gumlau

geo-citations

Analyze which source domains AI answers cite and how often your domain versus competitors get cited — harvest sources[].url from raw answers, normalize to domains, and rank most-cited domains overall and per engine, your own citation rate, competitor citation rates, and citation-gap domains you should try to appear on. Use when the user asks which sources AI cites, what domains ChatGPT/Perplexity/Gemini link, my citation rate, how often AI cites my site vs competitors, which domains AI trusts, where should I get published to be cited, citation gap, or most-cited sources in AI answers.

geo-competitors

Build a side-by-side competitive GEO profile of how AI answers treat a brand versus each named competitor — assembling visibility, share-of-voice, citation footprint, and sentiment into one comparison table and surfacing why AI favors the leaders. Use when the user asks to compare competitors in AI answers, benchmark against rivals, build a competitor matrix, see who wins in ChatGPT/Perplexity/Gemini, analyze AI share of voice vs competitors, or asks why AI recommends a competitor instead of them.

geo-monitor

Track brand visibility and share-of-voice over time by registering a prompt set as AgentGEO schedules, then diffing each new run against the previous to report trend — visibility up/down, new competitors appearing, lost or gained citations, sentiment drift. Use when the user asks to monitor GEO over time, track AI visibility, watch share of voice, set up a schedule, re-run my prompt set weekly, alert me when a competitor shows up, trend my brand in AI answers, detect when we lose citations, or compare this week's AI answers to last week.

geo-prompt-set

Generate a representative, intent-layered set of real user prompts (informational, commercial, comparison, transactional, local) for a brand or category and emit a copy-pasteable JSON prompt library that every geo-* skill consumes. Use when the user asks to build a prompt set, generate GEO prompts, create an AI-search prompt library, seed a brand/category with test queries, list the questions people ask ChatGPT/Perplexity/Gemini about a brand, or says "what prompts should I track", "make prompts for my brand", or "start a GEO analysis".

Data & Documents Listed

geo-report

Synthesize a full GEO audit report from AgentGEO raw answers — an answer-first executive verdict, an engine × buyer-intent visibility matrix, a decomposed per-dimension scorecard (visibility, share-of-voice, citations, sentiment) with published banding, a quantified competitor benchmark, per-threat evidence cards, a priority-scored fix plan, trend deltas vs a prior run, and a quarantined evidence registry — every score, rank, and fix computed agent-side and backed by a verbatim quote or cited URL. Saves the deliverable as local files when the agent can write to disk — a markdown report, an optional self-contained HTML scorecard, and a multi-sheet xlsx workbook (mention-rate and citation-rate pivots plus a raw detail log). Use when the user asks for a GEO report, full AI-visibility report, generative engine optimization report, executive GEO summary, "how do we show up in AI and what do we fix", a GEO audit across ChatGPT/Perplexity/Gemini/Copilot/Google, a prioritized GEO action plan, a client-ready or sharea

geo-sentiment

Characterize how AI engines describe a brand — classify tone (positive/neutral/negative) per mention, extract recurring attribute words and framing, and output a sentiment + attribute profile per surface with representative quotes. Use when the user asks how AI talks about my brand, what ChatGPT/Perplexity/Gemini say about us, is the sentiment positive or negative, what attributes AI associates with my brand, how AI frames us vs competitors, brand perception in AI answers, or whether AI describes us accurately/on-message.

geo-share-of-voice

Compute a brand's share of voice against named competitors across AI answers — count mentions, flag explicit recommendations, and produce a mention-weighted and recommendation-weighted SoV leaderboard plus a per-engine breakdown. Use when the user asks for share of voice, AI SoV, share of voice vs competitors, how often my brand shows up vs [competitor], who dominates AI answers, brand vs competitor mention share, SoV leaderboard, or which brands AI recommends most.

geo-visibility

Measure whether and how prominently a brand appears in AI answers across engines from a prompt set — detect per-answer mention (present/absent), position (first-mentioned, recommended), and surrounding context, then build a prompt×surface presence matrix with a per-engine and blended visibility rate. Use when the user asks does AI mention my brand, am I visible in ChatGPT/Perplexity/Gemini, check my AI visibility, how often does AI recommend me, build a presence matrix, measure brand visibility across AI engines, or is my brand showing up in AI answers.