agentsclimarketplace

Apify google ai overview monitoring

Skill johnisanerd/claude-skill-google-ai-overview-monitoring/apify-google-ai-overview-monitoring

Claude/agent skill: track brand visibility inside Google AI Overviews. Installs via npx skills add.

Install
npx -y skills add johnisanerd/claude-skill-google-ai-overview-monitoring --skill apify-google-ai-overview-monitoring

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

  • 19 days oldThe repository was created 19 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Monitor whether a brand or domain is cited in Google AI Overviews with the Apify Google AI Overview API Actor (johnvc/Google-AI-Overview-API). Run a watchlist of queries on a schedule, check ai_overview_present, match your domain against the cited references, and build a citation history keyed by the fetched_at timestamp for AEO and GEO reporting. Use when the user wants google ai overview monitoring or tracking, brand visibility in AI Overviews, AI search visibility checks for a brand or client, answer engine optimization (AEO) or generative engine optimization (GEO) measurement, competitor citation share in AI Overviews, or alerts when a domain drops out of an AI Overview. Pay-per-retrieval billing, MCP-ready for Claude and other AI agents.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

7.4 KB, ~1.7k tokens by cl100k_base, as published. Nobody here has run it

Google AI Overview Monitoring: Brand Citations Over Time

Watch how a brand shows up in Google's AI Overviews. Run a fixed list of queries on a schedule, score each answer for whether your domain is cited, and build a history of citation share for AEO and GEO reporting.

When to use this skill

  • The user wants to monitor or track a brand, domain, or client in Google AI Overviews.
  • They want AI search visibility, AEO, or GEO measurement for a set of queries.
  • They want competitor citation share: which domains AI Overviews cite in their category.
  • They want alerts when a domain drops out of an overview, or when an overview disappears for a money query.

Not for: one-off answer extraction or ad hoc lookups (use the google-ai-overview-api skill), organic rank tracking (this reads the AI Overview only), or other engines' AI answers (see references/actor-index.md for Bing, Brave, and Naver equivalents).

The signals (one row per query per run)

Each row carries ai_overview_present (did an overview show at all), references (each cited source with link, source, index, plus title and snippet when present), text_blocks (the answer text, for brand mentions that are not linked), and fetched_at (the ISO timestamp that keys your time series). gl and hl echo the market targeting so multi-country histories stay separable.

Per query per run, the derived metrics are: overview shown (yes or no), brand cited (any references[].link or references[].source matching your domain), citation position (the matching reference's index), and competitor domains cited (the full source list).

Prerequisites

The Actor

Run it with the Apify CLI

One watchlist poll:

apify actors call "johnvc/Google-AI-Overview-API" -i '{"queries":["best crm for startups","crm with free tier","easiest crm for small business"],"gl":"us","hl":"en"}' \
  --json \
  --user-agent apify-awesome-skills/apify-google-ai-overview-monitoring \
  2>/dev/null

Read a run's rows later, for example from a scheduled run:

apify datasets get-items <DATASET_ID> --format json --user-agent apify-awesome-skills/apify-google-ai-overview-monitoring 2>/dev/null

Every call carries the three flags this repo expects: --json (or --format json), --user-agent apify-awesome-skills/apify-google-ai-overview-monitoring, and 2>/dev/null.

Run it from Claude or another AI agent (MCP)

The Actor is MCP-ready. Add the hosted server URL:

https://mcp.apify.com/?tools=actors,docs,johnvc/Google-AI-Overview-API

Then ask, for example: "Check whether example.com is cited in the Google AI Overview for these ten queries and list who is cited instead." MCP setup docs: https://docs.apify.com/platform/integrations/mcp

Workflow

  1. Define the watchlist. Pick 10 to 50 queries where the brand should appear: category head terms, "best X for Y" picks, and question-style searches customers actually ask. Fix the list so runs stay comparable.
  2. Pin the market. One queries input per market with gl set (keep hl at en; AI Overviews are currently English-only). Run one Actor call per market so histories never mix.
  3. Estimate cost per poll and per month, then confirm with the user. See references/gotchas.md.
  4. Run and score each row. Overview shown: ai_overview_present. Brand cited: match your domain against each reference's link or source (compare registered domains, not exact hosts, so www and subdomains still match). Unlinked mentions: scan the snippet text in text_blocks. Competitors: tally every other source.
  5. Append to history and report. Store rows keyed by query plus fetched_at. Report citation share (cited queries over queries with an overview), new and lost citations since the last poll, and the top cited competitor domains.
  6. Schedule it. Save the input as an Apify task and attach a schedule (daily or weekly), or cron the CLI call. Alert when a previously cited query loses the citation or loses its overview.

Inputs

  • queries (array of strings): the fixed watchlist; merged with query and deduped
  • query (string): single-query alternative; at least one of the two is required
  • gl (string, default us): two-letter country code, one market per run
  • hl (string, default en): keep en
  • location (string): optional named location for local-intent watchlists

Cost

Billing is pay per event: a small setup fee per run plus a fee per AI Overview retrieval, about $0.015 each at the time of writing. A daily 20-query poll is about $0.31 per run, roughly $9.40 per month; weekly is about $1.35 per month. Deferred answers cost one extra retrieval each. Estimate with the live prices in references/gotchas.md before scheduling.

Honest limits

  • This is a polled monitor, not a push feed: freshness is your schedule interval.
  • AI Overviews are not deterministic. Text and cited sources can change between identical runs, so judge trends over several polls, not single flips.
  • Queries without an overview still cost a lookup, and ai_overview_present: false is itself a signal worth logging.
  • English-only for now, in a limited set of countries; there is no historical backfill, so the history starts when your polling starts.

Troubleshooting

  • Citation flapping between polls: expected variance; alert only after two or three consecutive misses.
  • Domain never matches: compare registered domains, and check references[].link as well as source (some references carry only link, source, and index).
  • Whole watchlist shows no overviews: check hl is en, try gl at us, and rephrase head terms as questions.

See references/gotchas.md for cost guardrails and error recovery, and references/actor-index.md for the Actor routing table.

Related answer-engine Actors

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.