review-replies
Skill0 starsChanged 35 days agoMITView on GitHub
Draft owner-approved replies to customer reviews, positive or negative, in the owner's voice. Use when the user pastes one or more reviews and asks how to respond.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- codebywater/WB-OZON-AI-TEAMtheir own version, first seen Oct 25, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- codebywater/WB-OZON-AI-TEAM★ 2same 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 repository6 other files it gives its agents.
- ai-visibilitySkill
- domain-checkupSkill
- local-schemaSkill
- map-pack-gapSkill
- presence-auditSkill
- review-requestsSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Facts you do not have: ask the owner. Do not invent what happened on the job.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Review replies
Reviews to answer: $ARGUMENTS
Draft one reply per review for the owner to approve before posting.
- Positive (4 or 5 stars): thank them by first name, repeat one specific detail from their review, two or three sentences, no sales pitch, no keyword stuffing.
- Mixed or negative (1 to 3 stars): one apology at most, the facts stated calmly without arguing, and an offline route with a named person and how to reach them. Never reveal private details about the customer or the job, never accuse the reviewer of lying, and never offer anything in exchange for changing the review.
- Facts you do not have: ask the owner. Do not invent what happened on the job.
Return the replies as a numbered list matching the reviews, each headed by the star rating and the reviewer's first name. Under each negative reply, add one line for the owner on what to change in the business so the same review does not happen again. No em dashes.
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.