Exa Agent Skills
Official Exa skills connect an agent to the Exa API: semantic search, page extraction, answers, company research and lead lists
- 70 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The skills send your queries and page URLs to the external Exa service with an API key
- API use is paid and lead-generation collects company and contact details for lists
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/exa-agent-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The skills send your queries and page URLs to the external Exa service with an API key
- API use is paid and lead-generation collects company and contact details for lists
This is third-party code. Review the repository files before installing.
What it does
The set of five Exa skills teaches an agent to work with the Exa platform: semantic search, page content extraction, answers with sources, monitors, Websets and OpenAI-compatible endpoints. An API key from the Exa dashboard in `EXA_API_KEY` is required. The skills: `build-with-exa` helps build apps and agents on the platform and the `exa-py` and `exa-js` packages; `exa-search` calls `POST https://api.exa.ai/search` through cURL with no SDK, with domain and category filters, freshness, structured output and streaming; `exa-contents` pulls text, highlights, summaries, links and subpages for a known list of URLs; `company-research` gathers data about companies, competitors, funding, news and leadership; `lead-generation` builds lead lists from an target-customer profile with scoring and CSV output. `exa-search` works through query examples: plain search with `type: "auto"`, search with highlights and result parameters. The skills describe direct HTTP calls, so they suit an agent with no SDK installed.
Who it is for. Developers and analysts who use Exa as a search layer for agents, company research and prospect lists.
Good fit when
- The agent needs semantic web search with domain, category and freshness filters and no SDK install
- You need text, highlights and summaries from a known list of URLs, including subpages
- Before a meeting you need company data: competitors, funding, news, leadership
- You need a list of companies matching an target-customer profile with scoring and CSV export
- You build an app on `exa-py` or `exa-js` and want the agent to know the platform
Not a fit when
- You have no Exa key: every skill calls a paid API and fails without it
- You need search with no external API: the skills go only to Exa
- Data must stay on your machine: Exa processes the queries and pages
- You need a ready MCP server: here there are only skills with HTTP calls
Example request
Use Exa to find the five strongest competitors of this company and show their funding and latest newsLimitations
- An API key from dashboard.exa.ai in `EXA_API_KEY` is required and sent in the `x-api-key` header.
- Queries and extracted pages are processed by the external Exa service, and API use is billed on the Exa side.
- `exa-search` and `exa-contents` describe direct HTTP calls and install no SDK.
- `lead-generation` and `company-research` rely on Exa Agent and advanced search, so feature availability depends on your Exa plan.
How to disable. Remove the skills from the agent skills directory and delete `EXA_API_KEY` from the environment. Updates and reinstall use the same `npx skills` command.
FAQ
How do I install the Exa skills?
Run `npx skills add exa-labs/agent-skills`. Then get a key at dashboard.exa.ai and set it in `EXA_API_KEY`.
Which skills are included?
Five: `build-with-exa`, `exa-search`, `exa-contents`, `company-research` and `lead-generation`.
Is an SDK required?
No. `exa-search` and `exa-contents` call the API directly through cURL or raw HTTP, and `build-with-exa` helps if you do write with `exa-py` or `exa-js`.
Is it free?
The skills are free, but Exa API calls follow Exa pricing and need a key. See the terms in the Exa dashboard.
How is `exa-contents` different from `exa-search`?
`exa-search` finds results from a query, while `exa-contents` extracts content from URLs you already know: text, highlights, summaries, links and subpages.
Discussion
No questions or reviews yet.
Related
SkillsThree skills and four utilities that let an agent search the web, read pages, pull video subtitles and process media
Official Exa MCP server: web search, reading pages as Markdown and multi-step research via Exa Agent
Four research skills for company, competitor, foreign trade and renewable energy market intelligence through Exa.
Three search skills: four-source search scored by intent, deep thread tracing and clean Markdown extraction from pages.
A web search skill with no MCP server: four command-line clients search the web and 16 vertical domains, in batches and with page extraction
Official Brave skills that teach an agent to call the Search API for web, news, images, videos, places and page extracts for LLMs
README in short
The README briefly introduces the set: connecting assistants to the Exa API, a note on the key and a table of five skills with descriptions. Install takes one `npx skills add exa-labs/agent-skills` command.
README badge
Original SKILL.md
---
name: exa-search
description: "Call Exa Search directly with cURL or raw HTTP. Use when an agent needs Exa semantic web retrieval from POST /search without an SDK, including ranked results, domain or category filters, freshness-aware result content, highlights or text extraction, structured output, or streaming search responses."
---
# Exa Search
> Requires API key: Get one at https://dashboard.exa.ai/api-keys
>
> Header: `x-api-key: $EXA_API_KEY`
Use `POST https://api.exa.ai/search` for semantic web retrieval, ranked results, and optional result-level extraction in one raw HTTP call. Start with `type: "auto"` for general retrieval. Add `contents` only when the caller needs page text, highlights, summaries, freshness-controlled crawling, subpages, or extracted links.
## Quick Start (cURL)
### Basic search
```bash
curl -sS -X POST "https://api.exa.ai/search" \
-H "Content-Type: application/json" \
-H "x-api-key: $EXA_API_KEY" \
-d '{
"query": "latest developments in LLMs",
"type": "auto",
"numResults": 10
}'
```
### Search with highlights
```bash
curl -sS -X POST "https://api.exa.ai/search" \
-H "Content-Type: application/json" \
-H "x-api-key: $EXA_API_KEY" \