Skip to content
SkillModel-led1,220 tokens in use

geo-report-pdf

Turns a GEO-AUDIT-REPORT.md into a styled, client-ready PDF with a cover page, color-coded score tables and a 90-day roadmap.

11,792 stars on the repository MIT Licensezubair-trabzada/geo-seo-claude · skills/geo-report-pdf
curl -fsSL https://raw.githubusercontent.com/zubair-trabzada/geo-seo-claude/main/install.sh | bash
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing geo-report-pdf costs

58tokens idle
1,220tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldeclared and detectednetworkdetectedwrites filesdeclared

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter8/15
  • Structure23/25
  • Examples9/15
  • Output7/15
  • Size11/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent
  • Runs shell commands−2

    does this on the machine, as the frontmatter declares

    SKILL.md, line 55

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity100
  • Maintenance52
  • Community68
  • Maturity32
  • Momentum40

geo-report-pdf takes the markdown report produced by the GEO audit and renders it as a finished PDF. It reads the brand name, domain, GEO score, date, business type, locations and CMS from the top of the report, runs pandoc with a bundled HTML template and stylesheet, then prints the result to PDF with headless Chrome.

The PDF has a dark navy cover with a score badge, score cells colored by band, finding sections tagged by severity, page breaks before the major sections and a footer with page numbers. Colors, cover layout, score thresholds and page breaks can all be changed by editing the template files.

What You Get

  • A GEO-REPORT.pdf in the current directory with a cover page, score badge and audit metadata
  • Score cells color-coded by band: 80 and up green, 65 blue, 50 amber, 35 orange, below 35 red
  • Finding sections with severity-colored callout blocks for Critical, High, Medium and Low
  • A self-contained GEO-REPORT.html built by pandoc that you can also open in a browser
  • Editable template and stylesheet for brand colors, cover layout and page breaks

Common Use Cases

  • Delivering a GEO audit to a client as a branded-looking PDF
  • Archiving a monthly audit snapshot in a fixed format
  • Sending a stakeholder a readable score summary and 90-day roadmap
  • Re-rendering a report after editing the markdown findings

What Makes It Unique

Most report skills stop at markdown. This one covers the last mile to a finished PDF using two common command-line tools, pandoc and Chrome in headless mode, with no Python libraries or JSON data files in between. The styling is in an HTML template and a CSS file, so a change to colors or thresholds is an edit to a text file. It is built to read the exact header format the GEO audit writes.

Under The Hood

The skill is a set of instructions for the agent with no scripts of its own. The agent reads GEO-AUDIT-REPORT.md, extracts the header fields, then runs a pandoc command through the shell that applies the template and stylesheet from the geo skill folder in your home directory and writes GEO-REPORT.html. It then runs Google Chrome from its macOS application path in headless mode to print that HTML to GEO-REPORT.pdf, and reports the file size. It writes both files into the current directory and works entirely on local files. It needs pandoc and Chrome installed, and the template files installed with the main geo skill.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers