pdf-report-generator

pdf-report-generator is a skill for Claude Code, Codex from datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction. It costs 21 tokens per session (3,714 once invoked), scanned A, original, MIT.

A tool for creating formatted PDF reports from construction project data. It can organize text, tables, charts, key metrics, and images into report sections.

In plain words
What is it for?
Use it for progress, cost, safety, quality, executive, weekly, or monthly construction reports.
Why use it?
It reduces the manual work and inconsistent formatting involved in producing recurring project reports.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it for progress, cost, safety, quality, executive, weekly, or monthly construction reports.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/pdf-report-generator
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill pdf-report-generator
Clone the repo
git clone --depth 1 https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pdf-report-generator

README.md
[![agentmods](https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/pdf-report-generator/github.svg)](https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/pdf-report-generator)
Your own site
<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/pdf-report-generator"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/pdf-report-generator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pdf-report-generator

Your own site · 80×15
<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/pdf-report-generator"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/pdf-report-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,714 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00021 $0.03714
Opus 5 $0.00010 $0.01857
Sonnet 5 $0.00004 $0.00743
Haiku 4.5 $0.00002 $0.00371

Measured 8d ago against content hash 2be22e11fcaf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pdf-report-generator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

2_DDC_Book/4.2-ETL-Automation/pdf-report-generator/SKILL.md · 466 lines

How it starts

The opening of the file, as written. The whole thing — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PDF Report Generator

Business Case

Problem Statement

Report generation challenges:

  • Manual report creation is time-consuming
  • Inconsistent formatting
  • Data aggregation from multiple sources
  • Repetitive weekly/monthly reports

Solution

Automated PDF report generation from project data with templates, charts, and customizable sections.

Technical Implementation

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


class ReportType(Enum):
    PROGRESS = "progress"
    COST = "cost"
    SAFETY = "safety"
    QUALITY = "quality"
    EXECUTIVE = "executive"
    WEEKLY = "weekly"
    MONTHLY = "monthly"


class SectionType(Enum):
    HEADER = "header"
    TEXT = "text"
    TABLE = "table"
    CHART = "chart"
    KPI_CARDS = "kpi_cards"
    IMAGE = "image"
    PAGE_BREAK = "page_break"


@dataclass
class ReportSection:
    section_type: SectionType
    title: str = ""
    content: Any = None
    style: Dict[str, Any] = field(default_factory=dict)


@dataclass
class KPICard:
    name: str
    value: Any
    unit: str = ""
    target: Any = None
    status: str = "normal"  # normal, warning, critical, good


@dataclass
class ChartConfig:
    chart_type: str  # bar, line, pie
    data: Dict[str, List]
    title: str = ""
    x_label: str = ""
    y_label: str = ""


class PDFReportGenerator:
    """Generate PDF reports from construction project data."""

    def __init__(self, project_name: str, report_type: ReportType):
        self.project_name = project_name
        self.report_type = report_type
        self.sections: List[ReportSection] = []
        self.metadata: Dict[str, Any] = {
            'author': '',
            'date': date.today(),
            'version': '1.0'
        }

    def set_metadata(self, author: str = "", report_date: date = None, version: str = "1.0"):
        """Set report metadata."""
        self.metadata['author'] = author
        self.metadata['date'] = report_date or date.today()
        self.metadata['version'] = version

    def add_header(self, title: str, subtitle: str = ""):
        """Add report header section."""
        self.sections.append(ReportSection(
            section_type=SectionType.HEADER,
            title=title,
            content={'subtitle': subtitle, 'date': self.metadata['date'].isoformat()}
        ))

    def add_text(self, title: str, content: str):
        """Add text section."""
        self.sections.append(ReportSection(
            section_type=SectionType.TEXT,
            title=title,
            content=content
        ))

    def add_table(self, title: str, df: pd.DataFrame, style: Dict[str, Any] = None):
        """Add table section from DataFrame."""
        self.sections.append(ReportSection(
            section_type=SectionType.TABLE,
            title=title,
            content=df.to_dict('records'),
            style=style or {}
        ))

    def add_kpi_cards(self, title: str, kpis: List[KPICard]):
        """Add KPI cards section."""
        self.sections.append(ReportSection(
            section_type=SectionType.KPI_CARDS,
            title=title,
            content=[{
                'name': k.name,
                'value': k.value,
                'unit': k.unit,
                'target': k.target,
                'status': k.status
            } for k in kpis]
        ))

    def add_chart(self, title: str, chart_config: ChartConfig):
        """Add chart section."""
        self.sections.append(ReportSection(
            section_type=SectionType.CHART,
            title=title,
            content={
                'type': chart_config.chart_type,
                'data': chart_config.data,
                'x_label': chart_config.x_label,
                'y_label': chart_config.y_label
            }
        ))

    def add_page_break(self):
        """Add page break."""
        self.sections.append(ReportSection(section_type=SectionType.PAGE_BREAK))

    def generate_progress_report(self, data: Dict[str, Any]):
        """Generate standard progress report."""

        self.add_header(
            f"{self.project_name} - Progress Report",
            f"Report Date: {self.metadata['date']}"
        )

