AI Content Detection

概要

The AI Content Detection skill, hosted within the TerminalSkills/skills repository, provides a multi-tiered framework for identifying machine-generated text. It employs a three-step methodology to ensure accuracy: initial rule-based analysis focusing on linguistic and statistical patterns, a secondary evaluation where Claude acts as a judge against specific detection rulesets, and optional corroboration through external APIs such as GPTZero or Originality.ai. Compatible with agents like Claude-code, Cursor, and Gemini, this tool assists users in verifying document authenticity. By leveraging both internal logic and third-party validation, the skill offers a structured approach to content review and research. The TerminalSkills repository, which currently holds 71 stars, serves as the primary source for this utility's implementation and documentation.

ユースケース

導入方法

# Review source first
open https://github.com/TerminalSkills/skills/blob/main/skills/ai-content-detection/SKILL.md

Copy or clone the skill folder into your agent skills directory after reviewing its instructions and scripts.

セキュリティ

This skill utilizes a combination of local rule-based analysis and external calls to LLMs or third-party APIs. Users should be aware that content is processed by Claude for scoring and may be sent to external services like GPTZero or Originality.ai if those optional features are enabled. Review the TerminalSkills repository documentation for specific data handling practices related to these external integrations.