Skip to content
cccskills
FreePublished on GitHub

geo-setup

Initialize or repair the GEO-SEO Codex runtime for plugin and classic installer modes. Creates a Python virtual environment, installs requirements, verifies bundled scripts/templates, and explains optional PDF/browser dependencies.

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md3.9 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

GEO Runtime Setup Skill

Purpose

Use this skill when a GEO workflow needs bundled Python utilities, dependencies, templates, or PDF tooling and the runtime is missing or uncertain. It supports both installation modes:

  • Plugin mode: skills are loaded from a geo-seo-codex plugin checkout/cache, while scripts, schema templates, and report templates remain in that plugin root.
  • Classic installer mode: files are copied under ~/.codex/skills/geo/, with sub-skills under ~/.codex/skills/geo-*/ and optional agents under ~/.codex/agents/.

Do not require ~/.codex/agents/geo-*.toml for setup. Agents are the preferred full-audit acceleration path when available; plugin-only installs must still work through skills fallback.


Runtime Root Resolution

Resolve GEO_ROOT before running scripts:

  1. If CODEX_GEO_ROOT is set and contains scripts/, use it.
  2. If this skill was loaded from a plugin path like <plugin-root>/skills/geo-setup/SKILL.md, use <plugin-root>.
  3. If the current repository contains scripts/ and requirements.txt, use that repository root.
  4. Fall back to the classic installer path: ${CODEX_HOME:-$HOME/.codex}/skills/geo.

If no root contains scripts/fetch_page.py, stop and ask the user to install the plugin or run install.sh / install-win.sh.


Setup Workflow

Run the equivalent of this shell flow in the user's environment:

GEO_ROOT="${CODEX_GEO_ROOT:-}"

if [ -z "$GEO_ROOT" ]; then
  for candidate in "$PWD" "$PWD/.." "$PWD/../.." "${CODEX_HOME:-$HOME/.codex}/skills/geo"; do
    if [ -f "$candidate/scripts/fetch_page.py" ]; then
      GEO_ROOT="$(cd "$candidate" && pwd)"
      break
    fi
  done
fi

if [ -z "$GEO_ROOT" ] || [ ! -f "$GEO_ROOT/scripts/fetch_page.py" ]; then
  echo "GEO runtime root not found. Set CODEX_GEO_ROOT to the geo-seo-codex plugin/repo root."
  exit 1
fi

if [ "$GEO_ROOT" = "${CODEX_HOME:-$HOME/.codex}/skills/geo" ]; then
  GEO_RUNTIME_DIR="$GEO_ROOT"
else
  GEO_RUNTIME_DIR="${CODEX_GEO_RUNTIME_DIR:-${CODEX_HOME:-$HOME/.codex}/geo-seo-codex}"
fi

mkdir -p "$GEO_RUNTIME_DIR"

if command -v python3 >/dev/null 2>&1; then
  GEO_SYSTEM_PYTHON="python3"
elif command -v python >/dev/null 2>&1; then
  GEO_SYSTEM_PYTHON="python"
elif command -v py >/dev/null 2>&1; then
  GEO_SYSTEM_PYTHON="py"
else
  echo "Python 3.8+ is required."
  exit 1
fi

"$GEO_SYSTEM_PYTHON" -m venv "$GEO_RUNTIME_DIR/.venv"

if [ -x "$GEO_RUNTIME_DIR/.venv/bin/python" ]; then
  GEO_PYTHON="$GEO_RUNTIME_DIR/.venv/bin/python"
else
  GEO_PYTHON="$GEO_RUNTIME_DIR/.venv/Scripts/python.exe"
fi

"$GEO_PYTHON" -m pip install --upgrade pip
"$GEO_PYTHON" -m pip install -r "$GEO_ROOT/requirements.txt"

echo "GEO_ROOT=$GEO_ROOT"
echo "GEO_RUNTIME_DIR=$GEO_RUNTIME_DIR"
echo "GEO_PYTHON=$GEO_PYTHON"

On Windows, run the commands from Git Bash. If the user prefers the classic installer, use ./install-win.sh instead.


Verification

After setup, verify:

"$GEO_PYTHON" "$GEO_ROOT/scripts/fetch_page.py" https://example.com page
test -f "$GEO_ROOT/templates/geo-report-template.html"
test -f "$GEO_ROOT/templates/geo-report-style.css"
test -f "$GEO_ROOT/schema/organization.json"

Report the resolved GEO_ROOT, GEO_RUNTIME_DIR, and Python version.


Optional Dependencies

PDF reports require:

  • pandoc
  • Google Chrome, Microsoft Edge, Chromium, or another compatible headless Chromium executable

Screenshot/browser features may require:

"$GEO_PYTHON" -m playwright install chromium

These are optional. If unavailable, core audit, schema, crawler, llms.txt, citability, and reporting workflows should still run without PDF/browser output.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

geo

Free

GEO-first SEO analysis tool. Optimizes websites for AI-powered search engines (ChatGPT, Claude, Perplexity, Gemini, Google AI Overviews) while maintaining traditional SEO foundations. Performs full GEO audits, citability scoring, AI crawler analysis, llms.txt generation, brand mention scanning, platform-specific optimization, schema markup, technical SEO, content quality (E-E-A-T), and client-ready GEO report generation. Use when user says "geo", "seo", "audit", "AI search", "AI visibility", "optimize", "citability", "llms.txt", "schema", "brand mentions", "GEO report", or any URL for analysis.

The English summary is being prepared. Showing the original description.

bytefer/geo-seo-codex12Updated Jul 1, 2026

Full website GEO+SEO audit with parallel agents first and skills fallback. Orchestrates a comprehensive Generative Engine Optimization audit across AI citability, platform analysis, technical infrastructure, content quality, and schema markup. Produces a composite GEO Score (0-100) with prioritized action plan.

The English summary is being prepared. Showing the original description.

bytefer/geo-seo-codex12Updated Jul 1, 2026

Brand mention and authority scanner for AI visibility. Analyzes brand presence across platforms that AI models rely on for entity recognition and citation decisions. Produces a Brand Authority Score (0-100) with platform-specific recommendations.

The English summary is being prepared. Showing the original description.

bytefer/geo-seo-codex12Updated Jul 1, 2026

AI citability scoring and optimization. Analyzes web page content to determine how likely AI systems (ChatGPT, Claude, Perplexity, Gemini) are to cite or quote passages from the page. Provides a citability score (0-100) with specific rewrite suggestions.

The English summary is being prepared. Showing the original description.

bytefer/geo-seo-codex12Updated Jul 1, 2026

Monthly delta tracking and progress reporting for GEO clients. Compares two GEO audits (baseline vs. current), calculates score improvements across all categories, tracks action item completion, and generates a "here's your progress" client report. Use when user says "compare", "delta", "monthly report", "progress", "confronta", "progressi", "report mensile", or when running a monthly client check-in.

The English summary is being prepared. Showing the original description.

bytefer/geo-seo-codex12Updated Jul 1, 2026

Content quality and E-E-A-T assessment for AI citability — evaluate experience, expertise, authoritativeness, trustworthiness, and content structure

The English summary is being prepared. Showing the original description.

bytefer/geo-seo-codex12Updated Jul 1, 2026

See all skills by bytefer

Report a problem with this skill