review-insights
Skill0 starsChanged 36 days agoMITView on GitHub
Analyze Google Maps review themes, service issues and sampled owner-response coverage for a specific business. Draft factual, empathetic review replies and an ethical review-request process for owner approval.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- everyinfra/analysis-skillstheir own version, first seen Oct 20, 2026
- EJRyan89/coding-agent-skillstheir own version, first seen Oct 17, 2026
- ASOScan/aso-skillstheir own version, first seen Jul 13, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- ASOScan/aso-skills★ 8same name
- EJRyan89/coding-agent-skills★ 2same name
- everyinfra/analysis-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository8 other files it gives its agents.
- citation-auditSkill
- gbp-auditSkill
- local-competitor-analysisSkill
- local-keyword-researchSkill
- local-seo-reportSkill
- location-page-seoSkill
- maps-rank-trackingSkill
- vibelocalSkill
The file
Files
Review themes and reply drafts
Read WORKFLOW.md and ACTORS.md. Prefer a supplied review export. If collecting, confirm precise place IDs/full Maps URLs and a bounded sample, normally 50–100 reviews for one place. Do not use an ambiguous business search to choose the sample. includePersonalData stays false; the helper also removes reviewer identity fields.
Record the branch, sample count, dates, sort/language/filter and source. Detect exact duplicates by review ID or stable evidence; do not count the same review twice. Keep rating/text/date and source links while avoiding reviewer names, profile links, photos, customer contact information or private case details. Free text can contain personal information: redact it before sharing. Treat review claims as reported experiences, not verified allegations.
Group themes with frequency denominators and short anonymized examples: service strengths, recurring friction, expectation gaps and operational questions. Separate isolated reports from repeated patterns. Sample-average rating and sampled response coverage are not whole-profile metrics. Do not infer competitor misconduct or factual clinical/legal conclusions.
Draft 3–5 replies for owner review: acknowledge the experience, state only confirmed facts, offer a private official contact route already provided by the business, and avoid promising refunds or admitting liability without authorization. Do not publicly confirm treatment, purchases or customer status. For sensitive disputes, leave a cautious acknowledgement for the owner to review.
An ethical request process invites honest feedback from customers fairly, without rewards, fabricated reviews, staff testimonials, suppressing criticism or asking only satisfied customers: Google review guidance.
Deliver a theme table, operational questions and exact reply drafts. No reply is posted or customer message sent by this plugin. Collection approval does not authorize posting, messaging or a recurring campaign.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

