AI Content Detection

Detect whether text was written by a human or generated by AI using a multilayer approach: 1. Rulebased analysis — linguistic patterns and statistical indicators 2. LLMasjudge — use Claude to score content against a detection ruleset 3. External APIs — optional GPTZero or Originality.ai for corroboration

概览

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.

使用场景

Verifying the authenticity of submitted research documents or academic papers.
Auditing marketing copy to ensure human-centric tone and original authorship.
Cross-referencing internal linguistic analysis with external detection APIs for high-stakes content reviews.

安装说明

# 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.

安全提示

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.

相关 Skills

Claude API

anthropics/skills

编程开发

Claude API / Anthropic SDK 参考指南 — 模型 ID、定价、参数、流式传输、工具使用、MCP、智能体、缓存、Token 计数、模型迁移。 TRIGGER — 阅读 BEFORE 并打开目标文件;不要因为它“看起来像一行代码”就跳过 — 每当:提示词以任何形式提及 Claude/Anthropic(Claude、Anthropic、Fable、Opus、Sonnet、Haiku、`anthropic`、`@anthropic-ai`、`claude-*`、`us.anthropic.*`、`[1m]`);用户询问关于 LLM(定价/模型选择/限制/缓存)时 — 绝不回答

Claude CodeClaude
typescriptpython
171,224 StarsApache-2.0

Doc Coauthoring

anthropics/skills

文档处理

引导用户完成文档共同创作的结构化工作流。当用户想要编写文档、提案、技术规范、决策文档或类似的结构化内容时使用。此工作流可帮助用户高效地传递上下文,通过迭代完善内容,并验证文档对读者的有效性。当用户提到编写文档、创建提案、起草规范或类似的文档任务时触发。

Claude CodeClaude
designtesting
171,224 Stars已链接来源

MCP Builder

anthropics/skills

编程开发

创建高质量 MCP (Model Context Protocol) 服务器的指南,使 LLM 能够通过设计良好的工具与外部服务进行交互。在构建 MCP 服务器以集成外部 API 或服务时使用,无论是使用 Python (FastMCP) 还是 Node/TypeScript (MCP SDK)。

CodexClaude
typescriptpython
171,224 StarsApache-2.0

Skill Creator

anthropics/skills

编程开发

创建新技能、修改和改进现有技能,并衡量技能性能。适用于用户希望从零开始创建技能、编辑或优化现有技能、运行评估以测试技能、通过方差分析对技能性能进行基准测试,或优化技能描述以提高触发准确性的场景。

Claude CodeClaude
pythondesign
171,224 StarsApache-2.0

CI Cd And Automation

addyosmani/agent-skills

DevOps

自动化 CI/CD 流水线设置。适用于设置或修改构建和部署流水线。当需要自动化质量门禁、在 CI 中配置测试运行器或建立部署策略时使用。

typescriptsecurity
89,319 StarsMIT

API And Interface Design

addyosmani/agent-skills

编程开发

指导稳定的 API 和接口设计。适用于设计 API、模块边界或任何公共接口。在创建 REST 或 GraphQL 端点、定义模块间的类型契约或建立前后端边界时使用。

typescriptfrontend
89,319 StarsMIT