web-search-exa
web-search-exa provides neural search powered by embeddings to discover relevant web content, extract full page text, and synthesize findings. Query the web intelligently across multiple search modes, filter by domain or date, and get LLM-generated answers informed by live search results.
web-search-exa lets you search the web using neural embeddings to find and extract relevant content with deep research capabilities.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-23
web-search-exa lets you search the web using neural embeddings to find and extract relevant content with deep research capabilities. web-search-exa provides neural search powered by embeddings to discover relevant web content, extract full page text, and synthesize findings. Query the web intelligently across multiple search modes, filter by domain or date, and get LLM-generated answers informed by live search results.
Use it when
- Yes, web-search-exa extracts and retrieves full page contents from URLs.
- web-search-exa is available under the MIT license, making it straightforward to integrate.
Verify before relying
Read SKILL.md below before installing (2 files). Open directory: indexed for reading, not audited.
Install
gooseworks-ai/goose-skills/web-search-exa · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How to search the web with embeddings using web-search-exa?
web-search-exa uses neural embeddings to power intelligent web searches. Query the web by providing search terms, and the skill returns relevant content discovered through embedding-based matching. You can filter results by domain, date, and other parameters to refine your search and find exactly what you need across the internet.
Can web-search-exa extract full webpage contents and summaries?
Yes, web-search-exa extracts and retrieves full page contents from URLs. Beyond search results, you can fetch complete webpage text and get summaries, enabling comprehensive content analysis and research without manual browsing.
What is the web-search-exa research api setup process?
web-search-exa is available under the MIT license, making it straightforward to integrate. The skill supports multiple query modes for neural search, URL content extraction, and async research task creation. Documentation and setup guidance are provided to get your research workflows running quickly.
How does web-search-exa find similar links to a URL?
web-search-exa identifies similar or related links to a given webpage using neural embeddings. This capability enables discovery of comparable content, competitive intelligence, and related articles—useful for market research, content analysis, and comprehensive web exploration.
Can web-search-exa create async research tasks for web exploration?
web-search-exa supports creating async research tasks for comprehensive web exploration. This allows you to automate deep research workflows, enabling fact-finding with sourced answers and intelligent discovery across multiple search modes without blocking on individual queries.
Does web-search-exa provide LLM-powered web search results?
Yes, web-search-exa delivers LLM-informed answers backed by live web search results. The skill synthesizes findings from neural searches to generate intelligent, sourced responses, combining the power of embeddings-based discovery with language model reasoning.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Exa - Neural Web Search & Research
Setup
Read your credentials from ~/.gooseworks/credentials.json:
export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])")
export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))")
If ~/.gooseworks/credentials.json does not exist, tell the user to run: npx gooseworks login
All endpoints use Bearer auth: -H "Authorization: Bearer $GOOSEWORKS_API_KEY"
Neural search engine for finding similar content, extracting pages, and deep research.
Capabilities
- Exa Research: Retrieve a paginated list of your research tasks
- Answer: Get an LLM answer to a question informed by Exa search results
- Search: The search endpoint lets you intelligently search the web and extract contents from the results
- Get a task: Retrieve the status and results of a previously created research task
- **Find similar
(truncated - see the full file via the links below)
File tree — 2 files
skills/research-tools/capabilities/web-search-exa/SKILL.md
skills/research-tools/capabilities/web-search-exa/skill.meta.json
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Search the web using neural embeddings to find relevant content”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
web-search-linkup provides programmatic access to web search and content fetching through two core endpoints. Use /search to retrieve web results with customizable depth, date ranges, and structured output formatting, or use /fetch to extract content from individual URLs with optional JavaScript rendering and image extraction.
browser-automation-notte provides programmatic control over browser sessions for web automation, scraping, and AI agent deployment. Start sessions with custom configurations, execute page interactions, capture screenshots, and manage cookies and network logs. Run autonomous agents to complete complex browser tasks end-to-end.
SEO Analyzer maps site structure, extracts page content, and identifies backlink opportunities to evaluate SEO performance. It examines keywords, content quality, and competitor positioning across your website. Use it to prioritize optimization efforts and track ranking improvements over time.
Exa Search performs semantic web search and content discovery through embeddings, supporting multiple query types including similarity matching, category-specific searches, and structured research output. Route queries to the appropriate endpoint—search for general topics, findsimilar for related pages, contents for full text extraction, answer for direct responses, or research for formatted findings.
Exa Search integrates Exa's Search API to conduct web research with fine-grained control over results. Choose your search mode, apply domain and date filters, and request only the content you need—highlights for efficiency or full text for deep reading. Built-in workflows handle news lookups, source verification, and citation management.
Exa Research provides Q&A capabilities with source attribution, combining the Answer API for cited responses with deep search for query expansion and summaries. Use it to build research automation, fact verification, and long-form reports with streaming support.
More skills job-search (MIT) · exa-search (Apache-2.0) · deep-research (MIT) · Web Search Plus (MIT) · exa-entities (MIT) · web-search-tavily (MIT) · extract-webpage-data (MIT) · ai-web-scraping-scrapegraph (MIT)