Review Management logo

Review Management

Community
garrettjsmith
review-management

When the user wants to generate more reviews, respond to reviews, build a review strategy, or manage online reputation. Also use when the user mentions "reviews," "reputation management," "review generation," "review response," "star rating," "negative reviews," or "get more Google reviews." For GBP profile optimization, see gbp-optimization.

Overview

Publishergarrettjsmith
Repositorylocalseoskills
Skill namereview-management
Stars
140
Forks
27
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by garrettjsmith on GitHub. Read the source before you install it.

Installation

Install the Review Management AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/garrettjsmith/localseoskills/tree/main/skills/review-management
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/garrettjsmith/localseoskills.git /tmp/localseoskills
mkdir -p .claude/skills
cp -r /tmp/localseoskills/skills/review-management .claude/skills/review-management
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Review Management in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Review Management on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Review Management is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Review Management

Default data tool: LocalSEOData (localseodata-tool). Use google_reviews for recent reviews, review_velocity for trends over time, multi_platform_reviews for cross-platform data, reputation_audit for full reputation assessment. For review generation campaigns, use Whitespark.

You are an expert in local business review strategy. Your goal is to help businesses generate authentic reviews, respond effectively, and leverage reviews as both a ranking signal and conversion tool.

Initial Assessment

Before building a strategy, understand:

  1. Current State: Total reviews, average rating, review velocity, response rate
  2. Competitors: How many reviews do top-3 map pack competitors have?
  3. Channels: Google, Yelp, Facebook, industry-specific (Healthgrades, Avvo, etc.)
  4. Capacity: Who handles review responses? How quickly?

Reviews as a Ranking Factor

The #1 thing to understand about reviews and rankings: recency beats volume.

The number of reviews you've gotten THIS MONTH matters more than your total count. There's a direct, documented correlation: when businesses stop getting new reviews, rankings drop. When they resume, rankings recover. Review recency is a top-5 ranking factor as of 2025-2026.

This means a business with 500 total reviews but none in 90 days will lose ground to a competitor with 100 reviews getting 8/month. Stop optimizing for total count — optimize for consistent flow.

Reviews impact local rankings through:

  • Recency: Recent reviews weighted most heavily. A steady cadence is the strongest review signal
  • Velocity: Consistent flow over time (not bursts). Daily/weekly review requests, not quarterly campaigns
  • Volume relative to competitors: Total count matters, but only in context of your market
  • Rating: Higher average = stronger signal
  • Keywords: Natural mention of services/locations in review text
  • Diversity: Reviews across platforms, not just Google

Review Generation Strategy

The Ask Framework

  1. Identify the moment: After service completion, positive interaction, or milestone
  2. Ask in person first: Verbal ask is highest-converting
  3. Follow up digitally: SMS > Email for response rates
  4. Make it easy: Direct link to Google review form
  5. Don't incentivize: Offering rewards for reviews violates Google guidelines

Google Review Link

Generate a direct review link:

https://search.google.com/local/writereview?placeid=YOUR_PLACE_ID

Or short link via GBP dashboard.

Channel Priority

  1. Google — Primary ranking signal, highest visibility
  2. Industry-specific — See industry platforms table below
  3. Facebook — Social proof, recommendations
  4. Yelp — Don't ask directly (Yelp penalizes solicitation)

Industry-Specific Review Platforms

Different verticals have review platforms that carry outsized weight with consumers and often influence search rankings.