        # KPIs
        kpis = [
            KPICard("Overall Progress", f"{data.get('overall_progress', 0)}%", target="100%",
                   status="good" if data.get('overall_progress', 0) >= data.get('planned_progress', 0) else "warning"),
            KPICard("SPI", f"{data.get('spi', 1.0):.2f}", target="1.00",
                   status="good" if data.get('spi', 1) >= 0.95 else "critical"),
            KPICard("CPI", f"{data.get('cpi', 1.0):.2f}", target="1.00",
                   status="good" if data.get('cpi', 1) >= 0.95 else "critical"),
            KPICard("Days Remaining", str(data.get('days_remaining', 0)), "days")
        ]
        self.add_kpi_cards("Key Performance Indicators", kpis)

        # Progress summary
        self.add_text("Executive Summary", data.get('summary', 'No summary provided.'))

        # Activities table
        if 'activities' in data:
            activities_df = pd.DataFrame(data['activities'])
            self.add_table("Activity Status", activities_df)

        # Progress chart
        if 'progress_history' in data:
            self.add_chart("Progress Trend", ChartConfig(
                chart_type="line",
                data=data['progress_history'],
                title="Progress Over Time",
                x_label="Date",
                y_label="Progress %"
            ))

        # Issues
        if 'issues' in data:
            self.add_text("Current Issues", "\n".join(f"- {issue}" for issue in data['issues']))

    def generate_cost_report(self, data: Dict[str, Any]):
        """Generate cost report."""

        self.add_header(
            f"{self.project_name} - Cost Report",
            f"Period: {data.get('period', 'Current')}"
        )

        # Cost KPIs
        budget = data.get('budget', 0)
        actual = data.get('actual_cost', 0)
        variance = budget - actual

        kpis = [
            KPICard("Budget", f"${budget:,.0f}"),
            KPICard("Actual Cost", f"${actual:,.0f}"),
            KPICard("Variance", f"${variance:,.0f}",
                   status="good" if variance >= 0 else "critical"),
            KPICard("CPI", f"{data.get('cpi', 1.0):.2f}",
                   status="good" if data.get('cpi', 1) >= 0.95 else "warning")
        ]
        self.add_kpi_cards("Cost Summary", kpis)

        # Cost breakdown
        if 'cost_breakdown' in data:
            breakdown_df = pd.DataFrame(data['cost_breakdown'])
            self.add_table("Cost Breakdown by Category", breakdown_df)

        # Cost trend
        if 'cost_history' in data:
            self.add_chart("Cost Trend", ChartConfig(
                chart_type="bar",
                data=data['cost_history'],
                title="Monthly Cost",
                x_label="Month",
                y_label="Cost ($)"
            ))

    def generate_safety_report(self, data: Dict[str, Any]):
        """Generate safety report."""

        self.add_header(
            f"{self.project_name} - Safety Report",
            f"Period: {data.get('period', 'Current')}"
        )

        # Safety KPIs
        kpis = [
            KPICard("Days Without Incident", str(data.get('days_without_incident', 0)), "days"),
            KPICard("TRIR", f"{data.get('trir', 0):.2f}",
                   status="good" if data.get('trir', 0) <= 2 else "critical"),
            KPICard("Near Misses", str(data.get('near_misses', 0))),
            KPICard("Safety Observations", str(data.get('observations', 0)))
        ]
        self.add_kpi_cards("Safety Metrics", kpis)

        # Incidents
        if 'incidents' in data and data['incidents']:
            incidents_df = pd.DataFrame(data['incidents'])
            self.add_table("Incident Log", incidents_df)

        # Training
        if 'training' in data:
            self.add_text("Training Summary", data['training'])

    def to_html(self) -> str:
        """Generate HTML representation of report."""

        html = f"""
<!DOCTYPE html>
<html>
<head>
    <title>{self.project_name} Report</title>
    <style>
        body {{ font-family: Arial, sans-serif; margin: 40px; }}
        .header {{ background: #2196F3; color: white; padding: 20px; margin-bottom: 20px; }}
        .section {{ margin-bottom: 30px; }}
        .section-title {{ color: #333; border-bottom: 2px solid #2196F3; padding-bottom: 5px; }}
        .kpi-grid {{ display: grid; grid-template-columns: repeat(4, 1fr); gap: 15px; }}
        .kpi-card {{ border: 1px solid #ddd; padding: 15px; border-radius: 5px; text-align: center; }}
        .kpi-value {{ font-size: 24px; font-weight: bold; }}
        .kpi-name {{ color: #666; }}
        .status-good {{ border-left: 4px solid #4CAF50; }}
        .status-warning {{ border-left: 4px solid #FF9800; }}
        .status-critical {{ border-left: 4px solid #F44336; }}
        table {{ width: 100%; border-collapse: collapse; }}
        th, td {{ border: 1px solid #ddd; padding: 8px; text-align: left; }}
        th {{ background: #f5f5f5; }}
        .page-break {{ page-break-after: always; }}
    </style>
</head>
<body>
"""

