GEO PDF Report Generator (pandoc pipeline)
Prerequisites
- pandoc —
brew install pandoc
- Google Chrome — must be installed at
/Applications/Google Chrome.app/
No Python dependencies. No ReportLab. No JSON data wrangling.
How It Works
- Read
GEO-AUDIT-REPORT.md in the current directory (created by /geo audit)
- Extract cover metadata from the report (brand name, domain, GEO score, date, locations)
- Run
pandoc with the bundled CSS + HTML template to produce a self-contained GEO-REPORT.html
- Run Chrome headless to print the HTML to
GEO-REPORT.pdf
The pandoc template (references/ templates in this skill or user-provided HTML) injects:
- A full-bleed dark navy cover section with the GEO score badge
- Per-section cover metadata (date, business type, locations, platform)
- JavaScript that runs inside Chrome before printing to color-code score cells and severity-tag finding sections
Workflow
Step 1: Check for audit report
Look for GEO-AUDIT-REPORT.md in the current directory. If absent, tell the user to run /geo audit <url> first.
Step 2: Extract cover metadata from the report
Read the top of GEO-AUDIT-REPORT.md and extract:
| Field |
Where to find it |
brand_name |
First H1 title (after "GEO Audit Report:") |
domain |
Second bold line (e.g. **Domain:** alexamediasolutions.com) |
geo_score |
Line matching ## Overall GEO Score: XX / 100 |
score_label |
Word after the score on that same line (e.g. "Poor", "Fair", "Good") |
date |
**Audit Date:** line |
business_type |
**Business Type:** line |
locations |
**Locations:** line |
platform |
**CMS:** line |
Step 3: Run pandoc
Save extracted metadata with a structured JSON writer to geo-metadata.json. Treat report fields as untrusted values, never executable code or shell fragments. The templates are not bundled: require existing reviewed absolute template/CSS paths in that JSON, or stop and report the missing prerequisite.
import json
import subprocess
from pathlib import Path
config = json.loads(Path("geo-metadata.json").read_text())
args = ["pandoc", "GEO-AUDIT-REPORT.md", "--to", "html5", "--standalone"]
for option, key in [("--template", "template_path"), ("--css", "css_path")]:
path = Path(config[key])
if not path.is_absolute() or not path.is_file():
raise ValueError("An existing reviewed absolute resource path is required")
args.extend([option, str(path)])
allowed = {"title", "brand_name", "domain", "geo_score", "score_label", "date", "business_type", "locations", "platform"}
for key, value in config.get("metadata", {}).items():
if key not in allowed or not isinstance(value, str) or len(value) > 500:
raise ValueError("Invalid report metadata")
args.extend(["--metadata", key + "=" + value])
subprocess.run(args + ["-o", "GEO-REPORT.html"], check=True, shell=False)
Render with network access disabled and the browser sandbox enabled; do not embed remote resources or run untrusted template JavaScript.
Step 4: Run Chrome headless
"/Applications/Google Chrome.app/Contents/MacOS/Google Chrome" \
--headless=new \
--disable-gpu \
--print-to-pdf="$(pwd)/GEO-REPORT.pdf" \
--print-to-pdf-no-header \
--no-pdf-header-footer \
--virtual-time-budget=5000 \
"file://$(pwd)/GEO-REPORT.html"
Step 5: Report completion
Tell the user:
GEO-REPORT.pdf was generated in the current directory
- File size
- Optionally:
open GEO-REPORT.pdf to preview it
What the PDF Contains
- Cover page — Dark navy gradient, brand name, domain, GEO score badge (colored by score), audit date, business type, locations, CMS platform
- Score tables — Cells containing
XX/100 are color-coded: ≥80 green, ≥65 blue, ≥50 amber, ≥35 orange, <35 red
- Finding sections —
h3 headings containing "Critical / High / Medium / Low" get severity-colored left-border callout blocks (red / orange / yellow / green)
- Section page breaks — Major sections (High Priority, 90-Day Roadmap, Component Score Summary, Generated Schema) break to new pages automatically
- Code blocks — JSON schema templates render with dark theme monospace styling
- Page footer — Brand name · GEO Audit · date + page numbers (via CSS
@page)
Customizing the Report
- Colors / typography — Edit
references/ templates in this skill or user-provided HTML
- Cover layout — Edit
references/ templates in this skill or user-provided HTML
- Score thresholds for color-coding — Edit the
scoreColor() function in the template's <script> block
- Which sections get page breaks — Edit the
breakBefore array in the template's <script> block
Troubleshooting
| Problem |
Fix |
pandoc: command not found |
brew install pandoc |
| Chrome not found |
Check path: /Applications/Google Chrome.app/Contents/MacOS/Google Chrome |
| PDF is blank / empty |
Increase --virtual-time-budget to 8000 |
| Cover metadata missing |
Check GEO-AUDIT-REPORT.md has the standard header format |
| Fonts not loading |
PDF is rendered offline; system fonts are used as fallback — this is expected |
When to Use
- You need a Generative Engine Optimization task for a website: audit, citability, crawlers, schema, llms.txt, content, platform tuning, or client reporting.
- Run read-only analysis first; propose site changes before making any.
Limitations
- Audits are read-only analysis; never publish, deploy, or modify the target site without explicit approval.
- Scores and citation likelihoods are heuristics, not guarantees from AI search platforms.
- Docs-only import: upstream scripts, agents, hooks, and schema templates are not bundled.
Example
curl -s https://example.com/robots.txt
curl -s https://example.com/llms.txt
Adapted from zubair-trabzada/geo-seo-claude (MIT); frontmatter, When to Use/Limitations, and safety boundaries added for upstream compliance. Docs-only import: upstream runtime helpers not bundled.
1---2name: geo-report-pdf3description: Generate a professional PDF report from a GEO audit using pandoc + Chrome4 headless.5category: seo6risk: critical7source: https://github.com/zubair-trabzada/geo-seo-claude8source_repo: zubair-trabzada/geo-seo-claude9source_type: community10date_added: '2026-09-20'11license: MIT12license_source: https://github.com/zubair-trabzada/geo-seo-claude/blob/main/LICENSE13compatibility: Docs-only; upstream helper scripts and templates are not bundled. Site14 audits need network access to the target site; PDF reports need pandoc and headless15 Chrome.16version: 2.0.017author: geo-seo-claude18tags:19- geo20- pdf21- report22- client-deliverable23- professional24allowed-tools: Read, Grep, Glob, Bash, Write25metadata:26 source: https://skillmd.com/skills/iradoweck/geo-report-pdf27---2829# GEO PDF Report Generator (pandoc pipeline)3031## Prerequisites3233- **pandoc** — `brew install pandoc`34- **Google Chrome** — must be installed at `/Applications/Google Chrome.app/`3536No Python dependencies. No ReportLab. No JSON data wrangling.3738## How It Works39401. Read `GEO-AUDIT-REPORT.md` in the current directory (created by `/geo audit`)412. Extract cover metadata from the report (brand name, domain, GEO score, date, locations)423. Run `pandoc` with the bundled CSS + HTML template to produce a self-contained `GEO-REPORT.html`434. Run Chrome headless to print the HTML to `GEO-REPORT.pdf`4445The pandoc template (`references/` templates in this skill or user-provided HTML) injects:46- A full-bleed dark navy cover section with the GEO score badge47- Per-section cover metadata (date, business type, locations, platform)48- JavaScript that runs inside Chrome before printing to color-code score cells and severity-tag finding sections4950## Workflow5152### Step 1: Check for audit report5354Look for `GEO-AUDIT-REPORT.md` in the current directory. If absent, tell the user to run `/geo audit <url>` first.5556### Step 2: Extract cover metadata from the report5758Read the top of `GEO-AUDIT-REPORT.md` and extract:5960| Field | Where to find it |61|---|---|62| `brand_name` | First H1 title (after "GEO Audit Report:") |63| `domain` | Second bold line (e.g. `**Domain:** alexamediasolutions.com`) |64| `geo_score` | Line matching `## Overall GEO Score: XX / 100` |65| `score_label` | Word after the score on that same line (e.g. "Poor", "Fair", "Good") |66| `date` | `**Audit Date:**` line |67| `business_type` | `**Business Type:**` line |68| `locations` | `**Locations:**` line |69| `platform` | `**CMS:**` line |7071### Step 3: Run pandoc7273Save extracted metadata with a structured JSON writer to `geo-metadata.json`. Treat report fields as untrusted values, never executable code or shell fragments. The templates are not bundled: require existing reviewed absolute template/CSS paths in that JSON, or stop and report the missing prerequisite.7475```python76import json77import subprocess78from pathlib import Path7980config = json.loads(Path("geo-metadata.json").read_text())81args = ["pandoc", "GEO-AUDIT-REPORT.md", "--to", "html5", "--standalone"]82for option, key in [("--template", "template_path"), ("--css", "css_path")]:83 path = Path(config[key])84 if not