aeo-skills

Curated prompt pack for AI tool brands tracking their visibility in AI answer engines. 17 prompts covering AI-task discovery, alternatives to incumbents (ChatGPT, Claude, etc.), free-vs-paid framing, accuracy claims, privacy positioning, and vertical use cases. Variables (task, competitor, use_case, domain) fill per workspace. Use when a user is tracking visibility for an AI product, building an AEO baseline for AI-tool category, or asks for prompt ideas for an AI startup.

Curated prompt pack for B2B SaaS AEO visibility tracking. 20 vertical-specific prompts covering category discovery, vendor comparison, alternatives, pricing, integrations, and trust signals. Designed to be merged into an existing aeo.config.json before running aeo-baseline. Template variables (category, problem, vendor, integration, company_size) are filled in per workspace. Use when a user is setting up AEO tracking for a B2B SaaS product, wants a starter prompt set for software-category visibility, or asks for prompt ideas for a SaaS company.

Curated prompt pack for local service businesses (plumbers, dentists, lawyers, mechanics, restaurants, contractors, etc.) tracking AEO visibility. 16 prompts covering near-me searches, ratings/reviews, pricing, emergency, trust signals, and specialty filtering. Template variables (service, city, specialty, neighborhood) are filled per workspace. Use when a user is setting up AEO tracking for a local service business, wants a starter prompt set for geographic queries, or asks for prompt ideas for a brick-and-mortar service provider.

Turn an AEO visibility baseline into a concrete content work queue. Reads the latest aeo-evidence-v1 file from aeo-data/, optionally reads aeo-report output and fetched page content, then produces a prioritized Markdown task list. Each task is evidence-backed: it cites the prompt_id, the metric driving the recommendation (mention rate, citation rate, position, decay, cannibalization, hub-page opportunity), and concrete next steps (refresh URL X, create page A vs B, add JSON-LD type Z, surface entity Y). SKILL.md-only — the agent reasons over the methodology in references/ and applies it to the user's data. No script, no API calls. Use when a user wants to: turn baseline data into action, decide what content to refresh or create next, plan an AEO sprint, build a backlog from a visibility report, or close the gap between "what's broken" and "what should I do about it".

Analyze web pages and generate structured data (JSON-LD) optimized for AI citation. Fetches a page, analyzes its content structure, checks existing schema markup, and generates optimized JSON-LD that helps Gemini 3 Flash and other AI models identify and cite the content. Includes templates for Article, FAQ, HowTo, Product, LocalBusiness, and BreadcrumbList. SKILL.md-only skill — no script, the agent follows the methodology. Use when a user wants to: add or improve structured data on a page, optimize schema for AI Overviews, generate JSON-LD for their content, audit existing schema markup, or implement an aeo-optimize recommendation that calls for new structured data.

Analyze WHY certain sources get cited by Gemini over others. Runs a prompt through Gemini 3 Flash with grounding, ranks cited sources by frequency, then fetches and profiles the top pages — word count, headings, structured data (JSON-LD), publication dates, and entity density. Outputs a "citation blueprint" showing what top-cited pages have in common. Optionally highlights where a specific domain's pages stand vs the blueprint. Use when a user wants to: understand what makes pages get cited by AI, reverse-engineer citation patterns, build a content template based on what Gemini prefers, compare their content to competitors' cited pages, or audit page-level factors that correlate with AI citations.

Read accumulated aeo-baseline evidence files and produce a visibility trend report. Surfaces visibility score trends, citation-rate decay, content cannibalization (multiple owned URLs competing for the same prompt), hub-page opportunities (one URL winning across many prompts), and competitor share-of-voice changes. Outputs Markdown + single-file HTML with embedded SVG charts. Pure analysis — no provider API calls, no API keys required. Use when a user wants to: see how their AI visibility is changing over time, find pages losing citations, identify which owned URLs are working across multiple prompts, share a visibility report with stakeholders, or understand competitor share trends.

