← Back to Skills Marketplace
evan-y25

ai-article-detector

by Evan · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
304
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install ai-article-detector
Description
AI Article Detector - Analyze article links and score AI writing probability (0-100). 100 means 100% likely AI-generated.
README (SKILL.md)

AI Article Detector

检测文章是否由 AI 生成,输出 0-100 的分数。

用途

分析任何网页文章,判断其是否由 AI 生成。基于 8 个独立维度的统计特征分析。

快速开始

node ai-article-detector.js "https://example.com/article"

工作原理

8 维度评分

  1. 词汇多样性 (15%) - Type-Token Ratio
  2. 句子变化 (15%) - 句子长度系数
  3. 段落规律性 (12%) - 段落长度统一度
  4. AI 模板词 (18%) - 转折词频率 ⭐ 最可靠
  5. 文本熵 (10%) - Shannon Entropy
  6. 情感强度 (10%) - 极端词汇比例
  7. 被动语态 (12%) - 被动表达占比
  8. 个性化标记 (8%) - 表情符号使用

分数解释

  • 80-100: 极高概率是 AI
  • 60-79: 较高概率是 AI
  • 40-59: 中等概率是 AI
  • 20-39: 较低概率是 AI
  • 0-19: 极低概率是 AI(人类风格)

特性

  • ✅ 多维度分析
  • ✅ 本地分析(隐私保护)
  • ✅ 秒级响应
  • ✅ 详细分数报告
Usage Guidance
This skill appears to do what it claims: it fetches the article URL you give it and runs local statistical checks to produce a score. Before installing or running it: 1) be aware it will perform HTTP requests to whatever URL is provided — that reveals your agent's IP and User-Agent to the remote host and could be used to access internal endpoints if you pass internal URLs (SSRF-like risk if you supply internal addresses); 2) npm install will download dependencies from the public registry (review or sandbox if you distrust third-party packages); 3) the detector is heuristic/statistical — it can produce false positives and is not legal proof; 4) if you plan to allow autonomous agent invocation, consider restricting which URLs the agent may request or require explicit user confirmation before running the skill against arbitrary links.
Capability Analysis
Type: OpenClaw Skill Name: ai-article-detector Version: 1.0.0 The skill bundle provides a legitimate tool for detecting AI-generated content through statistical analysis of article text. The code in ai-article-detector.js uses standard libraries (node-fetch and jsdom) to retrieve and parse web content, implementing heuristics like Type-Token Ratio and Shannon Entropy locally without any evidence of data exfiltration, remote code execution, or malicious prompt injection. All files, including SKILL.md and the test scripts, are consistent with the stated purpose of article analysis.
Capability Assessment
Purpose & Capability
The name/description (AI Article Detector) aligns with the included code: ai-article-detector.js fetches a webpage, extracts text with jsdom and computes 8 statistical features to produce a 0–100 score. There are no unrelated requirements (no cloud creds, no system binaries).
Instruction Scope
SKILL.md simply instructs running node ai-article-detector.js <URL> and describes the 8-dimension analysis. The runtime will perform an HTTP GET of the provided URL (using node-fetch) and parse the returned HTML locally. This is expected for the stated purpose, but note the network fetch means the remote host will see your request (IP/User-Agent) and the code will retrieve arbitrary content you supply.
Install Mechanism
There is no packaged install spec; package.json lists dependencies (node-fetch and jsdom). Installing will pull these packages from the public npm registry (normal for Node.js tools). This is moderate risk by default because npm packages are third-party code — expected for this skill but worth reviewing or sandboxing before running.
Credentials
The skill requests no environment variables, no credentials, and no config paths. All data access is limited to the URL(s) you provide and local analysis — no unexplained secret access.
Persistence & Privilege
The skill does not request always:true, does not modify other skills or system settings, and is user-invocable only. It can be invoked autonomously by an agent (platform default) but that is not combined with other privilege escalation behaviors here.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install ai-article-detector
  3. After installation, invoke the skill by name or use /ai-article-detector
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
AI Article Detector 1.0.0 - Initial release for detecting AI-generated articles. - Analyzes article links and scores AI-writing probability from 0–100. - Uses 8 independent statistical features including vocabulary diversity, sentence variation, AI template words, and more. - Fast, privacy-friendly local analysis with detailed scoring report. - Simple command-line interface for quick evaluation of any web article.
Metadata
Slug ai-article-detector
Version 1.0.0
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 1
Frequently Asked Questions

What is ai-article-detector?

AI Article Detector - Analyze article links and score AI writing probability (0-100). 100 means 100% likely AI-generated. It is an AI Agent Skill for Claude Code / OpenClaw, with 304 downloads so far.

How do I install ai-article-detector?

Run "/install ai-article-detector" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is ai-article-detector free?

Yes, ai-article-detector is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does ai-article-detector support?

ai-article-detector is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created ai-article-detector?

It is built and maintained by Evan (@evan-y25); the current version is v1.0.0.

💬 Comments