Reviewer Footprint Tracker

SKILL: Reviewer Footprint Tracker
A single Google review leaks more than people realize. By anchoring on one venue, capturing the reviewer's author id, and re-scanning nearby businesses for the same author, you reconstruct a geographic footprint from public reviews alone. Optional platform toggles extend the trail to other review sites via web search and to location-tagged posts on X, while scan_depth, review_sort, and country let the operator dial reach, sort order, and localization.

You are running this skill on API Direct via its MCP tools. Execute the steps below yourself by calling the named tools in order — values in <angle brackets> come from a previous step. Then deliver the result described at the end.

INPUTS:
  - business_name (required): <business_name — ASK THE USER>
      A venue the target is known to have reviewed
  - city (required): <city — ASK THE USER>
      The city/area the seed venue is in
  - reviewer_name (required): <reviewer_name — ASK THE USER>
      The target's Google reviewer display name
  - platforms (optional): (optional — e.g. web, twitter)
      Comma-separated list of platforms to run — options: places, web, twitter. Omit to run all of them; name specific platforms to limit the run.
  - scan_depth (optional): 10 (default — override if you like)
      How thoroughly to sweep — sets the number of result pages for the nearby-venue enumeration and the per-venue review re-scan. Higher = wider footprint, slower run.
  - review_sort (optional): newest (default — override if you like)
      Sort order for the per-venue review re-scan: highest_ranking, lowest_ranking, most_relevant, or newest. Defaults to newest for recency.
  - country (optional): (optional — e.g. United States)
      Country to localize Google Places and web results for non-US targets.

PLATFORM SELECTION: some steps are gated with "Only run if {platforms} includes X". If the user supplied a `platforms` value, run only the steps whose platform is listed. If the user did NOT supply `platforms`, run ALL steps — every platform the skill supports.

STEPS:
  1. Tool `search_places` — search_places(query="{business_name} {city}", pages=2)
     Resolve the seed venue's place_id and record its lat/lng as the anchor point. Pass {country} for non-US targets.
  2. Tool `place_reviews` — place_reviews(place_id=<seed_place_id>, sort_by=newest, pages=10, get_sentiment=true)
     Find {reviewer_name}'s review and capture their author_id, author_reviews_link, and the tone/emotion of their writing.
  3. Tool `search_places` — search_places(query="restaurants cafes bars", lat=<venue_lat>, lng=<venue_lng>, zoom=14, pages=10)
     Enumerate venues clustered tightly around the anchor point, the reviewer's likely home or work radius. 10 controls how wide the venue sweep goes (default 5).
  4. Tool `place_reviews` — place_reviews(place_id=<nearby_place_id>, sort_by=newest, pages=10)
     Re-scan each nearby venue for the same author_id to assemble the reviewer's repeat-visit footprint and infer their routine. newest defaults to newest; 10 sets how deep to read each venue's reviews (default 10).
  5. Tool `search_web` — search_web(query="\"{reviewer_name}\" reviews {city}", pages=3)
     Only run if {platforms} includes web: Sweep other review sites (Yelp, TripAdvisor, OpenTable) and public pages for the same named reviewer to extend the footprint beyond Google and surface a fuller name or handle that sharpens cross-platform matching.
  6. Tool `search_twitter` — search_twitter(query="{reviewer_name} {city}", sort_by=most_recent, pages=3, get_sentiment=true)
     Only run if {platforms} includes twitter: Surface the same person's location-tagged posts and check-ins on X to add venues they mention publicly and enrich the pattern-of-life map.

DELIVER: A geographic footprint of the target reviewer mapping the venues they frequent, with an inferred home/work radius and routine — built from matching Google author ids and, when enabled, corroborating mentions from other review sites and X check-ins.

Note: each underlying tool call is billed at its normal endpoint price; get_sentiment adds a small per-page surcharge. Page through results as needed but stop once you have enough to deliver the outcome.