SKILL.md · Claude Code, Cursor, Codex
geo-citation-playbook
description
Use when a brand needs to be retrieved and cited inside generative answers (ChatGPT Search, Copilot, Perplexity, Claude, Gemini, Google AI Mode) — per-engine eligibility, citation measurement, third-party corroboration. Not for winning one SERP answer box (aeo-answer-surface-playbook).
- What it does
- Gets a brand cited in ChatGPT Search, Copilot, Perplexity, Claude, Gemini and AI Mode, using a prompt × engine gap table and a truth file, with no rate reported without its sample size.
- Where it stops
- Not for winning one SERP answer box (aeo-answer-surface-playbook).
One-time payment. The zip has all 11 skill folders with their references.
- ---
- name: geo-citation-playbook
- description: Use when a brand needs to be retrieved and cited inside generative answers (ChatGPT Search, Copilot, Perplexity, Claude, Gemini, Google AI Mode) — per-engine eligibility, citation measurement, third-party corroboration. Not for winning one SERP answer box (aeo-answer-surface-playbook).
- ---
- # GEO citation playbook
- Diagnose citation gaps per engine, fix retrieval eligibility, then build citable evidence and third-party corroboration. Measure citations, not only clicks.
- This skill owns engine differences, 2026 measurement, volatility, and sequencing. It does not re-teach generic extractability templates, llms.txt recipes, or generic schema; use a dedicated writing guide for those.
- Facts here are dated (current as of early November 2026). If they are more than 14 days old, run the `search-change-triage` skill first, against your own dated watchlist of official sources.
- Always cite official docs or label `[HYPOTHESIS]`. Refresh any published stat older than 90 days. No prompt injection, fake mentions, manufactured branded-search campaigns, or inauthentic citation schemes (Google + Bing abuse policies). Refuse reciprocal CMS cite-exchange networks ("every outbound earns one back", agent-published articles that exist to trade links).
The other 10 skills in the pack
- technical-seo-2026-delta
Use when a site needs only the 2025–2026 Google/Bing technical changes checked (generative eligibility, snippet controls, dead rich results, crawler split, new Search Console reports and measurement caveats, EEA site-reputation split, regional SERP units, emergency crawl-rate controls).
- aeo-answer-surface-playbook
Use when the goal is to own the answer unit on a named results/answer surface (featured snippet, PAA, AI Overview, Copilot, Perplexity), especially when the site already ranks and still loses the box.
- programmatic-seo-gate
Use when someone wants template, location, integration, comparison, directory, or other pages at scale (programmatic SEO) and needs a 2026 allow/refuse decision with a page cap.
- site-ia-map
Use for a hub/spoke, cannibalization, one-URL-per-intent, internal-links, or site information-architecture job (live remap or greenfield).
- search-change-triage
Use every Monday, or when traffic / rankings / AI Overviews / AI citations moved, to classify the external search change and then choose wait, watch, or act.
- gsc-growth-review
Use when the ask is a Google Search Console period review and a qualitative SEO growth judgment for a named property.
- seo-agent-design
Use when someone asks you to build an SEO / AEO / GEO agent or content bot and you need its safety contract (tools, approve path, refuse list) before any code.
- how-to-site-factory
Use when building or rebuilding a vertical how-to / niche publisher site with a coding agent (repo, stack defaults, SEO defaults, image, accuracy and byline rules).
- linkedin-post-system
Use when designing a repeatable LinkedIn publishing system (topics, formats, cadence, review) that stays inside LinkedIn's 2026 rules, e.g. for building in public.
- skill-review
Use when auditing, tightening, or deciding whether to keep one agent SKILL.md.