exa-search · ejirocodes — Claude Code skill: what it does, how to install
exa-search guides agents in integrating Exa.ai web search, configuring neural queries, and extracting web content.
MIT 249 installs ★ 6 updated 2026-06-25
npx skills add ejirocodes/agent-skills --skill exa-search -a claude-codeWhat exa-search does
The skill provides patterns for implementing the Exa.ai search API with exa_py in Python and exa-js in TypeScript. It guides the model through calling search_and_contents, collecting snippets, and discovering related pages using find_similar_and_contents.
Included reference docs explain how to pick between auto, neural, and keyword search modes. They also cover domain inclusion, date filters, and generating summaries for retrieval-augmented generation pipelines.
Requests fail without a valid EXA_API_KEY environment variable. By default, Exa returns only URLs, which means fetching page text requires passing text=True explicitly in the query payload.
What it helps with
- integrate Exa web search into Python or TypeScript codebases
- extract page content and highlights using Exa API methods
- select appropriate search modes for conceptual or keyword queries
- find similar articles while excluding the source domain
Example prompts for the agent
- Write a Python snippet with exa_py to search AI funding news and return summaries
- How do I configure exa-js to filter results by domain and start date?
- Show how to find similar web pages using find_similar_and_contents in Exa
How to install exa-search
1Skills CLI (Vercel)
npx skills add ejirocodes/agent-skills --skill exa-search -a claude-code2Manually: put the files in place
~/.claude/skills/exa-search/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/exa-search/
1Skills CLI (Vercel)
npx skills add ejirocodes/agent-skills --skill exa-search -a codex2Manually: put the files in place
.agents/skills/exa-search/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add ejirocodes/agent-skills --skill exa-search -a cursor2Manually: put the files in place
.cursor/skills/exa-search/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install ejirocodes/agent-skills exa/skills/exa-search2Manually: put the files in place
.github/skills/exa-search/SKILL.md1Skills CLI (Vercel)
npx skills add ejirocodes/agent-skills --skill exa-search -a gemini-cli2Platform CLI
gemini skills install https://github.com/ejirocodes/agent-skills --path exa/skills/exa-searchManually: put the files in place
.devin/skills/exa-search/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add ejirocodes/agent-skills --skill exa-search -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about exa-search
How to install exa-search in Claude Code?
Run npx skills add ejirocodes/agent-skills --skill exa-search -a claude-code. It sets up the skill under ~/.claude/skills/exa-search/.
What does exa-search do?
It provides your coding assistant with standard implementation patterns for the Exa search API, covering content extraction, SDK usage, and search mode selection.
Why are relevance scores missing in search results?
Exa returns relevance scores only when the search type is set to neural. The default auto mode does not include them.
Source text
SKILL.md · MIT
---
name: exa-search
description: "Exa.ai search API integration for neural and keyword web search with content retrieval. Use when implementing web search features, integrating Exa SDK (exa_py, exa-js), or retrieving web content. Triggers on: Exa, exa_py, exa-js, neural search, web search API, search_and_contents, searchAndContents, find_similar, findSimilar, domain filtering, date filtering, text extraction, page summaries, highlights, search auto mode, fast search, search categories, livecrawl, excluding domains, include text, exclude text, EXA_API_KEY."
license: MIT
metadata:
author: ejirocodes
version: '1.0.0'
---
# Exa Search Integration
## Quick Reference
| Topic | When to Use | Reference |
|-------|-------------|-----------|
| **Search Modes** | Choosing between auto, neural, and keyword search | [search-modes.md](references/search-modes.md) |
| **Filters** | Domain, date, text, and category filtering | [filters.md](references/filters.md) |
| **Contents** | Text extraction, highlights, summaries, livecrawl | [contents.md](references/contents.md) |
| **SDK Patterns** | Python (exa_py) and TypeScript (exa-js) usage | [sdk-patterns.md](references/sdk-patterns.md) |
## Essential Patterns
### Basic Search (Python)
```python
from exa_py import Exa
exa = Exa(api_key="your-api-key") # or set EXA_API_KEY env var
results = exa.search_and_contents(
"latest developments in quantum computing",
type="auto",
num_results=10,
text=True,
highlights=True
)
for result in results.results:
print(f"{result.title}: {result.url}")
print(result.text[:500])
```
### Basic Search (TypeScript)
```typescript
import Exa from "exa-js";
const exa = new Exa(process.env.EXA_API_KEY);
const results = await exa.searchAndContents(
"latest developments in quantum computing",
{
type: "auto",
numResults: 10,
text: true,
highlights: true,
}
);
results.results.forEach((result) => {
console.log(`${result.title}: ${result.url}`);
});
```
### Search with Filters
```python
results = exa.search_and_contents(
"AI startup funding rounds",
type="neural",
num_results=10,
include_domains=["techcrunch.com", "venturebeat.com"],
start_published_date="2024-01-01",
text={"max_characters": 2000},
summary=True
)
```
### Find Similar Links
```python
similar = exa.find_similar_and_contents(
"https://example.com/interesting-article",
num_results=10,
exclude_source_domain=True,
text=True
)
```
## Search Mode Selection
| Mode | When to Use | Notes |
|------|-------------|-------|
| `auto` | Default for most queries | Exa optimizes between neural/keyword automatically |
| `neural` | Natural language, conceptual queries | Best for "what is...", "how to...", topic exploration |
| `keyword` | Exact matches, technical terms, names | Best for specific product names, error codes, proper nouns |
## Common Mistakes
1. **Using `keyword` for conceptual queries** - Neural search understands intent better; use `auto` or `neural` for natural language questions
2. **Not setting `text=True`** - Search returns URLs only by default; explicitly request content with `text=True`
3. **Ignoring `highlights`** - Use `highlights=True` for relevant snippets without downloading full page text
4. **Missing API key** - Set `EXA_API_KEY` environment variable or pass explicitly to constructor
5. **Over-filtering initially** - Start with broad searches, then add domain/date filters to refine
6. **Not using `summary`** - For RAG applications, `summary=True` provides concise context without full page text
7. **Expecting scores in auto mode** - Relevance scores are only returned with `type="neural"`; auto mode doesn't include them
© ejirocodes · MIT · ejirocodes/agent-skills
Similar skills
All skills for AI and ML →exa-search by other authors comes first.