一键导入
searxng
Search the web using SearXNG. Use when you need current information, news, or web search. Triggers on "search", "look up", "find online", "web search".
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Search the web using SearXNG. Use when you need current information, news, or web search. Triggers on "search", "look up", "find online", "web search".
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
文件系统操作。⚠️读取前先调用info获取文件信息:图片用read_file(mode='data_url'),大文件用from/lines分块。
PowerPoint 演示文稿处理。用于读取现有 PPTX 基本信息、文本、表格、图表基础数据与备注,创建新演示文稿,并提取媒体文件。支持在新建演示文稿时添加文本、图片、表格、图表、形状、媒体与演讲者备注。当用户提到 .pptx 文件或需要操作 PowerPoint 时触发。
Excel 文件处理。用于读取、写入、编辑 .xlsx/.xls/.csv 文件,支持工作表管理、格式化、公式计算、数据查询和格式转换。当用户需要操作电子表格文件时触发。
发票专用解析技能。支持中国增值税发票、普通发票、电子发票的结构化提取。基于 pdfjs-dist 实现坐标提取,可提取发票号码、日期、买卖双方信息、商品明细、金额等字段。
PDF 文件处理。用于读取、提取文本/表格/图片、合并、拆分、旋转、水印、加密/解密、表单填写、页面渲染。当用户提到 .pdf 文件或需要操作 PDF 时触发。
PDF 文件处理(Python 版)。使用 PyMuPDF 实现,内存效率高,适合处理大文件。用于读取、提取文本/表格/图片、合并、拆分、旋转、水印、加密/解密、页面渲染。当用户提到 .pdf 文件或需要操作 PDF 时触发。
| name | searxng |
| description | Search the web using SearXNG. Use when you need current information, news, or web search. Triggers on "search", "look up", "find online", "web search". |
| argument-hint | [query] |
| user-invocable | true |
| allowed-tools | ["Bash(curl *)"] |
Search the web using your local SearXNG instance - a privacy-respecting metasearch engine.
// Basic search
{ "query": "machine learning basics" }
// Search with options
{ "query": "breaking news", "category": "news", "time_range": "day", "n": 20 }
Search the web using SearXNG.
Parameters:
query (string, required): The search queryn (number, optional): Number of results (default: 10, max: 50)category (string, optional): "general" | "images" | "videos" | "news" | "map" | "music" | "files" | "it" | "science"language (string, optional): Language code like "en", "zh", "auto" (default: "auto")time_range (string, optional): "day" | "week" | "month" | "year"format (string, optional): "json" (default) or "table" for readable displayExamples:
// General search
{ "query": "node.js tutorial" }
// Image search
{ "query": "cute cats", "category": "images" }
// Recent news
{ "query": "AI news", "category": "news", "time_range": "day" }
// Get 30 results in table format
{ "query": "climate change", "n": 30, "format": "table" }
Set environment variable:
export SEARXNG_URL=https://your-searxng-instance.com
Default: http://localhost:8080
Returns JSON with search results:
{
"success": true,
"data": {
"query": "search term",
"number_of_results": 1000,
"results": [
{
"title": "Result Title",
"url": "https://example.com",
"content": "Snippet...",
"engines": ["google", "bing"]
}
]
}
}
Use format: "table" for human-readable output.