← Back to Skills Marketplace
phheng

Ebay Review Checker

by Henk Nie · GitHub ↗ · v0.1.0 · MIT-0
cross-platform ⚠ suspicious
117
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install ebay-review-checker
Description
eBay review and feedback authenticity analyzer. Detect fake reviews, suspicious seller feedback patterns, and buyer manipulation. Includes time clustering de...
README (SKILL.md)

eBay Review Checker 🔍

Review and feedback authenticity analyzer for eBay — detect fake reviews, suspicious patterns, and feedback manipulation.

Installation

npx skills add nexscope-ai/eCommerce-Skills --skill ebay-review-checker -g

Features

  • Seller Feedback Analysis — Analyze seller feedback authenticity
  • Buyer Feedback Patterns — Detect suspicious buyer behavior
  • eBay-specific Red Flags — Platform-specific warning signs
  • Progressive Analysis — More data = deeper insights

eBay-Specific Detection

Signal Description
Feedback timing Clustered feedback in short periods
Generic comments "A+++" or "Great seller" patterns
Account age New accounts leaving multiple feedbacks
Transaction patterns Unusual buying/selling patterns

Risk Levels

Score Level Description
70-100 ✅ Low Risk Feedback appears authentic
50-69 ⚠️ Medium Risk Some concerns found
30-49 🔴 High Risk Multiple red flags
0-29 💀 Critical Likely manipulated feedback

Usage

Paste Feedback

Check this seller feedback:

Positive - Great seller, fast shipping! A+++
Positive - Excellent transaction, thank you!
Positive - Perfect! Would buy again.
Negative - Item never arrived.

JSON Input

python3 scripts/analyzer.py '[
  {"content": "A+++ seller!", "rating": "positive", "date": "2024-01-15"},
  {"content": "Fast shipping", "rating": "positive", "date": "2024-01-15"}
]'

Output Example

📊 eBay Feedback Authenticity Report

Seller: example_seller
Feedback Count: 50
Analysis Level: L3

━━━━━━━━━━━━━━━━━━━━━━━━

Authenticity Score: 72/100 ✅

Low Risk - Feedback appears authentic.

━━━━━━━━━━━━━━━━━━━━━━━━

Detection Results

✅ Time Clustering: Normal
⚠️ Generic Comments: 15% (slightly high)
✅ Account Diversity: Good

Part of Nexscope AI — AI tools for e-commerce sellers.

Usage Guidance
Key things to consider before installing: 1) Code/purpose mismatch: the SKILL.md advertises eBay, but the code repeatedly mentions Amazon/ASIN and even prints 'Amazon Review Checker' in reports — confirm whether the logic is suitable for eBay or if the author reused Amazon-centric code. 2) Installation: SKILL.md suggests using npx to fetch a package (external network download). Only run that if you trust the nexscope-ai package source; review the package on npm/GitHub first. 3) Data handling: the tool parses and writes review data to an HTML file. If you plan to analyze sensitive data, run it in an isolated environment and inspect the code for any network calls (look for 'requests', 'urllib', 'socket', 'subprocess', or os.environ reads) in the parts truncated here. 4) If you need true eBay-specific checks (seller IDs, eBay API fields), verify the implementation or prefer a tool explicitly tested for eBay. 5) To improve confidence: get the full, untruncated source and scan it for network I/O and environment access. If you cannot verify the package source or full code, run the scripts offline in a sandbox before giving them any sensitive data.
Capability Analysis
Type: OpenClaw Skill Name: ebay-review-checker Version: 0.1.0 The ebay-review-checker skill bundle is a legitimate tool designed to analyze the authenticity of e-commerce feedback. The Python scripts (analyzer.py, parser.py, and report_html.py) implement standard data processing and visualization logic, such as Jaccard similarity for content, time-series analysis for clustering, and keyword detection for incentivized reviews. No evidence of data exfiltration, malicious execution, or prompt injection was found; a minor inconsistency in documentation (referring to Amazon in some code comments while the skill is for eBay) appears to be a harmless template reuse error.
Capability Assessment
Purpose & Capability
The SKILL.md and metadata claim an eBay-focused reviewer, but the bundled code (docstrings, variables, report footer) repeatedly references Amazon, ASIN, and 'Amazon Review Checker'. This mismatch could be harmless (reused code) but may also mean the analyzer uses Amazon-specific assumptions (ASIN, VP heuristics) that are not appropriate for eBay. Users should verify whether eBay-specific checks are actually implemented and whether outputs reference the correct identifiers.
Instruction Scope
Runtime instructions ask the agent to run the included Python scripts and paste or pass review text/JSON. The scripts parse text, score dimensions (time clustering, content similarity, rating distribution, VP ratio), and generate an HTML report. The instructions do not ask the agent to read unrelated files or environment variables. There is no obvious instruction to transmit data to external endpoints in the provided SKILL.md.
Install Mechanism
The skill has no formal install spec in the registry, but SKILL.md suggests installing via an npx command (npx skills add nexscope-ai/eCommerce-Skills --skill ebay-review-checker -g). That command will fetch code from an external package at install time — verify the package source before running. The included code itself has no obvious external download behavior in the visible portions, but the npx-based install is an external network action and should be treated accordingly.
Credentials
No environment variables, credentials, or config paths are required. The included scripts (parser, analyzer, report generator) do not reference os.environ or secret-bearing config in the provided excerpts. This is proportional to the declared purpose.
Persistence & Privilege
The skill is not marked always:true and uses normal model invocation. There is no sign in the provided files that it modifies other skills or system-wide agent settings. It writes an HTML report to disk (normal for a report generator) but does not request permanent system presence.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install ebay-review-checker
  3. After installation, invoke the skill by name or use /ebay-review-checker
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
Initial release of eBay Review Checker. - Analyze eBay seller feedback for authenticity and manipulation. - Detect fake reviews using time clustering, content similarity, and account behavior. - Identify eBay-specific red flags such as clustered feedback, generic comments, and suspicious transaction patterns. - Scoring system indicates risk level (Low to Critical). - No API key required; supports both text and JSON feedback input.
Metadata
Slug ebay-review-checker
Version 0.1.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Ebay Review Checker?

eBay review and feedback authenticity analyzer. Detect fake reviews, suspicious seller feedback patterns, and buyer manipulation. Includes time clustering de... It is an AI Agent Skill for Claude Code / OpenClaw, with 117 downloads so far.

How do I install Ebay Review Checker?

Run "/install ebay-review-checker" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Ebay Review Checker free?

Yes, Ebay Review Checker is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Ebay Review Checker support?

Ebay Review Checker is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Ebay Review Checker?

It is built and maintained by Henk Nie (@phheng); the current version is v0.1.0.

💬 Comments