AI_Agents_in_Construction
mkdir -p .claude/skills
cp -r /tmp/DDC_Skills_for_AI_Agents_in_Construction/1_DDC_Toolkit/Closeout/as-built-tracker .claude/skills/as-built-tracker
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable As Built Tracker in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads As Built Tracker on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so As Built Tracker is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

As-Built Documentation Tracker

Business Case

Problem Statement

As-built documentation challenges:

  • Tracking hundreds of drawings
  • Managing revisions
  • Ensuring completeness
  • Meeting handover deadlines

Solution

Systematic tracking of as-built documentation submissions, revisions, and approval status.

Technical Implementation

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


class DocumentStatus(Enum):
    NOT_STARTED = "not_started"
    IN_PROGRESS = "in_progress"
    SUBMITTED = "submitted"
    UNDER_REVIEW = "under_review"
    APPROVED = "approved"
    REJECTED = "rejected"
    RESUBMIT = "resubmit"


class DocumentType(Enum):
    ARCHITECTURAL = "architectural"
    STRUCTURAL = "structural"
    MECHANICAL = "mechanical"
    ELECTRICAL = "electrical"
    PLUMBING = "plumbing"
    FIRE_PROTECTION = "fire_protection"
    CIVIL = "civil"
    LANDSCAPE = "landscape"
    SPECIFICATIONS = "specifications"
    O_AND_M = "o_and_m"


@dataclass
class AsBuiltDocument:
    document_id: str
    document_number: str
    title: str
    doc_type: DocumentType
    discipline: str
    contractor: str
    status: DocumentStatus
    current_revision: str
    required_date: date
    submitted_date: Optional[date] = None
    approved_date: Optional[date] = None
    reviewer: str = ""
    comments: str = ""
    file_path: str = ""


@dataclass
class DocumentSubmission:
    submission_id: str
    document_id: str
    revision: str
    submission_date: date
    submitted_by: str
    file_path: str
    status: DocumentStatus
    review_comments: str = ""


class AsBuiltTracker:
    """Track as-built documentation."""

    def __init__(self, project_name: str, handover_date: date):
        self.project_name = project_name
        self.handover_date = handover_date
        self.documents: Dict[str, AsBuiltDocument] = {}
        self.submissions: List[DocumentSubmission] = []
        self._next_id = 1

    def add_document(self,
                     document_number: str,
                     title: str,
                     doc_type: DocumentType,
                     discipline: str,
                     contractor: str,
                     required_date: date = None) -> AsBuiltDocument:
        """Add document to tracking."""

        doc_id = f"DOC-{self._next_id:04d}"
        self._next_id += 1

        if required_date is None:
            required_date = self.handover_date - timedelta(days=14)

        doc = AsBuiltDocument(
            document_id=doc_id,
            document_number=document_number,
            title=title,
            doc_type=doc_type,
            discipline=discipline,
            contractor=contractor,
            status=DocumentStatus.NOT_STARTED,
            current_revision="0",
            required_date=required_date
        )

        self.documents[doc_id] = doc
        return doc

    def import_document_list(self, df: pd.DataFrame):
        """Import document list from DataFrame."""

        for _, row in df.iterrows():
            doc_type = DocumentType(row.get('type', 'architectural').lower())
            req_date = pd.to_datetime(row.get('required_date', self.handover_date)).date() if 'required_date' in row else None

            self.add_document(
                document_number=str(row['document_number']),
                title=row['title'],
                doc_type=doc_type,
                discipline=row.get('discipline', ''),
                contractor=row.get('contractor', ''),
                required_date=req_date
            )

    def record_submission(self,
                          document_id: str,
                          revision: str,
                          submitted_by: str,
                          file_path: str = "") -> Optional[DocumentSubmission]:
        """Record document submission."""

        if document_id not in self.documents:
            return None

        doc = self.documents[document_id]

        submission = DocumentSubmission(
            submission_id=f"SUB-{len(self.submissions)+1:04d}",
            document_id=document_id,
            revision=revision,
            submission_date=date.today(),
            submitted_by=submitted_by,
            file_path=file_path,
            status=DocumentStatus.SUBMITTED
        )

        self.submissions.append(submission)

