indranilbanerjee/digital-marketing-pro/aeo-geo

AEO/GEO Intelligence

Metrics: mention rate, citation rate, share of model, share of AI voice, sentiment and the AI Visibility Score are defined, with formulas, in skills/context-engine/ai-visibility-metrics.md. Report every score with its formula and its sample size (n).

Script location. If your host does not set ${CLAUDE_PLUGIN_ROOT}, the scripts are in this plugin's scripts/ folder, next to skills/. Run them with Python 3.10 or newer: python, or python3 where python is not found (macOS, many Linux systems).

When to Use This Skill

Activate this module when the user's request involves any of the following:

• AI Visibility: Questions about how a brand, product, or person appears in AI-generated answers (ChatGPT, Perplexity, Google AI Mode, Google AI Overviews, Copilot, Gemini, Claude)
• Answer Engine Optimization (AEO): Optimizing content so it gets selected as a source for AI-generated answers
• Generative Engine Optimization (GEO): Structuring content and entities so generative AI platforms accurately represent a brand
• Citation Tracking: Monitoring which sources AI models cite when answering queries related to a brand or industry
• Entity Consistency: Ensuring brand information is uniform across all knowledge sources that AI models train on or retrieve from
• Knowledge Graph Optimization: Improving how a brand is represented in Google Knowledge Graph, Wikidata, and other structured knowledge bases
• Structured Data for AI: Implementing schema markup and structured data specifically to improve AI comprehension and citation likelihood

Trigger phrases: "AI visibility," "how does ChatGPT describe my brand," "Perplexity results," "AI Mode optimization," "AI Overview optimization," "answer engine," "generative engine," "LLM optimization," "AI citations," "entity consistency," "Knowledge Graph"

Google AI Mode (May 2026 — treat as a distinct surface): This is DMP's one statement of the fact; other files point here. Google AI Mode has more than one billion monthly users, Gemini 3.5 Flash is its default model, and it is reachable from every AI Overview worldwide (Google, "Google Search's I/O 2026 updates", 2026-05-19). AI Overviews remain the default search surface: AI Mode is a separate conversational tab, not the default search experience. AI Mode is not the same as AI Overviews — it is a separate conversational tab with deeper reasoning, multi-turn follow-ups, and a citation pattern that frequently diverges from AI Overviews for the same query. Brands must audit AI Mode independently. Practical implication: an AEO program that only tests AI Overviews + ChatGPT + Perplexity now has a measurable blind spot.

Additional I/O 2026 announcements that change AEO scope (source: blog.google/products-and-platforms/products/search/search-io-2026):

• AI Overview → AI Mode follow-up flow is live worldwide (desktop + mobile) — users can ask a follow-up directly from an AI Overview and flow into a conversational AI Mode session. AEO implication: the first impression in an AI Overview is now also a gateway to multi-turn citation. Optimize for being the foundational citation, not just the brief snippet.
• Personal Intelligence in AI Mode is expanding to ~200 countries and 98 languages, no subscription required, with Gmail / Photos / Calendar connections. AEO implication: AI answers are increasingly personalized — generic brand-search results will be reweighted against the user's own context. Brand schema completeness and entity consistency (NAP, services, hours) matter even more.
• AI Information Agents (user-created, monitoring blogs/news/social 24/7) launch for AI Pro & Ultra subscribers in summer 2026. AEO implication: brands that publish structured, dated updates on owned channels will be more legible to user-configured agents than those relying on third-party PR pickup.

Official Google guidance on AI search optimization (last updated 2026-07-10 — Google AI Optimization Guide):

• No `llms.txt` file is needed. Google's official position: "You don't need to create new machine readable files, AI text files, markup, or Markdown to appear in generative AI search." Do not waste time generating llms.txt for Google AI Features. (Other AI search engines may or may not consume it; current Anthropic / OpenAI / Perplexity public positions are also that they do not require it. Document any client pressure to ship llms.txt as a low-priority deliverable with no measurable upside.)
• No special AI-specific schema is needed. "Structured data isn't required for generative AI search, and there's no special schema.org markup you need to add." Schema continues to matter for classic SEO and rich results.
• Eligibility is standard Search. "To be eligible to be shown in generative AI features on Google Search, a page must be indexed and eligible to be shown in Google Search with a snippet, fulfilling the Search technical requirements."

