Anysearch

AnySearch 提供命令行实时搜索能力，可执行网页搜索、按域名与子域名的垂直领域搜索、2-5 条并行批量搜索，以及把 URL 页面正文提取为 Markdown。支持匿名访问，可选 API Key 提升配额；文档要求首次加载时运行 doc 命令读取接口规范。

shifengwang333-ai

热度 51.67

最近更新 2026-06-24 20:42:24

分类：搜索依赖：代码执行 / 第三方 API / 读写文件应用场景：研究 / 市场分析 / 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 anysearch

Metadata

name: anysearch
description: Real-time search engine supporting web search, vertical domain search, parallel batch search, and URL content extraction.
version: 2.0.0
authors: ["AnySearch Team"]
credentials: [{"name":"ANYSEARCH_API_KEY","required":false,"description":"API key for higher rate limits. Anonymous access available with lower rate limits.","storage":".env file, environment variable, or --api_key CLI flag"}]

Overview

AnySearch is a unified real-time search service supporting general web search, vertical domain search, parallel batch search, and full-page content extraction. It exposes a single JSON-RPC 2.0 endpoint and requires no MCP server installation.

Trigger

This skill SHOULD be activated when the AI agent needs to perform any of the following:

Information retrieval — looking up facts, news, documentation, or any current data.
Fact-checking — verifying claims, cross-referencing statements.
Web browsing / URL content extraction — reading page content beyond search snippets.
Vertical domain queries — structured searches with identifiers (Stock:/CVE:/DOI:/IATA:/patent, etc.).
Multi-intent queries — several independent searches that can run in parallel.

Vertical domain rule: For queries that may belong to a supported domain (finance, academic, travel, health, code, geo, etc.), always call list_domains first to get the correct sub_domain and query_format before searching.

Recommended Entry Point

When this skill is first loaded, the agent MUST run the active CLI's doc command to obtain the complete interface specification:

Runtime	Command
Python	`python3 ~/.openclaw/workspace/skills/anysearch/scripts/anysearch_cli.py doc`
Node.js	`node ~/.openclaw/workspace/skills/anysearch/scripts/anysearch_cli.js doc`
Bash/sh	`bash ~/.openclaw/workspace/skills/anysearch/scripts/anysearch_cli.sh doc`

Platform Detection & CLI Routing

Priority: Python > Node.js > Shell

API Key Management

Anonymous access available (lower rate limits)
Optional API key: visit https://anysearch.com/console/api-keys
Key can be stored in scripts/.env as ANYSEARCH_API_KEY=<key>

Available Commands

1. search — Single query search

python3 ~/.openclaw/workspace/skills/anysearch/scripts/anysearch_cli.py search "query" [--domain finance] [--sub_domain finance.us_stock] [--zone cn] [--max_results 10] [--freshness week]

2. list_domains — Query vertical domain directory

python3 ~/.openclaw/workspace/skills/anysearch/scripts/anysearch_cli.py list_domains --domain finance

3. batch_search — Execute 2-5 search queries in parallel

python3 ~/.openclaw/workspace/skills/anysearch/scripts/anysearch_cli.py batch_search --queries '[{"query":"AAPL"},{"query":"GOOG"}]'

4. extract — Fetch full page content as Markdown

python3 ~/.openclaw/workspace/skills/anysearch/scripts/anysearch_cli.py extract --url https://example.com

Vertical Domains

Available: code, travel, home, ecommerce, gaming, film, music, finance, academic, legal, business, ip, health, geo, environment, energy

For finance queries (stock codes, financial data), ALWAYS use --domain finance with appropriate sub_domain.

Decision Flow

User query
  |
  +-- Has structured identifiers? (Stock:/CVE:/DOI:/IATA:/patent etc.)
  |     YES -> 1) list_domains --domain X
  |             2) read query_format from result
  |             3) search "<query>" --domain X --sub_domain Y
  |
  +-- Multiple independent intents?
  |     YES -> batch_search --query "..." --query "..."
  |
  +-- Need deeper content than snippets?
        YES -> extract "https://example.com/article"

  Otherwise -> search "<general query>"