        # Update document
        doc.status = DocumentStatus.SUBMITTED
        doc.current_revision = revision
        doc.submitted_date = date.today()

        return submission

    def review_submission(self,
                          document_id: str,
                          approved: bool,
                          reviewer: str,
                          comments: str = ""):
        """Review submitted document."""

        if document_id not in self.documents:
            return

        doc = self.documents[document_id]

        if approved:
            doc.status = DocumentStatus.APPROVED
            doc.approved_date = date.today()
        else:
            doc.status = DocumentStatus.REJECTED

        doc.reviewer = reviewer
        doc.comments = comments

        # Update latest submission
        for sub in reversed(self.submissions):
            if sub.document_id == document_id:
                sub.status = DocumentStatus.APPROVED if approved else DocumentStatus.REJECTED
                sub.review_comments = comments
                break

    def get_summary(self) -> Dict[str, Any]:
        """Get documentation status summary."""

        docs = list(self.documents.values())
        today = date.today()

        # Status counts
        status_counts = {}
        for status in DocumentStatus:
            status_counts[status.value] = sum(1 for d in docs if d.status == status)

        # By type
        by_type = {}
        for doc_type in DocumentType:
            pending = sum(1 for d in docs if d.doc_type == doc_type and d.status != DocumentStatus.APPROVED)
            if pending > 0:
                by_type[doc_type.value] = pending

        # Overdue
        overdue = sum(
            1 for d in docs
            if d.required_date < today and d.status != DocumentStatus.APPROVED
        )

        # Completion rate
        approved = sum(1 for d in docs if d.status == DocumentStatus.APPROVED)
        completion = (approved / len(docs) * 100) if docs else 0

        return {
            'total_documents': len(docs),
            'approved': approved,
            'completion_rate': round(completion, 1),
            'by_status': status_counts,
            'by_type': by_type,
            'overdue': overdue,
            'days_to_handover': (self.handover_date - today).days
        }

    def get_contractor_status(self, contractor: str) -> Dict[str, Any]:
        """Get status for specific contractor."""

        docs = [d for d in self.documents.values() if d.contractor == contractor]

        approved = sum(1 for d in docs if d.status == DocumentStatus.APPROVED)
        pending = len(docs) - approved

        return {
            'contractor': contractor,
            'total': len(docs),
            'approved': approved,
            'pending': pending,
            'completion_rate': round(approved / len(docs) * 100, 1) if docs else 0
        }

    def get_overdue_documents(self) -> List[Dict[str, Any]]:
        """Get overdue documents."""

        today = date.today()
        overdue = []

        for doc in self.documents.values():
            if doc.required_date < today and doc.status != DocumentStatus.APPROVED:
                overdue.append({
                    'document_id': doc.document_id,
                    'document_number': doc.document_number,
                    'title': doc.title,
                    'contractor': doc.contractor,
                    'required_date': doc.required_date,
                    'days_overdue': (today - doc.required_date).days,
                    'status': doc.status.value
                })

        return sorted(overdue, key=lambda x: x['days_overdue'], reverse=True)

    def forecast_completion(self) -> Dict[str, Any]:
        """Forecast documentation completion."""

        summary = self.get_summary()
        pending = summary['total_documents'] - summary['approved']

        # Calculate submission rate
        recent_approvals = sum(
            1 for d in self.documents.values()
            if d.approved_date and d.approved_date >= date.today() - timedelta(days=14)
        )
        weekly_rate = recent_approvals / 2 if recent_approvals > 0 else 1

        weeks_needed = pending / weekly_rate if weekly_rate > 0 else pending
        projected_completion = date.today() + timedelta(weeks=weeks_needed)

        return {
            'pending_documents': pending,
            'approval_rate_per_week': round(weekly_rate, 1),
            'weeks_needed': round(weeks_needed, 1),
            'projected_completion': projected_completion,
            'handover_date': self.handover_date,
            'on_track': projected_completion <= self.handover_date
        }

    def generate_transmittal(self,
                              document_ids: List[str],
                              to: str,
                              subject: str) -> Dict[str, Any]:
        """Generate transmittal for documents."""

