mcpbeat Sign in

As Built Documentation Agent Skill

Manage as-built documentation for project closeout. Track drawing markups, coordinate updates, and verify completeness.

2k tokens
context cost
the whole folder, loaded on every use
3
files
instructions only
0
copies elsewhere
how many repositories repackaged it
264
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill as-built-documentation

The instruction itself

7 sections, as written by the author

As-Built Documentation Manager

Business Case

Problem Statement

As-built documentation is often incomplete:

  • Field changes not documented
  • Drawings not updated consistently
  • Missing documentation at closeout
  • Difficult to verify completeness

Solution

Systematic as-built documentation tracking with drawing markup management, completeness verification, and handover preparation.

Technical Implementation

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


class DocumentType(Enum):
    DRAWING = "drawing"
    SPECIFICATION = "specification"
    SUBMITTAL = "submittal"
    MANUAL = "manual"
    WARRANTY = "warranty"
    CERTIFICATE = "certificate"


class MarkupStatus(Enum):
    PENDING = "pending"
    IN_REVIEW = "in_review"
    APPROVED = "approved"
    INCORPORATED = "incorporated"


class DocumentStatus(Enum):
    DRAFT = "draft"
    UNDER_REVIEW = "under_review"
    APPROVED = "approved"
    FINAL = "final"


@dataclass
class Markup:
    markup_id: str
    description: str
    location: str
    marked_by: str
    marked_date: date
    status: MarkupStatus
    cloud_reference: str = ""
    notes: str = ""


@dataclass
class AsBuiltDocument:
    document_id: str
    document_number: str
    title: str
    document_type: DocumentType
    discipline: str
    revision: str
    status: DocumentStatus
    original_file: str
    as_built_file: str
    markups: List[Markup] = field(default_factory=list)
    last_updated: Optional[date] = None
    verified_by: str = ""
    verified_date: Optional[date] = None

    @property
    def is_complete(self) -> bool:
        return self.status == DocumentStatus.FINAL and all(
            m.status == MarkupStatus.INCORPORATED for m in self.markups
        )


class AsBuiltDocumentManager:
    """Manage as-built documentation."""

    def __init__(self, project_name: str):
        self.project_name = project_name
        self.documents: Dict[str, AsBuiltDocument] = {}
        self._markup_counter = 0

    def register_document(self, document_number: str, title: str,
                         document_type: DocumentType, discipline: str,
                         original_file: str, revision: str = "0") -> AsBuiltDocument:
        doc_id = f"DOC-{len(self.documents) + 1:04d}"

        doc = AsBuiltDocument(
            document_id=doc_id,
            document_number=document_number,
            title=title,
            document_type=document_type,
            discipline=discipline,
            revision=revision,
            status=DocumentStatus.DRAFT,
            original_file=original_file,
            as_built_file=""
        )
        self.documents[doc_id] = doc
        return doc

    def add_markup(self, doc_id: str, description: str, location: str,
                  marked_by: str, cloud_reference: str = "") -> Markup:
        if doc_id not in self.documents:
            raise ValueError(f"Document {doc_id} not found")

        self._markup_counter += 1
        markup = Markup(
            markup_id=f"MKP-{self._markup_counter:05d}",
            description=description,
            location=location,
            marked_by=marked_by,
            marked_date=date.today(),
            status=MarkupStatus.PENDING,
            cloud_reference=cloud_reference
        )
        self.documents[doc_id].markups.append(markup)
        return markup

    def update_markup_status(self, doc_id: str, markup_id: str, status: MarkupStatus):
        if doc_id in self.documents:
            for markup in self.documents[doc_id].markups:
                if markup.markup_id == markup_id:
                    markup.status = status
                    break

    def upload_as_built(self, doc_id: str, file_path: str, new_revision: str = None):
        if doc_id not in self.documents:
            return
        doc = self.documents[doc_id]
        doc.as_built_file = file_path
        doc.last_updated = date.today()
        if new_revision:
            doc.revision = new_revision
        doc.status = DocumentStatus.UNDER_REVIEW