Initialize an AEO workspace by writing aeo.config.json — the workspace configuration file that every other v2 skill (aeo-baseline, aeo-track, aeo-report, aeo-optimize) reads. Captures the brand name and domain, aliases, competitors, the prompts to track, and spend limits. Supports both interactive prompts (for first-time setup) and flag-driven invocation (for agents). The output conforms to schemas/aeo-config-v1.json and validates against it when jsonschema is available. Use when a user wants to: start a new AEO tracking project, scaffold the config that aeo-baseline reads, regenerate a workspace config from scratch, or add prompts to an existing setup.

Schedule recurring aeo-baseline runs without standing up Airflow, cron-monitor, or any external service. Generates a platform-appropriate scheduled job (launchd on macOS, cron on Linux), a wrapper shell script that loads the workspace's .env and runs aeo-baseline --yes, and tracks install state so the schedule can be inspected or removed cleanly. Default is dry-run — pass --apply to actually install. Multiple workspaces can be scheduled independently; state lives under ~/.aeo-track/<workspace-id>/. Use when a user wants to: set up daily/weekly visibility tracking, automate aeo-baseline so trends accumulate, see what's currently scheduled, or remove a previously-installed schedule.

Take an atomic AI visibility baseline for a brand. Runs each configured prompt 20 times against Gemini with Google Search grounding, extracts every signal (brand mentions, citations, citation position, query fan-out, entities, sentiment, competitor citations) from those same 20 responses, computes Wilson 95% confidence intervals, applies the aeo-v1 visibility score, and writes an append-only JSON evidence file conforming to schemas/aeo-evidence-v1.json. Use when a user wants to: measure where their brand sits in AI search retrieval, establish a starting visibility baseline before content work, produce a single evidence file that aeo-report and aeo-optimize can consume, or get a one-shot visibility snapshot for a specific prompt.

Simulate Google AI Overviews by running prompts through Gemini 3 Flash with Google Search grounding. See which sources get cited, how often, and what snippets get pulled — before checking the real AI Overview. Track a specific domain to measure mention rate, citation rate, and exact excerpts. Use when a user wants to: preview what an AI Overview would look like for a query, see which sources Google's AI cites, measure a domain's citation share, or understand what content Gemini pulls from their site.

Detect when a brand's own pages compete against each other for the same AI prompt citations. Runs prompts through Gemini 3 Flash with grounding and checks if multiple URLs from the same domain get cited across runs. Scores severity (LOW/MEDIUM/HIGH) and recommends consolidation or differentiation. Use when a user wants to: check if their pages cannibalize each other in AI answers, find which pages compete for the same AI prompts, decide whether to consolidate or differentiate competing content, or audit their site's AI citation efficiency.

Compare what different AI models cite for the same prompts. Runs prompts through Gemini 3 Flash with grounding to get Google's citations, then uses web search to approximate what ChatGPT and Perplexity would cite. Identifies gaps: sources cited by Google but not others, by others but not Google, or by all. For a target domain, shows where it appears vs where it's missing across AI citation landscapes. Use when a user wants to: find citation gaps between AI models, understand why they rank on one AI but not another, discover cross-platform AEO opportunities, or compare their visibility across Google AI, ChatGPT, and Perplexity.

Track competitor citations in AI Overviews over time. Runs prompts through Gemini 3 Flash with grounding and records which competitor domains get cited, how often, and with what snippets. Saves results to an append-only JSON data file for trend analysis. Generates comparison reports showing citation share changes over time. Use when a user wants to: track competitors' AI visibility, compare citation share across brands, monitor who's winning AI Overviews for key prompts, or detect when competitors gain or lose AI citations.

Extract the specific entities (brands, people, statistics, tools, URLs) that Gemini mentions in its grounded responses for a given prompt. Aggregates entity frequency across 20 runs to reveal the "entity universe" for a topic. Optionally performs entity gap analysis to show what a specific domain's content should include. Use when a user wants to: see what brands/tools Gemini recommends, find missing entities in their content, understand what statistics AI responses cite, map the competitive entity landscape, or discover which entities to include for better AI citation rates.

