yutori-web-research
Use Yutori’s Research API and Browsing API (cloud browser) to research topics, collect sources, and extract structured facts from the web. Use when the user asks to “research X”, “monitor/find papers”, or “navigate to a site and extract info” and you have access to YUTORI dev/prod endpoints via YUTORI_API_BASE and an API key in env (YUTORI_API_KEY or ~/.openclaw/openclaw.json env.YUTORI_API_KEY).
Why use this skill?
Enable advanced AI web research and cloud browser automation in OpenClaw. Extract data, summarize papers, and navigate sites with the Yutori Research API.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/juanpin/yutori-web-researchWhat This Skill Does
The yutori-web-research skill empowers your OpenClaw agent with advanced, autonomous web research and browser-based navigation capabilities. By interfacing with Yutori’s specialized cloud-hosted infrastructure, this skill bypasses the limitations of basic local browsing. It acts as an orchestrator, dispatching complex, multi-step tasks to cloud agents capable of searching the web, analyzing academic papers, and navigating interactive websites to extract structured data. It handles the heavy lifting of polling status endpoints and parsing raw responses, ensuring the final output presented to the user is clean, actionable text.
Installation
To integrate this skill into your OpenClaw environment, execute the following command in your terminal: clawhub install openclaw/skills/skills/juanpin/yutori-web-research. After installation, ensure your environment is configured for authentication. You must set YUTORI_API_KEY either as a system environment variable or within your ~/.openclaw/openclaw.json configuration file. Additionally, you may define YUTORI_API_BASE to toggle between https://api.dev.yutori.com (for testing) and https://api.yutori.com (for production).
Use Cases
This skill is ideal for tasks requiring deep focus and multi-page interaction. Use it when you need to perform competitive intelligence, such as monitoring changes on a competitor's pricing page, or when conducting academic literature reviews where you need to synthesize trends from numerous arXiv papers. It is also highly effective for web scraping scenarios that involve clicking through paginated lists, navigating menu structures, or filling out web forms to retrieve data that is not readily available via simple static HTML fetching.
Example Prompts
- "Research the latest advancements in LLM quantization techniques from the last month, focusing on papers released on arXiv, and provide a 1-page summary with a reading list of 10 key papers."
- "Go to the OpenAI careers page and extract a list of all remote engineering positions, including the specific stack requirements mentioned in each job description."
- "Navigate to the Yutori documentation site, find the list of supported API endpoints, and summarize the authentication requirements for each service."
Tips & Limitations
Always provide clear, concise instructions for the agent; the quality of the output is directly correlated to the precision of your prompt. For research tasks, request specific formats, such as lists with summaries and links, to ensure the agent returns actionable content. Be mindful that this skill relies on external cloud APIs; if you encounter a 403 Forbidden error, verify that your API key is active and that your subscription includes access to the required Research or Browsing products. Finally, ensure your environment maintains connectivity to the specified API endpoints to avoid latency or timeouts during long-running tasks.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-juanpin-yutori-web-research": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, external-api, code-execution