    def verify_document(self, doc_id: str, verified_by: str):
        if doc_id not in self.documents:
            return
        doc = self.documents[doc_id]
        doc.verified_by = verified_by
        doc.verified_date = date.today()
        doc.status = DocumentStatus.FINAL

    def get_completeness_report(self) -> Dict[str, Any]:
        total = len(self.documents)
        complete = sum(1 for d in self.documents.values() if d.is_complete)
        pending_markups = sum(
            len([m for m in d.markups if m.status != MarkupStatus.INCORPORATED])
            for d in self.documents.values()
        )

        by_discipline = {}
        for doc in self.documents.values():
            if doc.discipline not in by_discipline:
                by_discipline[doc.discipline] = {'total': 0, 'complete': 0}
            by_discipline[doc.discipline]['total'] += 1
            if doc.is_complete:
                by_discipline[doc.discipline]['complete'] += 1

        return {
            'project': self.project_name,
            'total_documents': total,
            'complete': complete,
            'completion_percent': round(complete / total * 100, 1) if total > 0 else 0,
            'pending_markups': pending_markups,
            'by_discipline': by_discipline
        }

    def get_incomplete_documents(self) -> List[AsBuiltDocument]:
        return [d for d in self.documents.values() if not d.is_complete]

    def export_register(self, output_path: str):
        with pd.ExcelWriter(output_path, engine='openpyxl') as writer:
            # Document register
            doc_data = [{
                'ID': d.document_id,
                'Number': d.document_number,
                'Title': d.title,
                'Type': d.document_type.value,
                'Discipline': d.discipline,
                'Revision': d.revision,
                'Status': d.status.value,
                'Complete': d.is_complete,
                'Markups': len(d.markups),
                'Verified By': d.verified_by
            } for d in self.documents.values()]
            pd.DataFrame(doc_data).to_excel(writer, sheet_name='Register', index=False)

            # Markups
            markup_data = []
            for doc in self.documents.values():
                for m in doc.markups:
                    markup_data.append({
                        'Document': doc.document_number,
                        'Markup ID': m.markup_id,
                        'Description': m.description,
                        'Location': m.location,
                        'Marked By': m.marked_by,
                        'Status': m.status.value
                    })
            if markup_data:
                pd.DataFrame(markup_data).to_excel(writer, sheet_name='Markups', index=False)

        return output_path

Quick Start

manager = AsBuiltDocumentManager("Office Tower")

# Register document
doc = manager.register_document(
    document_number="A-101",
    title="Floor Plan Level 1",
    document_type=DocumentType.DRAWING,
    discipline="Architectural",
    original_file="drawings/A-101.pdf"
)

# Add field markup
markup = manager.add_markup(
    doc.document_id,
    description="Wall moved 6 inches south",
    location="Grid B-3",
    marked_by="Site Superintendent"
)

# Upload as-built
manager.upload_as_built(doc.document_id, "as-built/A-101-AB.pdf", "AB")

# Verify
manager.verify_document(doc.document_id, "Project Manager")

# Check completeness
report = manager.get_completeness_report()
print(f"Completion: {report['completion_percent']}%")

Resources

  • DDC Book: Chapter 5 - Project Closeout

Other skills for the same job

different authors, same section of the catalogue
Protocolsio Integration
by christophacham
×4

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.

16k tokens
Tailored Resume Generator
by frostant
×4

Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances

3k tokens
Excalidraw Diagram Generator
by github
vendor ×3

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.

36k tokens scripts
Expo Dev Client
by openai
vendor ×3

Build and distribute Expo development clients locally or via TestFlight

961 tokens
Executing Plans
by ZhanlinCui
×3

Use when you have a written implementation plan to execute in a separate session with review checkpoints

542 tokens
Anndata
by christophacham
×3

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.

16k tokens
Benchling Integration
by christophacham
×3

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.

14k tokens
Biopython
by christophacham
×3

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.

24k tokens

How to use it

Copy the folder

Take datadrivenconstruction/as-built-documentation from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

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.