Services How it works About Pricing Skills AI Assessment Start a project
Business Ops

Review Responder.

A free Claude skill that writes review replies the way a sharp owner would — thanking without gushing, owning real mistakes, calmly flagging fakes — always written for the real audience: the next hundred people reading.

Free · MIT licensed · Works in Claude Code, Claude.ai & the API
What it does

The reply is marketing. The review is just the prompt.

Future customers judge the owner by the response, not the rating. This skill classifies the review first, then writes the reply that wins the readers.

  • Five review types — positive, legit-negative, vague-negative, fake, and false-claims — each with its own structure and goal.
  • Owner-voice rules — first-name sign-off, one echoed detail, no canned openers, 1–3 sentences for praise.
  • De-escalation built in — own your share, correct facts once, move it offline with a direct number.
  • HIPAA-aware — for dentists, doctors, and lawyers: never confirms someone was a patient or client.
  • Flags the real problem — when a review exposes an operational issue, the output says so — the reply is damage control, the fix is the work.

Who it's for

Any business the public can rate: restaurants, salons, contractors, dentists, shops, auto repair. Especially owners who either freeze on bad reviews or answer them angry — both cost real money.

Also handy for whoever manages reviews on the owner's behalf and needs replies that still sound like the owner.

What you say to trigger it

“We got a 1-star review.” · “Reply to this Google review.” · “I think this review is fake — what do I do?”

Example output

A 1-star review, and the owner's side of the story.

You tell Claude: “One star — ‘Tech showed up 3 hours late, no call, then the invoice was $80 over the quote.’ He's right about the lateness, and the $80 was a billing mistake we've already refunded.” Here's what comes back:

No “we regret any inconvenience,” no arguing, no public coupon. Ownership, the fix, and a phone number — that's the skill working.

How to install

Three ways in. All free.

Option 1 · Claude Code

One command

In your terminal, run:

npx skills add buildwithreef/claude-skills

Pick review-responder from the list (or install the whole set). Done.

Option 2 · Claude.ai

Upload the zip

Download the .zip below, then in Claude.ai go to Settings → Capabilities → Skills and upload it.

Download review-responder.zip

Option 3 · Manual

Copy the file

Copy the SKILL.md below into ~/.claude/skills/review-responder/SKILL.md. The zip also includes the worked-examples playbook the skill loads before drafting.

review-responder/SKILL.md
---
name: review-responder
description: Writes owner responses to Google, Yelp, and Facebook reviews — positive, negative, or fake — in an authentic local-business voice. Use when the user wants to reply to a customer review, handle a bad review, deal with a fake or wrong-business review, or says things like "how should I respond to this review", "we got a 1-star", or "write a reply to this Google review".
---

# Review Responder

Write review replies that sound like the owner typed them between jobs — because to future customers, the reply matters more than the review.

## Step 1 — Read the review, then classify it

Ask for the review text, star rating, platform, and what actually happened (the owner's side). Then classify:

| Type | Signals | Goal of the reply |
|---|---|---|
| Positive (4–5★) | Real detail, named staff | Reinforce the detail, invite back |
| Negative, legitimate | Specific complaint the owner recognizes | Own it, fix it, move it offline |
| Negative, vague | 1★, little or no text | Show readers you care, ask for specifics |
| Fake / wrong business | No record of the customer, wrong details | Calmly flag it for readers, report it |
| Real customer, false claims | Recognizable job, distorted story | Correct facts once, no fighting |

Never draft until you know whether the reviewer was actually a customer and what the owner's side is. If the user just pastes a review, ask those two things first.

## Step 2 — Apply the voice rules

- Sign with the owner's first name. Replies from "The Management Team" convince no one.
- Echo one specific detail from the review. It proves a human read it.
- Positive replies: 1–3 sentences. Gushing at a 5-star review reads as desperate.
- Never open two replies in a row the same way. Vary the opener or skip the thank-you.
- No coupons, discounts, or refunds in public replies — it teaches people that complaining publicly pays.
- Write for the next 100 readers, not the one reviewer. They are the real audience.
- Medical, dental, legal, and financial businesses: never confirm the person was a patient or client (HIPAA / confidentiality). Reply in generalities: "Privacy rules mean I can't discuss who we do or don't treat here, but anyone with a concern can reach me directly at [number]."

