review-responder
Skill1 starsChanged 5 months agoMITView on GitHub
Write a public reply to a Google or Yelp review — positive or negative — that reads like a real person and doubles as marketing. Use when the user says "reply to a review", "respond to a Google review", "Yelp reply", "answer a bad review", "review response", or "respond to feedback".
5 other projects use a version of this.
Adopted by
Most recently taken up by
- ARCASSystems/FounderOStheir own version, first seen Oct 24, 2026
- alumpe/skillstheir own version, first seen Sep 11, 2026
- nawazxz/20-claude-skills-for-businesstheir own version, first seen Aug 12, 2026
- buildwithreef/claude-skillstheir own version, first seen Jul 2, 2026
- emd-ai/trades-claude-skillstheir own version, first seen Mar 1, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- ARCASSystems/FounderOS★ 7same name
- emd-ai/trades-claude-skills★ 2same name
- alumpe/skills★ 0same name
- buildwithreef/claude-skills★ 0same name
- nawazxz/20-claude-skills-for-business★ 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 repository3 other files it gives its agents.
The file
Files
Review Responder
Reply to a Google or Yelp review, positive or negative.
When to use
Someone left a public review and you need a reply that everyone reading can see — warm for a good one, accountable for a bad one, never a template.
What you'll need
The review text, the star rating, and the reviewer's name (if shown).
Instructions
Collect any missing inputs from the user, then run this prompt:
You write public replies to customer reviews for my business. These replies are seen by everyone, not just the reviewer, so they double as marketing.
The review:
- Reviewer name: [name, or "anonymous"]
- Rating: [e.g. 2 stars]
- Platform: [Google / Yelp / other]
- Review text: [paste the full review]
About my business: [one line — what you do and your style, e.g. "family-run pizzeria, friendly and direct"]
Write a reply that:
- Thanks them by name and references something specific they mentioned (not generic).
- For a negative review: acknowledges the issue without excuses, says what I'm doing about it, and invites them to contact me directly to make it right (give them this contact: [email or phone]). Never argue or blame the customer.
- For a positive review: is genuinely warm, reinforces what they liked, and gently invites them back — without sounding like a template.
- Stays under 75 words and sounds like a real person.
Give me two versions to choose from.Tip: For negative reviews, never debate facts in public — move the details to a private channel. A calm, accountable reply impresses future customers more than "winning" the argument.
Built by Ootto — the AI autopilot that connects your tools once and runs invoicing, follow-up, and reports for you, automatically. Book a demo →
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.