Use Valyu (valyu.ai) to search the web, extract content from web pages, answer with sources, and do deepresearch.
数据来源：ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一：命令行安装（推荐）
推荐（无需提前安装 clawhub）
npx clawhub@latest --dir ~/.claude/skills install valyu-search或使用 clawhub CLI（需提前安装）
clawhub --dir ~/.claude/skills install valyu-search⚠️ 需要 Node.js 18+，没有 Node？请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二：手动下载安装（无需 Node）
下载 ZIP，解压后将文件夹放到以下路径，重启 Agent 即可：
安装路径
~/.claude/skills/valyu-search/💡解压后将文件夹放到上方路径，重启 Agent 即可生效
--- name: valyu-search description: "Use Valyu (valyu.ai) to search the web, extract content from web pages, answer with sources, and do deepresearch." metadata: {"openclaw":{"emoji":"🔎","requires":{"bins":["node"],"env":["VALYU_API_KEY"]},"primaryEnv":"VALYU_API_KEY","homepage":"https://docs.valyu.ai"}} ---
Search across the world's knowledge.
Trigger this skill when the user asks for:
VALYU_API_KEY in the Gateway environment (recommended) or in ~/.openclaw/.env.---
Run a search across the web:
node {baseDir}/scripts/valyu.mjs search web "<query>"Search across news, academic papers, financial data, patents and more
node {baseDir}/scripts/valyu.mjs search news "<query>"| Parameter | Type | Description | |-----------|------|-------------| | query | string | Search query (required) | | searchType | string | "web", "proprietary", "news", or "all" (default: "all") | | maxNumResults | number | 1-20 (default: 10) | | includedSources | string[] | Limit to specific sources (e.g., ["valyu/valyu-arxiv"]) | | excludedSources | string[] | Exclude specific sources | | startDate | string | Filter from date (YYYY-MM-DD) | | endDate | string | Filter to date (YYYY-MM-DD) | | countryCode | string | ISO 3166-1 alpha-2 (e.g., "US", "GB") | | responseLength | string | "short", "medium", "large", "max" | | fastMode | boolean | Reduced latency mode | | category | string | Natural language category (e.g., "academic research") | | relevanceThreshold | number | 0.0-1.0 (default: 0.5) |
| Source | Description | |--------|-------------| | valyu/valyu-arxiv | Academic papers from arXiv | | valyu/valyu-pubmed | Medical and life science literature | | valyu/valyu-stocks | Global stock market data |
Additional sources: BioRxiv, MedRxiv, clinical trials, FDA drug labels, WHO health data, SEC filings, USPTO patents, Wikipedia, UK Parliament, UK National Rail, maritime vessel tracking, and more.
Extract clean, structured content from any URL. Converts web pages to markdown or structured data.
node {baseDir}/scripts/valyu.mjs contents "https://example.com" --summary| Parameter | Type | Description | |-----------|------|-------------| | urls | string[] | Array of URLs to extract (required) | | responseLength | string | Output length: "short", "medium", "large", "max" | | extractEffort | string | "auto", "lightweight", "moderate", "heavy" | | jsonSchema | object | JSON Schema for structured extraction |
Get AI-generated answers grounded in real-time search results with citations.
node {baseDir}/scripts/valyu.mjs answer "What is quantum computing?" --fast| Parameter | Type | Description | |-----------|------|-------------| | query | string | Question or query (required) | | searchType | string | Search scope: "web", "proprietary", "news", "all" | | outputSchema | object | JSON Schema for structured responses |
Launch async, multi-step research tasks that produce detailed reports with citations.
| Mode | Duration | Use Case | |------|----------|----------| | fast | ~5 min | Quick answers, lightweight research | | standard | ~10-20 min | Balanced research with deeper insights | | heavy | ~90 min | In-depth, complex analysis |
node {baseDir}/scripts/valyu.mjs deepresearch create "AI market trends" --mode heavy --pdf| Parameter | Type | Description | |-----------|------|-------------| | query | string | Research query (required) | | mode | string | "fast", "standard", "heavy" | | outputFormats | array | ["markdown"], ["pdf"], or JSON Schema object | | files | array | File attachments (base64 encoded, max 10) | | urls | string[] | URLs to analyze (max 10) | | webhookUrl | string | HTTPS URL for completion notification |
| Need | API | |------|-----| | Quick facts, current events, citations | Search | | Read/parse a specific URL | Contents | | AI-synthesized answer with sources | Answer | | In-depth analysis or report | DeepResearch |
安装 Valyu Search 后，可以对 AI 说这些话来触发它
Help me get started with Valyu Search
Explains what Valyu Search does, walks through the setup, and runs a quick demo based on your current project
Use Valyu Search to use Valyu (valyu
Invokes Valyu Search with the right parameters and returns the result directly in the conversation
What can I do with Valyu Search in my data & analytics workflow?
Lists the top use cases for Valyu Search, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/valyu-search/ 目录（个人级，所有项目可用），或 .claude/skills/valyu-search/（项目级）。重启 AI 客户端后，用 /valyu-search 主动调用，或让 AI 根据上下文自动发现并使用。
Valyu Search 支持 Claude、Cursor、OpenClaw，可与这些 AI 平台无缝集成，扩展其能力。
Valyu Search 可免费安装使用。请查阅仓库了解许可证信息。
Use Valyu (valyu.ai) to search the web, extract content from web pages, answer with sources, and do deepresearch.
Valyu Search 属于「Data & Analytics」分类，该分类的技能帮助 AI 智能体在此领域执行专业任务。
Automate my data & analytics tasks using Valyu Search
Identifies repetitive steps in your workflow and sets up Valyu Search to handle them automatically