thesmokedev/geo-skills/geo-report-pdf
Claude Code and agent skill by thesmokedev/geo-skills
- community
Checking that the SKILL.md file is still in the repository.
Generate a professional PDF report from GEO audit data using ReportLab. Creates a polished, client-ready PDF with score gauges, bar charts, platform readiness visualizations, color-coded tables, and prioritized action plans.
Install
npx vskill@latest install thesmokedev/geo-skills/geo-report-pdfSKILL.md
The same SKILL.md was published earlier as thesmokedev/geo-skills/geo-report-pdf.
GEO PDF Report Generator
Purpose
This skill generates a professional, visually polished PDF report from GEO audit data. The PDF includes score gauges, bar charts, platform readiness visualizations, color-coded tables, and a prioritized action plan — ready to deliver directly to clients.
Prerequisites
- ReportLab must be installed:
pip install reportlab - The PDF generation script is located at:
~/.claude/skills/geo/scripts/generate_pdf_report.py - Run a full GEO audit first (using
/geo-audit) to have data to include in the report
How to Generate a PDF Report
Step 1: Collect Audit Data
After running a full /geo-audit, collect all scores, findings, and recommendations into a JSON structure. The JSON data must follow this schema:
Step 2: Write JSON Data to a Temp File
Write the collected audit data to a temporary JSON file:
Step 3: Generate the PDF
Run the PDF generation script:
The script will produce a professional PDF report with:
- Cover Page — Brand name, URL, date, overall GEO score with visual gauge
- Executive Summary — Key findings and top recommendations
- Score Breakdown — Table and bar chart of all 6 scoring categories
- AI Platform Readiness — Visual horizontal bar chart per platform with scores
- AI Crawler Access — Color-coded table (green=allowed, red=blocked)
- Key Findings — Severity-coded findings list (critical/high/medium/low)
- Prioritized Action Plan — Quick wins, medium-term, and strategic initiatives
- Appendix — Methodology, data sources, and glossary
Step 4: Return the PDF Path
After generation, tell the user where the PDF was saved and its file size.
Complete Workflow Example
When the user runs this skill, follow this exact sequence:
- Check for existing audit data — Look for recent GEO audit reports in the current directory:
GEO-CLIENT-REPORT.mdGEO-AUDIT-REPORT.md- Or any
GEO-*.mdfiles from a recent audit
- If no audit data exists — Tell the user to run
/geo-audit <url>first, then come back for the PDF.
- If audit data exists — Parse the markdown report to extract:
- Overall GEO score
- Category scores (citability, brand authority, content/E-E-A-T, technical, schema, platform)
- Platform readiness scores (Google AIO, ChatGPT, Perplexity, Gemini, Bing Copilot)
- AI crawler access status
- Key findings with severity levels
- Quick wins, medium-term, and strategic action items
- Executive summary
- Build the JSON — Structure all data into the JSON schema shown above.
- Write JSON to temp file — Save to
/tmp/geo-audit-data.json
- Run the PDF generator:
``bash python3 ~/.claude/skills/geo/scripts/generate_pdf_report.py /tmp/geo-audit-data.json "GEO-REPORT-[brand_name].pdf" ``
- Report success — Tell the user the PDF was generated, its location, and file size.
If the User Provides a URL
If the user runs /geo-report-pdf https://example.com with a URL:
- First run a full audit: invoke the
geo-auditskill for that URL - Then collect all the audit data from the generated report files
- Generate the PDF as described above
Parsing Markdown Audit Data
When extracting data from existing GEO markdown reports, look for these patterns:
- GEO Score: Look for "GEO Score: XX/100" or "Overall: XX/100" or "GEO Readiness Score: XX"
- Category Scores: Look for score tables with columns like "Component | Score | Weight"
- Platform Scores: Look for tables with "Google AI Overviews", "ChatGPT", "Perplexity", etc.
- Crawler Status: Look for tables with "Allowed" or "Blocked" status for crawlers like GPTBot, ClaudeBot
- Findings: Look for sections titled "Key Findings", "Critical Issues", "Recommendations"
- Action Items: Look for sections titled "Quick Wins", "Action Plan", "Recommendations"
Notes
- If ReportLab is not installed, run:
pip install reportlab - The PDF is designed for US Letter size (8.5" x 11")
- Color palette: Navy primary (#1a1a2e), Blue accent (#0f3460), Coral highlight (#e94560), Green success (#00b894)
- Each page has a header line, page numbers, "Confidential" watermark, and generation date
- Score gauges use traffic-light colors: green (80+), blue (60-79), yellow (40-59), red (below 40)
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/geo-report-pdf/SKILL.md
Popularity
- Repository stars
- 25
- Repository forks
- 6
- 7-day trend score
- 16
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/thesmokedev/geo-skills/geo-report-pdf)