Review Mining SKILL.md skillA

Review Mining from samuraigpt/open-ai-reputation-agent is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add samuraigpt/open-ai-reputation-agent/Review Mining@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
samuraigpt/open-ai-reputation-agent
Path
agents/review-mining/SKILL.md
Versions recorded
3
Latest version
v1.0.0, committed Sep 9, 2026
First version recorded
Aug 26, 2026
Size
4,879 bytes
Repository stars
1
License
MIT

Aggregates and summarizes themes from reviews (Amazon, Google, app stores) to flag reputation risks.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Review Mining

## Mission

Aggregate reviews of a product or business across review platforms (e-commerce, local/Google, app stores) and surface the recurring themes — especially the ones that indicate a reputation risk, like a spike in complaints about a specific defect or service failure.

## Use this agent when

- A brand wants a summary of what reviewers are actually saying instead of reading hundreds of reviews manually.
- A team needs to know if a recent product/service change is showing up as a new complaint theme.
- A brand wants to compare review themes across platforms (e.g. app store vs. e-commerce) or across a competitor.
- A team needs an early-warning signal that a defect or service issue is becoming widespread enough to be a reputation risk.

## Required inputs

- Product or business name/identifier, and the platforms to pull from (e.g. Amazon listing, Google Business listing, app store listing).
- Time window for the review pull (e.g. last 90 days, or all-time for a baseline).
- Optional: star-rating filter (e.g. focus on 1-2 star reviews).
- Optional: a specific change/release date to measure before/after themes around.

## Required connections
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add samuraigpt/open-ai-reputation-agent/Review Mining@sha256:d978fe883e6be857

The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_waukgu3uxxdjagbl.svg)](https://markdownregistry.com/a/art_waukgu3uxxdjagbl)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Aug 26, 2026 and Sep 9, 2026, about one every 7 days.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-09-09 7f3f43f 4,879 BA view · diff
v1.0.02026-09-08 938880a 4,835 BA view · diff
v1.0.02026-08-26 eec0e4b 4,581 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4879 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

samuraigpt/open-ai-reputation-agent · 1 stars · license MIT · pushed 2026-09-29 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_waukgu3uxxdjagbl
GET https://markdownregistry.com/api/v1/resolve?ref=samuraigpt/open-ai-reputation-agent/Review Mining
GET https://markdownregistry.com/api/v1/blob/d978fe883e6be8571d8c2535b67635e63be9d5b3afe57bf627049158831e103d

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from samuraigpt/open-ai-reputation-agent

News Monitoring SKILL.md skill
samuraigpt/open-ai-reputation-agent · agents/news-monitoring/SKILL.md · Tracks news and press mentions of a brand and flags anything requiring a response.
v1.0.0 · audit A · 1 stars
PR & Communications SKILL.md skill
samuraigpt/open-ai-reputation-agent · agents/pr-communications/SKILL.md · Drafts response statements and talking points for a flagged reputation event, for human review before publishing.
v1.0.0 · audit A · 1 stars
Social Sentiment SKILL.md skill
samuraigpt/open-ai-reputation-agent · agents/social-sentiment/SKILL.md · Tracks sentiment trends about a brand across social platforms over time.
v1.0.0 · audit A · 1 stars

Every file in samuraigpt/open-ai-reputation-agent

Browse by kind, by grade A, or by owner.