        docs = [self.documents[d] for d in document_ids if d in self.documents]

        return {
            'transmittal_number': f"TR-{date.today().strftime('%Y%m%d')}-001",
            'date': date.today(),
            'from': self.project_name,
            'to': to,
            'subject': subject,
            'documents': [
                {
                    'number': d.document_number,
                    'title': d.title,
                    'revision': d.current_revision
                }
                for d in docs
            ],
            'document_count': len(docs)
        }

    def export_to_excel(self, output_path: str) -> str:
        """Export tracking to Excel."""

        summary = self.get_summary()

        with pd.ExcelWriter(output_path, engine='openpyxl') as writer:
            # Summary
            summary_df = pd.DataFrame([{
                'Project': self.project_name,
                'Handover Date': self.handover_date,
                'Total Documents': summary['total_documents'],
                'Approved': summary['approved'],
                'Completion %': summary['completion_rate'],
                'Overdue': summary['overdue'],
                'Days to Handover': summary['days_to_handover']
            }])
            summary_df.to_excel(writer, sheet_name='Summary', index=False)

            # All Documents
            docs_df = pd.DataFrame([
                {
                    'ID': d.document_id,
                    'Number': d.document_number,
                    'Title': d.title,
                    'Type': d.doc_type.value,
                    'Discipline': d.discipline,
                    'Contractor': d.contractor,
                    'Status': d.status.value,
                    'Revision': d.current_revision,
                    'Required': d.required_date,
                    'Submitted': d.submitted_date,
                    'Approved': d.approved_date
                }
                for d in self.documents.values()
            ])
            docs_df.to_excel(writer, sheet_name='Documents', index=False)

            # Overdue
            overdue = self.get_overdue_documents()
            if overdue:
                overdue_df = pd.DataFrame(overdue)
                overdue_df.to_excel(writer, sheet_name='Overdue', index=False)

            # By Contractor
            contractors = set(d.contractor for d in self.documents.values())
            contractor_data = [self.get_contractor_status(c) for c in contractors]
            if contractor_data:
                contractor_df = pd.DataFrame(contractor_data)
                contractor_df.to_excel(writer, sheet_name='By Contractor', index=False)

        return output_path

Quick Start

python
from datetime import date, timedelta

# Initialize tracker
tracker = AsBuiltTracker("Office Building A", handover_date=date(2024, 12, 31))

# Add documents
tracker.add_document(
    document_number="A-001",
    title="Floor Plans Level 1-5",
    doc_type=DocumentType.ARCHITECTURAL,
    discipline="Architecture",
    contractor="ABC Architects"
)

tracker.add_document(
    document_number="M-001",
    title="HVAC Layout",
    doc_type=DocumentType.MECHANICAL,
    discipline="HVAC",
    contractor="XYZ MEP"
)

# Record submission
tracker.record_submission("DOC-0001", revision="A", submitted_by="John Smith")

# Review
tracker.review_submission("DOC-0001", approved=True, reviewer="PM", comments="Approved")

Common Use Cases

1. Status Summary

python
summary = tracker.get_summary()
print(f"Completion: {summary['completion_rate']}%")
print(f"Overdue: {summary['overdue']}")

2. Contractor Report

python
status = tracker.get_contractor_status("ABC Architects")
print(f"Pending: {status['pending']}")

3. Forecast

python
forecast = tracker.forecast_completion()
print(f"On Track: {forecast['on_track']}")

Resources

  • DDC Book: Chapter 5.1 - Documentation Management

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the As Built Tracker AI skill do?

Track as-built documentation and record drawings. Monitor submission status, manage revisions, and ensure completeness for handover.

Why use As Built Tracker on TypingMind?

Because you install it once and use it with any model. As Built Tracker is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install As Built Tracker in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction/tree/main/1_DDC_Toolkit/Closeout/as-built-tracker. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use As Built Tracker?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with As Built Tracker?

As many as you like. As long as a model supports skills, you can use As Built Tracker with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the As Built Tracker AI skill free?

Yes. It is published on GitHub by datadrivenconstruction under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