Healthcare (Medical, Dental, Chiropractic):

  • Healthgrades — Highest authority for doctor searches, often outranks the practice's own site
  • WebMD — Significant consumer trust; negative reviews here damage reputation disproportionately
  • Vitals — Used by insurance networks for doctor discovery
  • ZocDoc — Combines reviews with appointment booking; high conversion platform
  • RateMDs — Particularly relevant in markets near Canada (cross-border patients)
  • Doximity — Physician peer network, not consumer-facing but affects referrals

Legal:

  • Avvo — Dominant for attorney searches; Avvo rating is its own ranking system
  • Martindale-Hubbell — Oldest legal directory; peer ratings carry weight
  • Lawyers.com — Consumer-facing FindLaw property
  • Super Lawyers — Selection-based (not open reviews) but high authority
  • Google remains critical — most people search Google, not legal directories

Home Services (HVAC, Plumbing, Electrical, Roofing):

  • Angi (formerly Angie's List) — Paid lead platform with reviews
  • HomeAdvisor — Now merged with Angi; still has separate review ecosystem
  • Thumbtack — Strong in some markets, particularly for smaller jobs
  • Houzz — Dominant for remodeling, design, and construction
  • BBB — Accreditation matters to older demographics; complaints are visible in search

Restaurants & Hospitality:

  • Yelp — Actually critical in this vertical (unlike others where it's secondary)
  • TripAdvisor — Essential for tourism-dependent restaurants
  • OpenTable — Reviews tied to actual diners (verified)
  • DoorDash/Uber Eats — Ratings on delivery platforms now affect discovery

Automotive:

  • DealerRater — Primary review platform for dealerships
  • Cars.com — Reviews visible in vehicle shopping flow
  • Edmunds — Consumer research phase reviews
  • CarGurus — Growing platform with dealer reviews

Real Estate:

  • Zillow — Agent reviews integrated into property search
  • Realtor.com — Reviews visible to active homebuyers
  • Homes.com — Growing review platform

Financial Services:

  • NerdWallet — Reviews for banks, credit unions, financial advisors
  • Bankrate — Consumer finance reviews
  • FINRA BrokerCheck — Not reviews per se, but public record that shows in searches

Industry-Specific Response Rules

Healthcare — HIPAA compliance (CRITICAL):

  • NEVER confirm or deny someone is a patient
  • NEVER reference diagnoses, treatments, medications, or appointments
  • NEVER share any Protected Health Information, even if the reviewer mentioned it first
  • Safe response pattern: "Thank you for your feedback. We take all patient experiences seriously. Please contact our office at [phone] to discuss your concerns."
  • Train ALL staff who might respond to reviews on HIPAA

Legal — Attorney-client privilege:

  • Similar to HIPAA — never confirm someone is/was a client
  • Don't reference case details, outcomes, or legal strategy
  • Check state bar advertising rules before using client testimonials in marketing

Home services — Photo responses:

  • Encourage customers to include photos of completed work in reviews
  • Respond with project details (general, not customer-specific): "That kitchen remodel was a great project — glad you love the tile work!"
  • Photo reviews are worth 3-5x a text-only review for conversion

Cadence Targets

Business SizeMonthly TargetRationale
Solo/small4-8 reviewsSteady growth without looking suspicious
Medium (5-20 employees)10-20 reviewsMatch competitor velocity
Large/multi-location20-50+ per locationEnterprise-level volume

What NOT to Do

  • Don't buy reviews — ever
  • Don't gate reviews (only sending happy customers to Google)
  • Don't use review kiosks in-office (same IP = flagged)
  • Don't incentivize with discounts or gifts
  • Don't write reviews yourself or have employees do it
  • Don't get 50 reviews in a week then zero for months

Review Response Strategy

Why Respond to Every Review

  • Google confirms responses are a ranking factor
  • Shows future customers you're engaged
  • Opportunity to add keywords naturally
  • Turns negative experiences into recovery stories

Response Framework: Positive Reviews

  1. Thank them by name
  2. Mention the specific service they referenced
  3. Add a natural keyword/location reference
  4. Keep it genuine — vary your responses (don't copy-paste)

Example:

Thanks, Sarah! We're glad the AC installation went smoothly. Our Buffalo team takes pride in getting systems running before the summer heat. See you for your annual tune-up!

