detect-ai by humanizerai/agent-skills
npx skills add https://github.com/humanizerai/agent-skills --skill detect-ai使用 HumanizerAI API 分析文本,以判断其是否由 AI 编写。
当用户调用 /detect-ai 时,您应该:
$ARGUMENTS 中提取文本向 https://humanizerai.com/api/v1/detect 发送 POST 请求:
Authorization: Bearer $HUMANIZERAI_API_KEY
Content-Type: application/json
{
"text": "<用户文本>"
}
API 返回如下 JSON:
{
"score": {
"overall": 82,
"perplexity": 96,
"burstiness": 15,
"readability": 23,
"satPercent": 3,
"simplicity": 35,
"ngramScore": 8,
"averageSentenceLength": 21
},
"wordCount": 82,
"sentenceCount": 4,
"verdict": "ai"
}
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
重要提示: 主要的 AI 分数是 score.overall(不是直接的 score)。这是要向用户显示的分数。
## AI 检测结果
**分数:** [score.overall]/100 ([verdict])
**分析的词数:** [wordCount]
### 指标
- Perplexity: [score.perplexity]
- Burstiness: [score.burstiness]
- Readability: [score.readability]
- N-gram Score: [score.ngramScore]
### 建议
[根据 score.overall 的值,建议是否需要进行人性化处理]
如果 API 调用失败:
HUMANIZERAI_API_KEY 是否已设置每周安装量
108
代码仓库
GitHub 星标数
10
首次出现
2026年2月3日
安全审计
安装于
gemini-cli102
opencode101
codex100
cursor98
kimi-cli94
github-copilot93
Analyze text to determine if it was written by AI using the HumanizerAI API.
When the user invokes /detect-ai, you should:
Make a POST request to https://humanizerai.com/api/v1/detect:
Authorization: Bearer $HUMANIZERAI_API_KEY
Content-Type: application/json
{
"text": "<user's text>"
}
The API returns JSON like this:
{
"score": {
"overall": 82,
"perplexity": 96,
"burstiness": 15,
"readability": 23,
"satPercent": 3,
"simplicity": 35,
"ngramScore": 8,
"averageSentenceLength": 21
},
"wordCount": 82,
"sentenceCount": 4,
"verdict": "ai"
}
IMPORTANT: The main AI score is score.overall (not score directly). This is the score to display to the user.
## AI Detection Results
**Score:** [score.overall]/100 ([verdict])
**Words Analyzed:** [wordCount]
### Metrics
- Perplexity: [score.perplexity]
- Burstiness: [score.burstiness]
- Readability: [score.readability]
- N-gram Score: [score.ngramScore]
### Recommendation
[Based on score.overall, suggest whether to humanize]
If the API call fails:
Weekly Installs
108
Repository
GitHub Stars
10
First Seen
Feb 3, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
gemini-cli102
opencode101
codex100
cursor98
kimi-cli94
github-copilot93
AI 代码实施计划编写技能 | 自动化开发任务分解与 TDD 流程规划工具
49,000 周安装
Build工作流编排器:AI驱动的开发流程自动化工具,支持绿地/棕地/TDD/重构
239 周安装
设计模式实现指南:TypeScript/JavaScript 代码架构最佳实践与SOLID原则
238 周安装
aixyz on OpenClaw:无需编码部署可收费AI代理的完整指南
237 周安装
Prompt Guard v3.5.0 - 100%离线AI智能体运行时安全防护,内置600+检测模式
238 周安装
Julia编程专家指南:多重分派、类型系统与高性能计算最佳实践
89 周安装
fal.ai AI图像视频生成技能:使用先进AI模型一键生成图像和视频内容
241 周安装