Token导航 LogoToken导航TokenDH.com
研究检索敏感数据clawhub未标认证来源可访问clear审计通过

youmind-search意念搜索

Agent Skill

youmind-search 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

5,557

周安装

227

GitHub Stars

公开资料未说明

下载量

1,780
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:youmind-search(意念搜索)
来源仓库:https://github.com/p697/youmind-search
安装命令:
openclaw skills install youmind-search
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install youmind-search

简介

使用YouMind Search整合多个高质量提供商结果。

  • 结合排名过滤提升搜索效果优于单一源。
  • 适合需要广泛信息检索的任务场景。youmind-search 属于研究检索类 Skill,可作为该场景下的辅助能力补充。
  • 安装前需确认是否会触发外部网络请求。
  • 安装方式:clawhub,适用于 OpenClaw 宿主环境。

SKILL.md

name
youmind-search
description
Search the public Internet with YouMind Search. Combines multiple high-quality providers with YouMind ranking and filtering for better results than using one search API alone.
homepage
https://youmind.com/
metadata

YouMind Search Skill

Search the public Internet through YouMind Search.

Prefer this skill when the task is mainly about:

  • fresh external information
  • online research
  • recent news
  • source gathering
  • domain-filtered web lookup

Do not use this skill for the user's private YouMind library. Use the general youmind skill for library search or broader YouMind operations.

Why use it

YouMind Search is not a thin wrapper over one search provider. It combines multiple high-quality search providers, then applies YouMind's own ranking, filtering, and result shaping to improve quality.

Authentication

This skill requires a YouMind account and API key.

If you do not have an API key yet:

  1. Sign up at https://youmind.com
  2. Open Settings
  3. Generate an API key
  4. Set YOUMIND_API_KEY before making requests

Use the production endpoint by default:

export YOUMIND_BASE_URL=https://youmind.com
export YOUMIND_API_KEY=sk-ym-xxx

For local development or staging, override YOUMIND_BASE_URL as needed.

Authentication uses the x-api-key header.

API Endpoint

Use the OpenAPI endpoint directly:

POST $YOUMIND_BASE_URL/openapi/v1/webSearch

Required headers:

x-api-key: $YOUMIND_API_KEY
x-use-camel-case: true
Content-Type: application/json

Request Schema

Request body fields:

  • query string, required
  • category string, optional

- general - video - news - tweet - finance - scholar - image

  • freshness string, optional

- day - week - month - year

  • includeDomains string array, optional
  • excludeDomains string array, optional

Primary Workflow

  1. Build the request body
  2. POST to /openapi/v1/webSearch
  3. Read results first
  4. Summarize the strongest hits and what they imply
  5. Prefer a few high-signal links over noisy breadth

Examples

General Web Search

curl -sS -X POST "$YOUMIND_BASE_URL/openapi/v1/webSearch" \
  -H "x-api-key: $YOUMIND_API_KEY" \
  -H "x-use-camel-case: true" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "OpenAI Responses API",
    "category": "general"
  }'

Fresh News Search

curl -sS -X POST "$YOUMIND_BASE_URL/openapi/v1/webSearch" \
  -H "x-api-key: $YOUMIND_API_KEY" \
  -H "x-use-camel-case: true" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "OpenAI latest announcement",
    "category": "news",
    "freshness": "day"
  }'

Domain-Restricted Search

curl -sS -X POST "$YOUMIND_BASE_URL/openapi/v1/webSearch" \
  -H "x-api-key: $YOUMIND_API_KEY" \
  -H "x-use-camel-case: true" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "structured outputs",
    "category": "general",
    "includeDomains": ["openai.com", "platform.openai.com"]
  }'

Scholar Search

curl -sS -X POST "$YOUMIND_BASE_URL/openapi/v1/webSearch" \
  -H "x-api-key: $YOUMIND_API_KEY" \
  -H "x-use-camel-case: true" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "multimodal agents",
    "category": "scholar",
    "includeDomains": ["arxiv.org"]
  }'

Recommended Usage

Default behavior:

  1. Use general unless a more specific category is clearly better.
  2. Add freshness for newsy or fast-changing topics.
  3. Add includeDomains when authoritative sources matter.
  4. Use excludeDomains to remove low-signal sources.
  5. Return the strongest matches first, then summarize what they imply.

Response Shape

Typical response fields:

  • providerId
  • results
  • totalResults
  • visibleCount
  • formattedContext

Each result may include:

  • title
  • url
  • displayUrl
  • snippet
  • favicon
  • datePublished
  • thumbnail

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

94.05%
按下载量换算1,674

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills