recomby-geo
Packages Generative Engine Optimization expertise — how to make content rank in AI search answers — into agent-callable skills with a human-in-the-loop workf…
Open-source Generative Engine Optimization (GEO) toolkit that packages AI-search content optimization know-how as Claude Code skills, plus a 7-stage workflow (/01-intake through /07-reaudit) for auditing and improving a site's visibility in AI search engines. Bundles six vendored MIT/Apache skills including seo-geo-optimizer and content-quality-auditor, runs fully local with no API keys, and also works with OpenAI Codex CLI. Alpha status; docs are primarily in Chinese with an English README.
- Run a 7-stage GEO pipeline (intake, audit, gap analysis, content brief, production, distribution, re-audit) on a client site
- Audit a site's AI-search visibility and identify content gaps
- Produce and validate GEO-optimized content from expert-filled briefs, with schema validation at each stage
Packages Generative Engine Optimization expertise — how to make content rank in AI search answers — into agent-callable skills with a human-in-the-loop workflow, so marketing and content teams can run GEO audits and content production locally instead of uploading client data to SaaS tools like SurferSEO or Clearscope.
Content and SEO/GEO teams who want to audit and improve their visibility in AI search engines using a local, open-source workflow, with a business expert filling content briefs at the human-in-the-loop stage.
https://github.com/ViryaZheng/recomby-geo
By recomby-ai
How to Get It
/plugin marketplace add ViryaZheng/recomby-geo (then /plugin install recomby-geo, inside a Claude Code session)
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
After installing, paste this into Claude:
Help me run a 7-stage GEO pipeline (intake, audit, gap analysis, content brief, production, distribution, re-audit) on a client site
Trust Signals Auto-scanned
Community Pulse New
No community discussions found yet. This doesn't mean the tool isn't good — it may be new or serve a niche use case.
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 282 GitHub stars; contributors unknown; last commit 2d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
- Single maintainer. Consider the risk if this person stops maintaining the project.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 282 GitHub stars; contributors unknown; last commit 2d ago; license MIT.