restaurant-report-pdf

Restaurant PDF Report Generator

You compile all the markdown analyses produced by other /restaurant skills (RESTAURANT-AUDIT-.md, RESTAURANT-REVIEWS-.md, RESTAURANT-MENU-*.md, etc.) in the current working directory into a single polished, client-ready PDF report using the bundled ReportLab Python script.

DISCLAIMER: AI-generated report. Owner should review before sending to clients.

---

When to use

• /restaurant report-pdf — generate PDF from existing markdown analyses
• "make a PDF of the restaurant audit"
• "client-ready report for [name]"

---

Execution Pipeline

Step 1: Scan Current Directory

List all RESTAURANT-*.md files in the cwd:

ls RESTAURANT-*.md

Recognize these files:

• RESTAURANT-AUDIT-[Name].md — main audit (highest priority)
• RESTAURANT-REVIEWS-[Name].md
• RESTAURANT-MENU-[Name].md
• RESTAURANT-PRICING-[Name].md
• RESTAURANT-ONLINE-[Name].md
• RESTAURANT-PHOTOS-[Name].md
• RESTAURANT-SOCIAL-[Name].md
• RESTAURANT-SEO-[Name].md
• RESTAURANT-ADS-[Name].md
• RESTAURANT-EMAIL-[Name].md
• RESTAURANT-COMPETITORS-[Name].md
• RESTAURANT-RESPONSES-[Name].md

Step 2: Extract Key Data

From each markdown file, extract:

• Restaurant name (from filename or top-of-file)
• Date
• Score (if applicable)
• Top findings
• Top recommendations
• Tables of data

Assemble into a single JSON payload like:

{
  "restaurant_name": "Bella Italia Trattoria",
  "city": "Austin, TX",
  "cuisine": "Italian",
  "date": "2026-05-20",
  "overall_score": 64,
  "categories": {
    "Reviews & Reputation": {"score": 68, "weight": "25%"},
    "Menu & Pricing": {"score": 72, "weight": "20%"},
    "Online Presence": {"score": 55, "weight": "20%"},
    "Marketing & Engagement": {"score": 48, "weight": "15%"},
    "Local Competition": {"score": 70, "weight": "20%"}
  },
  "reviews": {...},
  "menu": {...},
  "online": {...},
  "competitors": [...],
  "action_plan": [...]
}

Step 3: Write Temp JSON

Save extracted data to /tmp/restaurant_data.json.