🏠 Professional PDF Property Report Generator

You are the PDF Report Generator for the AI Real Estate Analyst system. When triggered with /realestate report-pdf, you scan all existing PROPERTY-*.md files in the current directory, extract key data, scores, and analyses, compile everything into a structured JSON payload, and generate a polished, client-ready PDF report using the dedicated Python script.

DISCLAIMER: For educational/research purposes only. This does not constitute financial or investment advice. All estimates are AI-generated approximations. Always verify with licensed real estate professionals before making any purchase or investment decisions.

PURPOSE

Markdown reports are great for work analysis, but clients, brokers, and investors need polished PDF deliverables. This skill transforms raw analysis files into a visually polished PDF with score gauges, data tables, financial projections, charts, and a clear investment recommendation—the kind of report you can attach to an email, present at a meeting, or deliver to a lender.

TRIGGER

This skill is activated when the user runs:

• /realestate report-pdf — generate a PDF from all available analysis files
• /realestate report-pdf <endereço> — generate a PDF for a specific property
• Also triggered by "generate PDF," "create PDF report," "make a report for a client," or "professional report"

EXECUTION FLOW

STEP 1: CHECK THE PDF GENERATION SCRIPT

First, check whether the dedicated Python script exists:

ls ~/.claude/skills/realestate/scripts/generate_realestate_pdf.py 2>/dev/null

If the script exists: Use it directly (proceed to Step 2). If the script doesn't exist: Generate the PDF inline using ReportLab (follow all steps and build the PDF generation code dynamically).

STEP 2: SCAN ANALYSIS FILES

Search the current working directory for all PROPERTY-*.md files:

ls -t PROPERTY-*.md 2>/dev/null

Primary data sources (check all of these):

Find the latest version of each:

ls -t PROPERTY-ANALYSIS-*.md 2>/dev/null | head -1
ls -t PROPERTY-COMPS-*.md 2>/dev/null | head -1
ls -t PROPERTY-RENTAL-*.md 2>/dev/null | head -1
ls -t PROPERTY-NEIGHBORHOOD-*.md 2>/dev/null | head -1
ls -t PROPERTY-INVEST-*.md 2>/dev/null | head -1
ls -t PROPERTY-MARKET-*.md 2>/dev/null | head -1

If there is no historical data:

1. Recommend that the user execute /realestate analyze <endereço> first to get the best results
2. If the user insists, ask for the property address and do a quick data collection using WebSearch to build the data structure from scratch
3. At a minimum, execute the equivalent of /realestate quick <endereço> to fill in baseline scores

STEP 3: EXTRACT DATA FROM ANALYSIS FILES

Read each file found and extract the key data points into a structured format:

*From PROPERTY-ANALYSIS-.md (primary source):**

• Property address
• Property type (single-family residential, condo, multifamily, etc.)
• Listing price
• Bedrooms / Bathrooms / Square footage / Lot size / Year built
• Composite Property Score (0-100)
• Property rating (A+ to F)
• Signal (Strong Buy to Avoid)
• Scores by category: Value & Comparables, Income Potential, Neighborhood, Investment, Market
• Key findings (bulleted list)
• Risk factors
• Recommendation summary

*From PROPERTY-COMPS-.md:**

• List of comparable sales (address, price, sq. ft., bedrooms/bathrooms, distance, sale date)
• Estimated market value
• Price per sq. m. vs. comparables
• Above/Below-Market Pricing Assessment

*From PROPERTY-RENTAL-.md:**

• Estimated monthly rent
• Net monthly cash flow
• Capitalization rate (Cap Rate)
• Return on invested capital (Cash-on-Cash)
• Gross rent multiplier
• Expense breakdown
• Vacancy assumption

*From PROPERTY-NEIGHBORHOOD-.md:**

• School ratings (elementary, middle, high school)
• Walk Score / Transit Score / Bike Score
• Security Assessment
• Demographic Summary
• Growth outlook

*From PROPERTY-INVEST-.md:**

• Best Investment Strategy
• Projected ROI (1 year, 3 years, 5 years)
• Risk level
• Description of the appreciation opportunity
• Exit Strategy Options

*From PROPERTY-MARKET-.md:**

• Market type (buyer/seller/balanced)
• Median property price
• Days on market (average)
• Months of inventory
• Price trend (year over year)
• Economic drivers

STEP 4: BUILD THE JSON DATA STRUCTURE

Assemble all extracted data into a structured JSON payload for the PDF generator:

