Tavily Web Seeker

该 Skill 调用 Tavily 执行网页搜索，可自动识别查询意图（事实、新闻、研究、对比、教程、学术），按主题路由偏好域名，支持搜索运算符、关键信源校验与多 API Key 限流轮换，并可将结果导出为 Markdown 检索报告。检索依赖外部服务与用户自备的 API Key。

fundou1081

热度 36.74

最近更新 2026-05-11 17:39:08

分类：搜索依赖：代码执行 / 第三方 API应用场景：研究 / 报告撰写 / 摘要总结

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add tavily-web-seeker

Metadata

name: tavily-web-seeker
description: Enhanced Tavily search with intelligent intent recognition, source preferences, critical source validation, and offline report generation.
version: 1.1.0
metadata: {"openclaw":{"emoji":"🎯","requires":{"config":["plugins.entries.tavily.config"]}}}

tavily-web-seeker

Enhanced web search skill built on Tavily API with intelligent search strategies, user source preferences, and critical source handling.

Features

Intent Recognition - Auto-classify queries (factual, news, research, comparison, how-to, academic)
Source Preferences - Topic-based domain routing (tech→GitHub, news→Reuters, finance→WSJ)
Search Operators - Support OR, site:, -, exact phrase, time filters
Critical Source Check - Validate results against preferred sources, return not-found conclusions
Multi-API Key Rotation - Auto-failover on rate limits (429)
Offline Report - Markdown export with source coverage analysis

Tools

Tool	Description
`tavily_search`	Standard Tavily search
`web_seeker`	Enhanced search with all features

Configuration

API Keys

{
  "apiKey": { "key1": "tvly-xxx1", "key2": "tvly-xxx2" }
}

Or env: TAVILY_API_KEY, TAVILY_API_KEY_2

Source Preferences

// User preferences
const PREFERENCES = {
  default_sites: ["wikipedia.org", "github.com"],
  preferred_topics: {
    tech: ["wikipedia.org", "github.com", "stackoverflow.com"],
    news: ["reuters.com", "apnews.com", "bbc.com"],
    finance: ["wsj.com", "bloomberg.com", "ft.com"],
    academic: ["scholar.google.com", "arxiv.org"]
  },
  critical_sources: {
    "官方": ["gov.cn", "moe.gov.cn"],
    "财经": ["wsj.com", "bloomberg.com"],
    "技术": ["github.com", "stackoverflow.com"]
  }
};

web_seeker Parameters

Parameter	Type	Default	Description
`query`	string	-	Search query
`mode`	string	"quick"	quick/research/compare
`max_results`	number	5	Results 1-20
`domains`	array	auto	Preferred domains
`time_range`	string	auto	day/week/month/year
`operators`	string	-	Raw operators
`strict_mode`	boolean	false	Require preferred sources only
`export_doc`	boolean	false	Generate report

Response Format

{
  "original_query": "Iran oil news",
  "intent": "news",
  "domains_used": ["reuters.com", "bbc.com"],
  "search_operator_applied": "site:reuters.com OR site:bbc.com",
  "results_found": true,
  "source_coverage": { "preferred": 3, "total": 10 },
  "results": [...],
  "summary": "..."
}

Not Found Response

{
  "results_found": false,
  "not_found_conclusion": "在指定的核心信源中未搜索到...",
  "suggestions": ["扩展搜索词", "放宽信源限制", "手动访问目标网站"]
}

Usage

# Basic search
node seeker.js "AI news"

# Research mode with report
node seeker.js "machine learning" --mode research --export

# Strict mode (require preferred sources)
node seeker.js "python tutorial" --strict