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.