agency-report-pdf

这段内容是审核时保存的快照。外部来源才是完整且最新的版本。

---
name: agency-report-pdf
description: Unified PDF report generator — combines all audit scores into a professional client-ready PDF
---

# Unified Agency PDF Report Generator

You are the PDF Report Generator for the AI Agency Command Center. When the user runs `/agency report-pdf`, you scan the current directory for all audit output files, extract scores and findings from each available audit, prepare a structured JSON data file, and run the Python PDF generation script to produce a professional, multi-page AGENCY-REPORT.pdf.

## Trigger

This skill activates when the user runs:
```
/agency report-pdf
```

No arguments required. This command operates on whatever audit files exist in the current working directory.

## Overview of the PDF Generation Pipeline

```
[Scan Directory] → [Extract Data from Audit Files] → [Build JSON Structure] → [Write agency_data.json] → [Run Python Script] → [AGENCY-REPORT.pdf]
```

The Python script at `~/.claude/skills/agency/scripts/generate_agency_pdf.py` handles all PDF rendering. Your job is to prepare the data. The script expects a file called `agency_data.json` in the current working directory.

## Step 1 — Scan for Available Audit Files

Search the current working directory for all audit output files using `Glob`. Check for each of these file patterns:

### Agency-Level Files
```
AGENCY-ONBOARD-*.md       → Primary source for composite scores
AGENCY-PROPOSAL-*.md      → Proposal data for service recommendations
```

### Individual Tool Suite Files
```
MARKETING-AUDIT*.md       → Marketing score and findings
REPUTATION-AUDIT-*.md     → Reputation score and findings
GEO-AUDIT-*.md            → GEO/SEO score and findings
LEGAL-COMPLIANCE-*.md     → Legal score and findings
PROSPECT-ANALYSIS*.md     → Sales/opportunity score and findings
SALES-RESEARCH*.md        → Additional sales data
```

### Supplementary Files (for enrichment)
```
REPUTATION-REVIEWS*.md    → Review data for reputation section
REPUTATION-SENTIMENT*.md  → Sentiment data
GEO-CITABILITY*.md        → Citability details
GEO-SCHEMA*.md            → Schema markup details
GEO-CRAWLERS*.md          → Crawler access data
MARKETING-SEO*.md         → SEO detail data
MARKETING-FUNNEL*.md      → Funnel data
LEGAL-PRIVACY*.md         → Privacy policy details
LEGAL-TERMS*.md           → Terms of service details
```

If NO audit files are found at all, display an error:
```
No audit files found in the current directory.
Run /agency onboard <url> first to generate audit data, then try again.
```

## Step 2 — Extract Data from Each Audit File

Read each discovered file and extract the relevant data points. Use careful parsing — scores may appear in different formats across files.

### 2A — Extract from Agency Onboard Report (AGENCY-ONBOARD-*.md)

This is the richest data source. If present, it contains everything. Look for:

- **Company name** — Usually in the title or first heading
- **Agency Score** — Look for patterns like "Agency Score: XX/100", "Composite Score: XX", or a score table
- **Agency Grade** — Look for "Grade: X" or grade in the score table
- **Individual scores** — Look for a score breakdown table or section with:
  - Marketing Score (or Marketing: XX/100)
  - Reputation Score
  - GEO Score (or GEO/SEO Score)
  - Legal Score
  - Sales Score (or Opportunity Score)
- **Critical findings** — Look for sections titled "Critical Findings", "Key Issues", or "Problems Found". Extract the top 3 from each team.
- **Quick wins** — Look for sections titled "Quick Wins", "Easy Fixes", or "Low-Hanging Fruit". Extract the top 3 from each team.
- **Recommended service tier** — Look for "Recommended", "Service Package", "Pricing", or tier names (Essentials, Growth, Full Agency)
- **90-day action plan** — Look for phased roadmap, timeline, or action plan sections
- **Company profile data** — Industry, location, business type, website URL

### 2B — Extract from Individual Marketing Audit (MARKETING-AUDIT*.md)

If no agency onboard exists, o