        for section in self.sections:
            if section.section_type == SectionType.HEADER:
                html += f"""
    <div class="header">
        <h1>{section.title}</h1>
        <p>{section.content.get('subtitle', '')}</p>
    </div>
"""
            elif section.section_type == SectionType.TEXT:
                html += f"""
    <div class="section">
        <h2 class="section-title">{section.title}</h2>
        <p>{section.content}</p>
    </div>
"""
            elif section.section_type == SectionType.KPI_CARDS:
                html += f"""
    <div class="section">
        <h2 class="section-title">{section.title}</h2>
        <div class="kpi-grid">
"""
                for kpi in section.content:
                    status_class = f"status-{kpi['status']}" if kpi['status'] != 'normal' else ''
                    html += f"""
            <div class="kpi-card {status_class}">
                <div class="kpi-name">{kpi['name']}</div>
                <div class="kpi-value">{kpi['value']}</div>
                <div class="kpi-target">Target: {kpi['target'] or 'N/A'}</div>
            </div>
"""
                html += "</div></div>"

            elif section.section_type == SectionType.TABLE:
                html += f"""
    <div class="section">
        <h2 class="section-title">{section.title}</h2>
        <table>
            <tr>
"""
                if section.content:
                    for key in section.content[0].keys():
                        html += f"<th>{key}</th>"
                    html += "</tr>"

                    for row in section.content:
                        html += "<tr>"
                        for value in row.values():
                            html += f"<td>{value}</td>"
                        html += "</tr>"

                html += "</table></div>"

            elif section.section_type == SectionType.PAGE_BREAK:
                html += '<div class="page-break"></div>'

        html += "</body></html>"
        return html

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

        with pd.ExcelWriter(output_path, engine='openpyxl') as writer:
            # Metadata
            meta_df = pd.DataFrame([{
                'Project': self.project_name,
                'Report Type': self.report_type.value,
                'Date': self.metadata['date'],
                'Author': self.metadata['author'],
                'Version': self.metadata['version']
            }])
            meta_df.to_excel(writer, sheet_name='Metadata', index=False)

            # Each section
            table_count = 0
            for section in self.sections:
                if section.section_type == SectionType.TABLE:
                    table_count += 1
                    sheet_name = section.title[:31] if section.title else f"Table_{table_count}"
                    df = pd.DataFrame(section.content)
                    df.to_excel(writer, sheet_name=sheet_name, index=False)

                elif section.section_type == SectionType.KPI_CARDS:
                    kpi_df = pd.DataFrame(section.content)
                    kpi_df.to_excel(writer, sheet_name='KPIs', index=False)

        return output_path

    def get_report_structure(self) -> Dict[str, Any]:
        """Get report structure as dictionary."""

        return {
            'project': self.project_name,
            'type': self.report_type.value,
            'metadata': self.metadata,
            'sections': [
                {
                    'type': s.section_type.value,
                    'title': s.title,
                    'content': s.content
                }
                for s in self.sections
            ]
        }

Read the full file on GitHub · 466 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 466 lines · 21 tokens per session scan A 2be22e11fcaf

Subscribe to this mod's changes

pdf-report-generator is a skill published in the GitHub repository datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction (310 stars, last pushed 20d ago), licensed MIT. It adds 21 tokens to every session and 3,714 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

google-apps-script

Build Google Apps Script automation for Sheets and Workspace. Custom menus, triggers (onEdit / time-driven / form submit), dialogs, sidebars, email batches, PDF export, external API. Use whenever the user wants to automate a Google Sheet, build a Sheets menu / sidebar / dialog, hit a Sheets row from email or a…

jezweb/claude-skills · 89 tokens

cli-anything-wps

A command-line tool that controls WPS Office on Windows, including Writer, Calc, and Impress. It can also build presentations from structured JSON data and export them as PowerPoint and PDF files.

yb2460/harness-anything · 37 tokens

anydoc

Convert Word (.doc/.docx/.docm), PowerPoint (.ppt/.pps/.pot/.pptx/.pptm/.ppsx/.ppsm), Excel (.xls/.xlsx/.xlsm/.xlsb), OpenDocument (.odt/.ods/.odp), RTF, EPUB, CSV, and PDF documents to clean GitHub-Flavored Markdown locally with the Any Doc CLI (npx -y @firecrawl/[email protected]): headings, GFM tables, slide structure…

magnus919/agent-skills · 189 tokens

documents

Generate, inspect, validate, and fix PDF, Word (.docx), Excel (.xlsx), and PowerPoint (.pptx) documents: turn structured content into render-ready artifacts, verify structural and output quality before delivery, and repair broken files. Use when a task involves creating, editing, converting, or validating office…

magnus919/agent-skills · 105 tokens

antinet-doc-parse

A document-processing skill for building RAG systems, which let an AI search a knowledge base before answering. It handles complex PDF, Word, and Excel files and produces structured Markdown and metadata.

anbeime/skill · 79 tokens

ag-5-documentos

Documentacao: Office (PPTX/DOCX/XLSX/PDF), README, API, diagramas, specs, changelog, data dictionary e CSV; executive para decks.

andregusman-raiz/a-gusman-claude · 44 tokens