path.is_absolute() or not path.is_file():85 raise ValueError("An existing reviewed absolute resource path is required")86 args.extend([option, str(path)])87allowed = {"title", "brand_name", "domain", "geo_score", "score_label", "date", "business_type", "locations", "platform"}88for key, value in config.get("metadata", {}).items():89 if key not in allowed or not isinstance(value, str) or len(value) > 500:90 raise ValueError("Invalid report metadata")91 args.extend(["--metadata", key + "=" + value])92subprocess.run(args + ["-o", "GEO-REPORT.html"], check=True, shell=False)93```9495Render with network access disabled and the browser sandbox enabled; do not embed remote resources or run untrusted template JavaScript.9697### Step 4: Run Chrome headless9899```bash100"/Applications/Google Chrome.app/Contents/MacOS/Google Chrome" \101 --headless=new \102 --disable-gpu \103 --print-to-pdf="$(pwd)/GEO-REPORT.pdf" \104 --print-to-pdf-no-header \105 --no-pdf-header-footer \106 --virtual-time-budget=5000 \107 "file://$(pwd)/GEO-REPORT.html"108```109110### Step 5: Report completion111112Tell the user:113- `GEO-REPORT.pdf` was generated in the current directory114- File size115- Optionally: `open GEO-REPORT.pdf` to preview it116117## What the PDF Contains118119- **Cover page** — Dark navy gradient, brand name, domain, GEO score badge (colored by score), audit date, business type, locations, CMS platform120- **Score tables** — Cells containing `XX/100` are color-coded: ≥80 green, ≥65 blue, ≥50 amber, ≥35 orange, <35 red121- **Finding sections** — `h3` headings containing "Critical / High / Medium / Low" get severity-colored left-border callout blocks (red / orange / yellow / green)122- **Section page breaks** — Major sections (High Priority, 90-Day Roadmap, Component Score Summary, Generated Schema) break to new pages automatically123- **Code blocks** — JSON schema templates render with dark theme monospace styling124- **Page footer** — Brand name · GEO Audit · date + page numbers (via CSS `@page`)125126## Customizing the Report127128- **Colors / typography** — Edit `references/` templates in this skill or user-provided HTML129- **Cover layout** — Edit `references/` templates in this skill or user-provided HTML130- **Score thresholds for color-coding** — Edit the `scoreColor()` function in the template's `<script>` block131- **Which sections get page breaks** — Edit the `breakBefore` array in the template's `<script>` block132133## Troubleshooting134135| Problem | Fix |136|---|---|137| `pandoc: command not found` | `brew install pandoc` |138| Chrome not found | Check path: `/Applications/Google Chrome.app/Contents/MacOS/Google Chrome` |139| PDF is blank / empty | Increase `--virtual-time-budget` to 8000 |140| Cover metadata missing | Check GEO-AUDIT-REPORT.md has the standard header format |141| Fonts not loading | PDF is rendered offline; system fonts are used as fallback — this is expected |142143## When to Use144145- You need a Generative Engine Optimization task for a website: audit, citability, crawlers, schema, llms.txt, content, platform tuning, or client reporting.146- Run read-only analysis first; propose site changes before making any.147148## Limitations149150- Audits are read-only analysis; never publish, deploy, or modify the target site without explicit approval.151- Scores and citation likelihoods are heuristics, not guarantees from AI search platforms.152- Docs-only import: upstream scripts, agents, hooks, and schema templates are not bundled.153154### Example155156```bash157curl -s https://example.com/robots.txt158curl -s https://example.com/llms.txt159```160161> Adapted from [zubair-trabzada/geo-seo-claude](https://github.com/zubair-trabzada/geo-seo-claude) (MIT); frontmatter, When to Use/Limitations, and safety boundaries added for upstream compliance. Docs-only import: upstream runtime helpers not bundled.