exa-plus
Neural web search via Exa AI. Search people, companies, news, research, code. Supports deep search, domain filters, date ranges.
Why use this skill?
Enhance your OpenClaw agent with Exa Plus. Perform advanced neural web searches across research papers, news, LinkedIn, and GitHub with powerful filtering options.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/jordyvandomselaar/exa-plusWhat This Skill Does
The exa-plus skill provides the OpenClaw AI agent with advanced, neural-powered web searching capabilities. Unlike standard keyword-based search, this tool leverages Exa AI's semantic understanding to navigate diverse data sources including LinkedIn profiles, financial reports, research papers, GitHub repositories, and global news outlets. By processing complex queries through a deep-learning lens, the agent can synthesize information across multiple domains, filter by date, and extract raw textual content from URLs for further analysis.
Installation
To integrate this skill, ensure you have the OpenClaw environment set up. First, install the skill from the central hub using the terminal command: clawhub install openclaw/skills/skills/jordyvandomselaar/exa-plus. Once installed, you must configure your authentication credentials. Create a file located at ~/.clawdbot/credentials/exa/config.json and insert your Exa AI API key in the format {"apiKey": "your-exa-api-key"}. This allows the agent to authorize requests against the Exa API securely.
Use Cases
This skill is highly versatile. Researchers can use it to aggregate current scholarly papers on emerging technologies. Business analysts can identify competitive intelligence by filtering for financial reports or company news from specific domains. Developers can leverage it to find specific documentation or code patterns across GitHub. HR and recruiters can perform targeted searches for professional profiles on LinkedIn using location and role-specific parameters.
Example Prompts
- "Find the latest 2026 breakthroughs in transformer architecture as detailed in recent research papers, and summarize the top three findings for me."
- "Search for fintech startups based in the Netherlands that have been mentioned in news articles over the last three months, excluding generic blog posts."
- "Get the full text content from these three URLs [url1, url2, url3] and compile a brief report highlighting the key arguments from each."
Tips & Limitations
To optimize results, always use specific categories like CATEGORY=news or CATEGORY=research paper to narrow the neural search scope. Use the TYPE=deep option for complex, multi-faceted research, but be aware this may consume more token credits. Remember that search performance is dependent on the availability of the target domains. Always verify important information against primary sources, as AI-filtered search results may occasionally aggregate outdated or context-dependent data.
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-jordyvandomselaar-exa-plus": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, external-api
Related Skills
ralph-loop
Generate copy-paste bash scripts for Ralph Wiggum/AI agent loops (Codex, Claude Code, OpenCode, Goose). Use when asked for a “Ralph loop”, “Ralph Wiggum loop”, or an AI loop to plan/build code via PROMPT.md + AGENTS.md, SPECS, and IMPLEMENTATION_PLAN.md, including PLANNING vs BUILDING modes, backpressure, sandboxing, and completion conditions.
radarr
Search and add movies to Radarr. Supports collections, search-on-add option.
sonarr
Search and add TV shows to Sonarr. Supports monitor options, search-on-add.