## Step 3 — Structure by type

**Negative, legitimate (the one that matters most):**
1. Name the specific issue. Banned: "we regret any inconvenience" and every phrase shaped like it.
2. Own your share plainly: "We were late. That's on us."
3. Say what changed or what you'll do about it.
4. Move it offline with a direct line: "Call me at [number] and I'll make it right."
5. Keep it 3–5 sentences. Longer reads as defensive.

**Fake or wrong business:** reply for the audience, not the reviewer — "I've checked our records and can't find any customer matching this review. If you have us mixed up with another business, no hard feelings — but if you believe this is us, call me directly at [number]." Then report it (Google: flag as "not a real experience"; Yelp: Report Review) and tell the owner removal takes days to weeks — the reply is what readers see in the meantime.

**Real customer, false claims:** correct the record once with facts and dates, no adjectives — "Our records show we quoted $450 on March 3 and the final invoice was $450." — then the offline invitation. Never trade blows in a thread.

Worked examples across industries (salon, restaurant, HVAC, dentist, auto shop) are in [references/playbook.md](references/playbook.md). Load it before drafting.

## Step 4 — Deliver

```
**Type:** Negative, legitimate — 2★ on Google
**Reply:**

[reply text]

**Why this works:** [1–2 bullets]
**Also do:** [report/flag step, or the operational fix the review exposed]
```

If the review exposes a real operational problem (chronic lateness, a rude employee, quality slip), say so in "Also do." The reply is damage control; the fix is the actual work.

## What not to do

- Don't reply while the owner is still angry. If the situation is hot, draft it and recommend posting after 24 hours.
- Don't argue point-by-point. One factual correction maximum.
- Don't stuff keywords ("Best plumber in Des Moines thanks you!") — reads as spam to humans, does nothing for rankings.
- Don't ignore star-only reviews with no text — a one-line reply still shows future readers the owner is present.
- Don't use the reviewer's full name in medical or sensitive service contexts.

---

Built by Reef — AI systems for small business → https://buildwithreef.com
FAQ

Claude skill for review responses — common questions

Is there a Claude skill for responding to Google reviews?

Yes — this one. Review Responder is a free, open-source Claude skill that writes owner replies to Google, Yelp, and Facebook reviews. It classifies the review first — positive, legitimate complaint, vague, fake, or false claims — then writes a reply with the right structure for that type, in a voice that sounds like a real owner rather than a support bot.

How do I install the Review Responder Claude skill?

Three ways: run npx skills add buildwithreef/claude-skills in your terminal and select review-responder (Claude Code), upload the .zip from this page in Claude.ai under Settings → Capabilities → Skills, or copy the SKILL.md above into a folder at ~/.claude/skills/review-responder/.

Can it handle fake reviews or reviews meant for another business?

Yes. For fakes it writes a calm reply aimed at future readers — stating there's no record of the customer and offering a direct line — and walks you through reporting the review on Google or Yelp. It also sets honest expectations: removal takes weeks, so the public reply does the work in the meantime.

Will the replies sound like a chatbot wrote them?

No. The skill enforces owner-voice rules: sign with a first name, echo one specific detail from the review, keep praise replies to three sentences, never repeat the same opener, and never post corporate apology phrases like 'we regret any inconvenience.'

Is it really free?

Yes. MIT licensed, no signup, no catch. It's published by Reef, an Iowa-based studio that builds AI systems, websites, and automation for small businesses. If you'd rather have this whole workflow running done-for-you, that's the work Reef takes on.

Related skills

Goes well with

From the builder

Want reviews handled without thinking about them?

Reef builds review systems for small businesses — automatic post-job review requests, alerts when something needs the owner, and replies queued for one-click approval.