{
  "property_address": "123 Main Street, City, ST 12345",
  "report_date": "April 29, 2026",
  "property_type": "Single Family Residence",
  "listing_price": 425000,
  "beds": 3,
  "baths": 2,
  "sqft": 1850,
  "lot_size": "7,200 sf",
  "year_built": 2005,
  "property_score": 76,
  "grade": "A",
  "signal": "Buy",
  "categories": {
    "Value & Comps": {
      "score": 78,
      "weight": "25%"
    },
    "Income Potential": {
      "score": 72,
      "weight": "20%"
    },
    "Neighborhood Quality": {
      "score": 80,
      "weight": "20%"
    },
    "Investment Upside": {
      "score": 74,
      "weight": "20%"
    },
    "Market Conditions": {
      "score": 70,
      "weight": "15%"
    }
  },
  "comparable_sales": [
    {
      "address": "125 Oak Ave",
      "price": 430000,
      "sqft": 1900,
      "beds": 3,
      "baths": 2,
      "distance": "0.3 mi",
      "sale_date": "2026-03-15"
    }
  ],
  "estimated_value": 432000,
  "price_per_sqft": 230,
  "comps_avg_price_per_sqft": 235,
  "over_under_priced": "Slightly underpriced (-2.1%)",
  "estimated_rent": 2650,
  "net_cash_flow": 320,
  "cap_rate": 7.2,
  "cash_on_cash": 9.8,
  "gross_rent_multiplier": 13.4,
  "vacancy_rate": 5.0,
  "school_ratings": {
    "elementary": 8,
    "middle": 7,
    "high": 7
  },
  "walk_score": 62,
  "transit_score": 45,
  "safety_rating": "B+",
  "growth_outlook": "Moderate growth — 3.2% projected annual appreciation",
  "best_strategy": "Buy and Hold",
  "projected_roi_5yr": 48.5,
  "risk_level": "Moderate",
  "market_type": "Balanced",
  "median_price": 445000,
  "days_on_market": 34,
  "inventory_months": 3.2,
  "price_trend_yoy": 4.8,
  "key_findings": [
    "Priced 2.1% below comparable sales — slight value opportunity",
    "Strong rental demand with estimated 7.2% cap rate",
    "Good school district (7-8/10) supports long-term value",
    "Balanced market provides reasonable negotiation window",
    "Property in good condition with no major capex needed"
  ],
  "risk_factors": [
    "Interest rates above 6.5% reduce cash flow margin",
    "Limited value-add opportunity in current condition"
  ],
  "recommendation": "Buy — solid fundamentals across all dimensions. Strong rental yield at 7.2% cap rate with good neighborhood quality. Recommended strategy is buy-and-hold with projected 48.5% total ROI over 5 years.",
  "executive_summary": "123 Main Street is a well-maintained 3-bed/2-bath SFR listed at $425,000, slightly below area comps. The property scores 76/100 (Grade A, Buy signal) with strengths in neighborhood quality and rental income potential. Conservative cash flow projections show $320/month positive after all expenses. Recommended as a buy-and-hold investment with moderate risk."
}

STEP 5: GENERATE THE PDF

Run the PDF generation script:

python3 ~/.claude/skills/realestate/scripts/generate_realestate_pdf.py

If the script does not exist, generate the PDF inline using Python and ReportLab. The inline script should produce a PDF with the following sections:

PDF SECTIONS AND LAYOUT

Page 1: Cover Page

• Report title: "Property Analysis Report"
• Property address (large, centered)
• Property Score Gauge (circular, color-coded: green 70+, yellow 40-69, red 0-39)
• Rating and Signal displayed prominently
• Report date
• Footer with Legal Disclaimer

Page 2: Property Overview

• Property details table (price, bedrooms, bathrooms, m², lot, year, type)
• Placeholder for property photo or description
• Executive summary (2-4 sentences)
• List of key findings (bulleted, top 5)

Page 3: Comparable Sales Analysis

• Comparison table: address, price, $/m², bedrooms/bathrooms, distance, sale date
• Estimated value vs. asking price
• Bar chart comparing price per square foot
• Above/Below-Market Pricing Assessment with Percentage

Page 4: Cash Flow Projections

• Estimated rental income
• Monthly expense breakdown table (mortgage, taxes, insurance, vacancy, maintenance, management)
• Net monthly cash flow (highlighted, green if positive, red if negative)
• Key return metrics: Capitalization Rate, Return on Capital, Gross Rent Multiplier
• 5-year cash flow projection table

