Geo Pipeline
Orchestrates a 7-stage GEO (AI-search visibility) workflow on Codex CLI
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 21, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · e09b955
Located SKILL.md via GitHub API at plugins/recomby-geo/skills/geo-pipeline/; frontmatter parses with name+description and the body is a clean orchestrator (only a benign python3 jsonschema heredoc, no security smells). Spot-checked referenced files via raw fetch: commands/01-intake.md, orchestrator/run.md, and schemas/brand_context.schema.json all returned HTTP 200, and the schema parses as valid JSON. Could not measure output vs baseline: the skill routes to per-stage specs and faithfully running the smallest stage (01-intake) requires the full plugin scaffold (commands/ + schemas/ sit outside the skill dir), python3+jsonschema, a clients/<slug>/inputs/ project, and live WebFetch/WebSearch verification the skill's own "WebFetch before trust" rule forbids fabricating. Trigger judged 5/5 on three GEO/AI-visibility phrasings loading and two adjacents (traditional Google-SEO keyword audit; CI/CD pipeline) not loading.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 5/10
- Docs & honesty 4/5
What Geo Pipeline does
An orchestrator skill that drives recomby-geo's 7-stage Generative Engine Optimization workflow (intake, visibility audit, content-gap, brief, production, distribution, monthly re-audit) on OpenAI Codex CLI, routing to per-stage command specs and enforcing schema validation plus a human-in-loop brief checkpoint. Triggers when a user wants to run a GEO pipeline stage on a client folder, audit AI-search visibility, or "GEO this client." It coordinates existing stage files rather than doing the work itself, so it needs the full plugin scaffold to function.
How to install Geo Pipeline
git clone --depth 1 https://github.com/ViryaZheng/recomby-geo.git /tmp/geo-pipeline-src
mkdir -p ~/.claude/skills
cp -R /tmp/geo-pipeline-src/plugins/recomby-geo/skills/geo-pipeline ~/.claude/skills/geo-pipeline
# IMPORTANT: this skill is an ORCHESTRATOR and is non-functional standalone.
# It references files at the PLUGIN ROOT (outside the skill dir):
# plugins/recomby-geo/commands/01-intake.md ... 07-reaudit.md
# plugins/recomby-geo/orchestrator/run.md
# plugins/recomby-geo/schemas/*.schema.json
# plugins/recomby-geo/skills/geo-review-html/scripts/render_html.py
# To actually run stages, install the whole plugin instead of just this skill:
# cp -R /tmp/geo-pipeline-src/plugins/recomby-geo ~/.claude/plugins/recomby-geo
# Runtime deps: python3 on PATH + `pip install jsonschema` (schema validation).
# Also needs a scaffolded clients/<slug>/inputs/ folder with client materials,
# and live WebFetch/WebSearch + sub-agent scouting to execute stage 01 onward.
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Geo Pipeline
-
/geo-pipelineOrchestrates a 7-stage GEO (AI-search visibility) workflow on Codex CLI
It also activates on plain-language prompts like these:
-
Run a GEO visibility audit for this client -
Generate a content gap analysis for AI search -
Run the monthly GEO re-audit for this client folder
Frequently asked questions
- Is the Geo Pipeline skill free?
- Yes. The skill itself is free from ViryaZheng/recomby-geo. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Geo Pipeline work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Works with setup. Located SKILL.md via GitHub API at plugins/recomby-geo/skills/geo-pipeline/; frontmatter parses with name+description and the body is a clean orchestrator (only a benign python3 jsonschema heredoc, no security smells). Spot-checked referenced files via raw fetch: commands/01-intake.md, orchestrator/run.md, and schemas/brand_context.schema.json all returned HTTP 200, and the schema parses as valid JSON. Could not measure output vs baseline: the skill routes to per-stage specs and faithfully running the smallest stage (01-intake) requires the full plugin scaffold (commands/ + schemas/ sit outside the skill dir), python3+jsonschema, a clients/<slug>/inputs/ project, and live WebFetch/WebSearch verification the skill's own "WebFetch before trust" rule forbids fabricating. Trigger judged 5/5 on three GEO/AI-visibility phrasings loading and two adjacents (traditional Google-SEO keyword audit; CI/CD pipeline) not loading.
- What is the Geo Pipeline SkillProof Score?
- 7.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.
- How do I install Geo Pipeline?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Geo Pipeline with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.