generative-seo

Generative SEO (GEO) Operations

Runs an SEO + GEO program the same way a sharp in-house SEO operator would: technical audits, answer-first content built to be quoted by AI engines, an AI-citation tracker, competitor watch, and (draft-only) distribution. It is deliberately generic — first use in a repo spends a few minutes learning that project's facts, then behaves like a project-specific skill from then on.

Mode selection: the argument names the mode (content, audit, optimize, competitors, citations, report, social). No argument → read the project's docs (below), summarize current state, and recommend the highest-impact next action.

For the full evidence behind every rule below (which studies, what they found, why each technique works) and the complete technical checklist, see references/geo-methodology.md. Read it before an audit or before writing a first piece of content in a new project; skip re-reading it on later runs in the same project.

First run in a project: learn the project

Look for a config file at docs/seo/geo-config.md (or wherever the user says their SEO docs live — some repos keep them in content/, marketing/, or a wiki instead). If it exists, read it and skip to Read these first.

If it does not exist, this is the first run — ask the user (batch these, don't interview one question at a time):

1. Product/brand name(s) — and critically, if the product is a sub-brand of a parent company or a different name than the company that builds it, get that distinction explicit now (e.g. "Acme Corp is the company; Acme Flow is the product we're marketing" or "same name, no distinction needed"). Getting this wrong (writing "is Acme Corp free?" when the product is Acme Flow) is a real, recurring mistake — nail it once here instead of guessing per-page later.
2. Primary domain the content lives on (affects sitemap/robots checks and internal-link audits).
3. Framework — Next.js, Astro, Remix, SvelteKit, plain static HTML, a CMS (WordPress/Webflow/etc.), or something else. This determines where sitemap/robots/metadata/JSON-LD live (see references/geo-methodology.md for the per-framework map) — if unsure, look at the repo yourself first (package.json, top-level config files) before asking.
4. Where marketing/content pages live in the repo (a directory, a headless CMS, or "not in this repo" if content is managed elsewhere).
5. Existing design system doc, if any (a DESIGN.md, a Storybook, a Figma library) — new/edited pages should match it rather than invent a new look.
6. How to source real statistics for content — product analytics the user can query, a public dataset, or "external sources only." Never invent numbers regardless of the answer.
7. Docs folder for this skill's own working files (default: docs/seo/ at repo root — offer this default rather than making the user think of one).