Opt-out and AI training controls (Google AI Features doc):

• For AI Overviews and AI Mode (inside Google Search): use existing snippet directives — nosnippet, data-nosnippet, max-snippet, noindex. Robots.txt for Googlebot is the canonical control. There is no AI-specific robots/meta directive.
• For Google's other AI systems (Gemini app training, Vertex AI grounding outside Search): use the Google-Extended user agent in robots.txt. This is a distinct control from Googlebot.
• Search generative AI control (Search Console → Settings → Search generative AI; worldwide since 31 Aug 2026). Excluding a property removes its links and content from AI Overviews, AI Mode and generative AI features in Discover. Google: it "isn't used as a ranking or inclusion signal affecting other parts of Search" and "doesn't affect AI training" (that is Google-Extended); exclusion takes effect in a day or two. Decide on evidence, not fear: opting out gives up every AI-feature impression the Search Console generative AI report shows, and it also removes the "preferred" badge in AI Mode and AI Overviews for readers who chose the site as a Preferred Source. Recommend it only where AI answers demonstrably substitute for a paid or licensed product (for example paywalled reference content), and record the before/after impressions. Source: Search Console help, read 2026-10-27.
• Preferred Sources (playbook item). Readers can mark a site as a Preferred Source; its stories then appear more often in Top Stories with a "preferred" badge, and its content can carry that badge in AI Mode and AI Overviews. Google says use of the feature has grown more than 7x since the start of 2026 (blog.google, 15 Oct 2026). For publishers and brands with a news or blog cadence: add Google's "add as preferred source" button or the deep link https://www.google.com/preferences/source?q=<your domain> to articles, newsletters and social posts. Only domains and subdomains qualify (not subdirectories), and the AI Mode badge needs the site to stay included in Search generative AI features. Source: Search Central: Preferred sources (updated 2026-09-18).

EU AI Act Article 50 (has applied since 2 August 2026; generative systems that existed before then have until 2 December 2026 to mark their output under Article 50(2)) — for AI-generated marketing content surfaced in EU markets, see skills/context-engine/eu-code-of-practice.md for the voluntary Code of Practice (WG1 providers / WG2 deployers) and the C2PA c2pa.ai-disclosure assertion path. Compliance is plugin-level and applies to c2pa-metadata outputs.

Brand Context (Auto-Applied)

Before producing any marketing output from this module:

1. Check session context — The active brand summary was output at session start. Use the brand name, industry, voice settings, channels, goals, compliance, and competitors shown there.
2. If you need the full profile, read: ~/.claude-marketing/brands/{slug}/profile.json
3. Apply brand voice — Formality, energy, humor, authority levels must shape all content tone and word choices
4. Check compliance — Auto-apply rules for brand's target_markets and industry using skills/context-engine/compliance-rules.md
5. Reference industry benchmarks — Consult skills/context-engine/industry-profiles.md for the brand's industry
6. Use platform specs — Reference skills/context-engine/platform-specs.md for character limits and format requirements
7. Check campaign history — Run python "${CLAUDE_PLUGIN_ROOT}/scripts/campaign-tracker.py" --brand {slug} --action list-campaigns before planning new work
8. If no brand exists, say: "No brand profile found. Use /digital-marketing-pro:brand-setup to create one, or I can proceed with general best practices."
9. Check brand guidelines — If ~/.claude-marketing/brands/{slug}/guidelines/_manifest.json exists, load and enforce: restrictions.md for banned words, restricted claims, and mandatory disclaimers; channel-styles.md for channel-specific tone overrides (may differ from base voice); messaging.md for approved key messages, taglines, and positioning language; voice-and-tone.md for detailed voice rules beyond the 4 numeric scores. If producing content for a specific channel, channel style rules take precedence over base voice settings.

Do not ask the user for information that already exists in their brand profile.

Required Context

Before executing AEO/GEO work, gather:

1. Brand Identity: Official brand name, key products/services, unique value propositions, and brand positioning
2. Current AI Footprint: Ask the user if they have tested how AI platforms currently describe their brand (or offer to audit)
3. Target Queries: The questions and topics the brand wants to be cited for in AI-generated answers
4. Existing Content Assets: Website URL, blog, knowledge base, Wikipedia presence, schema markup status
5. Competitive Landscape: Key competitors who may already have strong AI visibility
6. Industry Vertical: Needed to assess YMYL (Your Money Your Life) sensitivity and trust signal requirements

If the user cannot provide all context, proceed with what is available and flag gaps as recommendations.

Minimum viable context: Brand name and website URL. Everything else can be inferred or discovered during the audit process.

Capabilities