真实性验证技能

SkillCommunication

Lets your agent check whether a message, image, or claim is fake, AI-generated, or misleading.

Then ask your AI: use the 真实性验证技能 skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.

No other account needed.

Add it as a step in a pipeline you build on Ahel, or connect Ahel to Claude, ChatGPT, Cursor, Claude Code or Codex and ask your AI to use it.

About this skill

Authenticity verification skill. Analyzes user-provided information, messages, images, or content to assess its authenticity and credibility, identifying misinformation, AI-generated content, or forged content.

What this skill tells your AI

The instructions your AI receives, as published by rtgs2017/nagaagent in skills/verify-authenticity/SKILL.md and read by Ahel’s review.

分析内容的真实性，帮助用户识别虚假信息和伪造内容。

执行流程（必须按顺序执行）

联网搜索：先使用工具搜索与用户内容相关的权威信息和事实依据，调用方式如下：

{"agentType": "openclaw", "task_type": "message", "message": "搜索：用户提供的关键内容"}

交叉比对：工具返回结果后，将用户内容与搜索到的权威来源进行对比
综合判断：结合搜索结果和以下分析维度给出结论

注意：真实性验证必须基于事实依据，第1步的联网搜索不可跳过。

分析维度

信息来源是否可靠
内容逻辑是否自洽
是否存在常见的伪造特征
与搜索到的已知事实是否矛盾
是否存在情绪操控或诱导话术

输出格式

真实性判断：真实 / 可疑 / 高风险
搜索验证：列出搜索到的关键事实依据
分析理由：逐条列出判断依据
建议操作：应该怎么做

Signals

GitHub stars: 2k
Forks: 165
Last commit: Aug 2026

Advanced

Item type: skill
Key: verify-authenticity
Source: github.com/rtgs2017/nagaagent

github.com/rtgs2017/nagaagent