GEO Pipeline Orchestrator

An entry-point skill that drives a 7-stage Generative Engine Optimization pipeline with strict stage ordering, schema validation and a human expert checkpoint.

Marketing & SEOAdvanced★ 452⑂ 38AI score 7/10Last updated: Jul 4, 2026

What it does

Acts as the single entry point for the recomby-geo GEO (Generative Engine Optimization) pipeline's 7 stages: intake → visibility audit → content-gap analysis → content brief → draft production → distribution → monthly re-audit.
Detects which stage you want, reads the matching commands/0X-*.md spec, and executes its procedure verbatim instead of duplicating logic.
Forces explicit validation of every JSON artifact against schemas/*.schema.json before moving on.
Enforces the dependency graph (02 needs 01; 03 needs 01+02; 05 needs a filled 04, etc.) and refuses out-of-order runs.
Core rule: only a human expert fills the REQUIRED-FILL brief slots; production refuses to start unless the brief meta status is ready-for-production.

Who it's for

SEO/GEO agencies and consultants managing brand visibility inside AI answer engines.
Teams that keep per-client artifact folders (clients/<slug>/) and want a repeatable, auditable process.
Codex CLI users who need the same workflow that Claude Code exposes as /01-intake … /07-reaudit.

Example uses

"Run the GEO audit for client acme" → reads the 02-audit spec, produces visibility_baseline.json, then validates it against the schema.
"Do the content-gap analysis" → checks that stage 01 and 02 artifacts exist, then runs 03-gap to write content_priorities.json.
"Draft the article from this brief" → refuses if briefs/<id>.meta.json isn't ready-for-production and asks the human expert to fill the slots.
Monthly check-in → runs 07-reaudit to emit reaudit/round-N.json, which feeds the next gap analysis round.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/ViryaZheng/recomby-geo/HEAD/plugins/recomby-geo/skills/geo-pipeline/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)

Download the ZIP with the button below.
In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.

↓ Download ZIP

Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the plugins/recomby-geo/skills/geo-pipeline folder from the GitHub repo ViryaZheng/recomby-geo into my ~/.claude/skills/geo-pipeline/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/ViryaZheng/recomby-geo.git && mkdir -p ~/.claude/skills && cp -r recomby-geo/plugins/recomby-geo/skills/* ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

Open a terminal and move to your working directory.
Clone the repository: git clone https://github.com/ViryaZheng/recomby-geo.git
Create the skills directory: mkdir -p ~/.claude/skills
Copy the plugin's skills over: cp -r recomby-geo/plugins/recomby-geo/skills/* ~/.claude/skills/
This skill only works together with the plugin's commands/, schemas/ and orchestrator/ files, so keep the clone and place it in your project as plugins/recomby-geo/.
Install the Python dependency: python3 -m pip install jsonschema
Create a client workspace: mkdir -p clients/<slug>/inputs
Restart Claude Code (or Codex CLI) and ask something like "run stage 01-intake of the GEO pipeline for clients/acme".

View source on GitHub ↗License: MIT