Response Framework: Negative Reviews

  1. Acknowledge: Thank them for the feedback
  2. Apologize: For the experience (not admitting fault)
  3. Take offline: Provide a direct contact for resolution
  4. Don't argue: Other customers are reading this

Example:

Hi Mark, thank you for sharing your experience. We're sorry the timeline didn't meet your expectations — that's not the standard we set for our customers. Please reach out to [name] at [phone] so we can make this right.

Response Timing

  • Positive: Within 24-48 hours
  • Negative: Within 4-12 hours (faster signals responsiveness)
  • Questions in reviews: Treat as Q&A, answer specifically

Handling Fake/Spam Reviews

Identification

  • Reviewer has no other reviews or photo
  • Review doesn't describe an actual experience
  • Reviewer was never a customer
  • Competitor leaving negative reviews
  • Review text is generic or nonsensical

Removal Process

  1. Flag the review in GBP (⋮ menu → Flag as inappropriate)
  2. Report via Google Business support
  3. Use the Google Reviews removal form with evidence
  4. If from a competitor, document the pattern
  5. Don't respond aggressively — respond professionally, then flag

When Removal Fails

  • Respond professionally for public record
  • Bury it with genuine positive reviews
  • Report repeatedly if it clearly violates guidelines
  • Consider legal options for defamatory reviews (last resort)

Review Monitoring

What to Track

  • New reviews across all platforms (weekly minimum)
  • Average rating trend
  • Review velocity vs. competitors
  • Keyword mentions in reviews
  • Response rate and response time
  • Sentiment trends

Tools

  • Google Business Profile notifications
  • Review aggregation tools (BirdEye, Podium, GatherUp)
  • Google Alerts for brand mentions
  • Manual platform checks weekly

Output Format

Review Strategy Document

  • Current review landscape (you vs. competitors)
  • Review generation plan with specific tactics
  • Response templates (customizable, not copy-paste)
  • Monitoring cadence and responsibility
  • 90-day targets

Task-Specific Questions

  1. How many Google reviews do you currently have?
  2. What's your current review velocity (reviews/month)?
  3. How many reviews do your top map pack competitors have?
  4. Who will be responsible for review responses?
  5. What's your primary method of customer communication (email, SMS, in-person)?

What to Do Next

What You FoundNext ActionSkill
Reviews improving but profile still not optimizedReviews amplify a strong profile — complete GBP optimizationgbp-optimization
Need to benchmark review count against competitorsRun competitive analysis focused on review metricslocal-competitor-analysis
Reviews are part of a broader auditFeed review findings into the full audit reportlocal-seo-audit
Review strategy running but rankings still weakReviews are one signal — run a geogrid scan to identify other gapsgeogrid-analysis
Need industry-specific review platform strategySee the Industry-Specific Review Platforms section above

Default next step: Set a 90-day review target (count + velocity). Measure monthly. If velocity drops, the generation process broke — fix the system, not the goal.

Tools for This Skill

See docs/tool-routing to pick based on what's connected.

  • Review monitoring (track reviews across platforms) → review monitoring tools (multiple options)
  • Review generation (automated request campaigns) → Whitespark Reputation Builder (primary option)
  • Review analysis (AI-powered sentiment and competitor comparison) → Local Falcon Reviews Analysis

Frequently asked questions

What does the Review Management AI skill do?

When the user wants to generate more reviews, respond to reviews, build a review strategy, or manage online reputation. Also use when the user mentions "reviews," "reputation management," "review generation," "review response," "star rating," "negative reviews," or "get more Google reviews." For GBP profile optimization, see gbp-optimization.

Why use Review Management on TypingMind?

Because you install it once and use it with any model. Review Management is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Review Management in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/garrettjsmith/localseoskills/tree/main/skills/review-management. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Review Management?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Review Management?

As many as you like. As long as a model supports skills, you can use Review Management with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Review Management AI skill free?

Yes. It is published on GitHub by garrettjsmith under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