Monitor how citation rates change as content ages. Runs prompts against Gemini 3 Flash with grounding and records citation/mention rates over time in an append-only JSON file. Detects decay trends, estimates time until citation loss, and flags pages needing urgent refresh. Use when a user wants to: track citation rate changes over time, detect content decay, find pages losing AI visibility, prioritize content refreshes, or monitor whether content updates restored citations.

Map the exact search queries Gemini 3 Flash fires when answering prompts. Run prompts multiple times with Google Search grounding to capture query frequency, cluster similar queries, identify patterns/themes, and analyze query evolution. Supports single prompts and batch mode (file input). Upgraded version of prompt-frequency-analyzer with richer analysis including query clustering, cross-prompt overlap, and theme detection. Use when investigating: what Google's AI actually searches for, query pattern analysis across related prompts, how to align content with AI search behavior, or comparing query strategies across different prompt phrasings.

Find pages that win across multiple prompts — authority hubs that enter the recurring retrieval set for many query patterns at once. Runs multiple prompts through Gemini 3 Flash with grounding and cross-references which URLs and domains get cited across prompts. Identifies hub pages, single-prompt winners, and gaps. Recommends whether to build comprehensive hub pages or optimize existing single-winners. Use when a user wants to: find which pages win multiple AI prompts, identify authority hub opportunities, decide between one hub page vs many focused pages, discover cross-prompt citation patterns, or build a multi-prompt content strategy.

Analyze what search queries Gemini uses when answering a prompt, by running it multiple times with Google Search grounding and reporting frequency distribution. Use when investigating AEO query patterns, understanding how AI models search the web for a topic, or studying the probabilistic nature of AI-triggered search queries.

Find question-based Google Autocomplete suggestions for any topic. Prepends question modifiers (what, how, why) to a seed topic and returns real autocomplete suggestions — useful for AEO prompt research, content ideation, and understanding what people ask about a topic. Use when the user wants to discover questions people search for, find content angles, or do keyword/prompt research for a topic.

Track AI visibility — measure whether a brand is mentioned and cited by AI assistants (Gemini, ChatGPT, Perplexity) for target prompts. Runs scans, tracks mention/citation rates over time, detects trends, and identifies opportunities. Uses Gemini API free tier (with grounding) as primary method, web search as fallback. Use when a user wants to: check if AI models mention their brand, track AI citation changes over time, measure AEO content effectiveness, monitor competitor AI visibility, or audit their brand's presence in AI-generated answers. Pairs with aeo-prompt-research-free (identifies prompts) and aeo-content-free (creates/refreshes content). This skill closes the loop by measuring results.

Create or refresh AEO-optimized content that gets cited by AI assistants (Gemini, ChatGPT, Perplexity) using only free tools. Two modes: CREATE new content targeting a specific prompt, or REFRESH existing content to improve AI citation-worthiness. Researches what AI models currently cite, builds a competitive brief, and produces citation-worthy content. Use when a user wants to: write content optimized for AI citations, create articles that show up in AI answers, refresh/update existing content for better AI visibility, build authority content for answer engines, or produce AEO content without paid tools. No API keys required — uses web_fetch, web_search (free tier), and LLM reasoning only. Pairs with aeo-prompt-research-free (which identifies WHAT to write about; this skill handles HOW to write or refresh it).

Discover which AI prompts and topics matter for a brand's Answer Engine Optimization (AEO) using only free tools. Crawls a website, analyzes the brand's positioning, generates prioritized prompts people ask AI assistants, and audits existing content coverage — all without paid APIs. Use when a user wants to: find what questions people ask AI about their industry, discover AEO opportunities, research prompts for content creation, audit a site's AI visibility, or build an AEO content strategy. No API keys required — uses web_fetch, web_search (free tier), and LLM reasoning only.