/sales-report-pdf

Professional Sales Report PDF Generator

Metadata

• **Title:** Professional Sales Report PDF Generator
• **Invocation:** `/sales report-pdf`
• **Input:** None (reads SALES-REPORT.md and prospect files from current directory)
• **Output:** `SALES-REPORT-{YYYY-MM-DD}.pdf` written to the current working directory
• **Dependencies:** Python 3, `reportlab` library, `scripts/generate_pdf_report.py`

---

Purpose

You generate a professional, visually polished PDF version of the sales pipeline report. The PDF is designed for sharing with sales leadership, investors, or team members who need a clean, portable document rather than a markdown file. It includes charts, formatted tables, color-coded scores, and a professional layout.

---

Instructions

When the user invokes `/sales report-pdf`, follow this process:

Step 1: Verify Prerequisites

Check that `SALES-REPORT.md` exists in the current working directory.

**If SALES-REPORT.md does NOT exist:**

• Inform the user: "No SALES-REPORT.md found. Run `/sales report` first to generate the pipeline report, then run `/sales report-pdf` to create the PDF version."
• Stop execution.

**If SALES-REPORT.md exists:**

• Read its contents
• Also scan for individual prospect analysis files (`**/PROSPECT-ANALYSIS.md`, `**/COMPANY-RESEARCH.md`, etc.) to enrich the PDF with additional detail

Step 2: Check for reportlab

Verify that the `reportlab` Python library is available by running:

python3 -c "import reportlab; print(reportlab.Version)"

**If reportlab is NOT installed:**

• Inform the user: "The `reportlab` Python library is required for PDF generation. Install it with: `pip install reportlab`"
• Offer to run the install command for them: `pip install reportlab`
• After installation, continue with PDF generation

**If Python 3 is NOT available:**

• Inform the user: "Python 3 is required for PDF generation. Please install Python 3 and the reportlab library."
• Stop execution.

Step 3: Parse Report Data

Extract the following data from `SALES-REPORT.md` and any prospect analysis files:

Pipeline Overview Data

• Report generation date
• Total number of prospects
• Average pipeline score (0-100)
• Overall pipeline health assessment

Prospect Data Array

For each prospect, extract into a structured object:

{
  "name": "Company Name",
  "url": "https://company.com",
  "score": 85,
  "grade": "A",
  "stage": "Qualified",
  "next_action": "Send intro email to VP Engineering",
  "est_value": "$24,000 ARR",
  "component_scores": {
    "company_fit": 88,
    "contact_access": 75,
    "opportunity_quality": 90,
    "competitive_position": 82,
    "outreach_readiness": 80
  },
  "key_pain_point": "Manual API monitoring causing outages",
  "key_contact": "Jane Smith, VP Engineering",
  "risk_factors": "Long procurement cycle"
}

Top Prospects Data

For the top 5 prospects, extract detailed data including:

• Full component score breakdown
• Key contacts with titles
• Pain points with severity
• Recommended approach
• Risk factors

Action Items

Extract the prioritized action list:

[
  {
    "priority": 1,
    "company": "Acme Corp",
    "action": "Send personalized email to VP Engineering",
    "urgency": "immediate",
    "reason": "Recent funding round creates budget window"
  }
]

Pipeline Health Metrics

{
  "total_prospects": 10,
  "average_score": 72,
  "a_grade_count": 3,
  "a_grade_pct": 30,
  "b_grade_count": 4,
  "b_grade_pct": 40,
  "c_grade_count": 2,
  "c_grade_pct": 20,
  "d_grade_count": 1,
  "d_grade_pct": 10,
  "highest_score": 92,
  "lowest_score": 35,
  "health_rating": "Good"
}

Step 4: Build JSON Input File

Write a JSON file at `_pdf_input.json` in the current working directory containing all extracted data:

{
  "title": "Sales Pipeline Report",
  "date": "2025-01-15",
  "overall_pipeline_score": 72,
  "health_rating": "Good",
  "total_prospects": 10,
  "prospects": [
    {
      "name": "...",
      "url": "...",
      "score": 85,
      "grade": "A",
      "stage": "Qualified",
      "next_action": "...",
      "est_value": "...",
      "component_scores": { ... },
      "key_pain_point": "...",
      "key_contact": "...",
      "risk_factors": "..."
    }
  ],
  "top_prospects": [ ... ],
  "action_items": [ ... ],
  "pipeline_health": { ... },
  "score_distribution": {
    "A+": { "count": 1, "pct": 10, "prospects": ["Acme Corp"] },
    "A": { "count": 2, "pct": 20, "prospects": ["Beta Inc", "Gamma Ltd"] },
    "B": { "count": 4, "pct": 40, "prospects": ["..."] },
    "C": { "count": 2, "pct": 20, "prospects": ["..."] },
    "D": { "count": 1, "pct": 10, "prospects": ["..."] }
  },
  "weekly_focus": [
    {
      "rank": 1,
      "company": "Acme Corp",
      "score": 92,
      "reason": "Highest score with active trigger event",
      "actions": ["Send intro email", "Connect on LinkedIn", "Schedule demo"]
    }
  ],
  "methodology": {
    "company_fit_weight": 25,
    "contact_access_weight": 20,
    "opportunity_quality_weight": 20,
    "competitive_position_weight": 15,
    "outreach_readiness_weight": 20
  }
}

Step 5: Locate or Create the PDF Generation Script

Check if the PDF generation script exists at `scripts/generate_pdf_report.py` relative to the project root.

**Finding the project root:** Look for the `scripts/` directory in these locations (in order): 1. The ai-sales-team-claude project directory (where the agents/ and skills/ folders are) 2. The current working directory 3. One level up from the current working directory

**If the script does NOT exist:**

• Inform the user: "The PDF generation script was not found at `scripts/generate_pdf_report.py`. This script is part of the AI Sales Team project setup. Please ensure the project is properly installed."
• Stop execution.

**If the script exists:**

• Proceed to execution.

Step 6: Generate the PDF

Run the PDF generation script:

python3 scripts/generate_pd