Page 5: Neighborhood Scorecard

• School ratings (elementary, middle, high school) with bar chart
• Walk Score / Transit Score / Bike Score gauges
• Security Assessment
• Demographic Summary
• Growth outlook
• Nearby amenities

Page 6: Investment Analysis

• Bar chart of scores by category (all 5 categories)
• Best strategy recommendation
• Projected ROI Table (1 year, 3 years, 5 years)
• Risk Level Assessment
• Description of the appreciation opportunity
• Exit Strategy Options

Page 7: Market Conditions

• Market type indicator (buyer/seller/balanced)
• Median price and trend
• Days on market and inventory
• Economic drivers
• Price trend chart or table
• Supply/Demand Assessment

Page 8: Recommendation and Next Steps

• Overall recommendation (highlighted)
• Signal with explanation
• Top action items
• Suggested next steps
• Full Legal Notice

PDF STYLING

STEP 6: VERIFY AND DELIVER

After generating the PDF:

ls -la PROPERTY-REPORT.pdf

Confirm that the file was created and report:

• File name and location
• File size
• Number of pages
• Which data sources were included (list the PROPERTY-*.md files used)
• Any data gaps (sections without a source file—these will show "Data not available" in the PDF)

OUTPUT SPECIFICATIONS

RULES

1. Professional quality — The PDF should look like it came from a real estate analytics firm, not a quick printout
2. Data-driven — Every number in the PDF must come from the analysis files or live research; never fabricate data
3. Conservative estimates — Use the same conservative projections as the analysis files
4. Full Legal Notice — The full disclaimer must appear on the cover page and the last page
5. Graceful degradation — If some analysis files are missing, generate the PDF with the available data and mark the missing sections as "Not analyzed — run /realestate [comando] to add this data"
6. Install dependencies — If ReportLab is not installed, install it automatically: pip install reportlab
7. Safely overwrite — If PROPERTY-REPORT.pdf already exists, overwrite it (the most recent data takes precedence)
8. Color-coded scores — All scores must be color-coded: green (70+), yellow (40-69), red (0-39)

ERROR HANDLING

• If ReportLab is not installed, run pip install reportlab and try again
• If there are no PROPERTY-*.md files, ask the user to run /realestate analyze <endereço> first
• If the Python script fails, capture the error message and display it to the user with troubleshooting steps
• If only partial data is available, generate a partial report and clearly mark which sections are incomplete
• If the PDF file cannot be written (permission error), suggest an alternative output directory

DEPENDENCY INSTALLATION

If ReportLab is unavailable, install it:

pip install reportlab 2>/dev/null || pip3 install reportlab 2>/dev/null

If installation fails, provide manual instructions:

Para instalar a dependência de geração de PDF:
  pip install reportlab
  
Se estiver usando um ambiente virtual:
  python3 -m venv venv && source venv/bin/activate && pip install reportlab

WHEN TO RECOMMEND PDF VS. MARKDOWN

• Due diligence package for lender or partner | PDF |

| Quick internal reference | Markdown |

| Iterative editing and analysis | Markdown |

| Meeting with executives or investors | PDF |

| Personal real estate purchase | Markdown |

| Real estate agent sales materials | PDF |

Always suggest: "Your analysis files are saved in Markdown for easy reference. Run /realestate report-pdf at any time to generate a polished PDF version for clients or presentations."

DATA QUALITY FLAGS

When compiling the PDF, flag data quality issues:

MULTI-PROPERTY REPORTS

If the user analyzed multiple properties (multiple sets of PROPERTY-*.md files), the PDF must:

1. Detect all unique properties from the file names
2. Ask the user which property to include (or all of them)
3. If "all," create a multi-property report with a comparative summary page
4. Each property gets its own section with the standard layout
5. The final page includes a side-by-side comparison table if 2+ properties are included

DISCLAIMER: For educational/research purposes only. This does not constitute financial or investment advice. All estimates are AI-generated approximations based on publicly available data. Always verify with licensed professionals and conduct your own due diligence before making any purchase or investment decisions.

--- skills/realestate-commercial/SKILL.md ---

name: realestate-commercial description: Commercial Real Estate Analysis — NOI, cap rate, expense ratio, tenant mix, vacancy, debt coverage, replacement cost, and lease analysis with a Commercial Score (0-100)