exa-search

name	exa-search
description	Use this skill when users need semantic web search, similar-page discovery, result content retrieval, research-paper lookup, GitHub discovery, or structured Exa-powered research.
license	MIT
compatibility	Designed for Claude Code; requires Node.js and network access to the Exa API.
metadata	{"author":"BenedictKing","version":"1.0.1","user-invocable":"true"}
allowed-tools	Bash Read

Exa Search Skill

Trigger Conditions & Endpoint Selection

Choose Exa endpoint based on user intent:

• search: Need semantic search / find web pages / research topics
• contents: Given result IDs, need to extract full content
• findsimilar: Given URL, need to find similar pages
• answer: Need direct answer to a question
• research: Need structured research output following given output_schema

Recommended Architecture (Main Skill + Sub-skill)

This skill uses a two-phase architecture:

1. Main skill (current context): Understand user question → Choose endpoint → Assemble JSON payload
2. Sub-skill (fork context): Only responsible for HTTP call execution, avoiding conversation history token waste

Execution Method

Use Task tool to invoke exa-fetcher sub-skill, passing command and JSON (stdin):

Task parameters:
- subagent_type: Bash
- description: "Call Exa API"
- prompt: cat <<'JSON' | node scripts/exa-api.cjs <search|contents|findsimilar|answer|research>
  { ...payload... }
  JSON

Payload Examples

1) Search

cat <<'JSON' | node scripts/exa-api.cjs search
{
  "query": "Latest research in LLMs",
  "type": "auto",
  "numResults": 10,
  "category": "research paper",
  "includeDomains": [],
  "excludeDomains": [],
  "startPublishedDate": "2025-01-01",
  "endPublishedDate": "2025-12-31",
  "includeText": [],
  "excludeText": [],
  "context": true,
  "contents": {
    "text": true,
    "highlights": true,
    "summary": true
  }
}
JSON

Search Types:

• neural: Semantic search using embeddings
• fast: Quick keyword-based search
• auto: Automatically choose best method (default)
• deep: Comprehensive deep search

Categories:

• company, people, research paper, news, pdf, github, tweet, etc.

2) Contents

cat <<'JSON' | node scripts/exa-api.cjs contents
{
  "ids": ["result-id-1", "result-id-2"],
  "text": true,
  "highlights": true,
  "summary": true
}
JSON

3) Find Similar

cat <<'JSON' | node scripts/exa-api.cjs findsimilar
{
  "url": "https://example.com/article",
  "numResults": 10,
  "category": "news",
  "includeDomains": [],
  "excludeDomains": [],
  "startPublishedDate": "2025-01-01",
  "contents": {
    "text": true,
    "summary": true
  }
}
JSON

4) Answer

cat <<'JSON' | node scripts/exa-api.cjs answer
{
  "query": "What is the capital of France?",
  "numResults": 5,
  "includeDomains": [],
  "excludeDomains": []
}
JSON

5) Research

cat <<'JSON' | node scripts/exa-api.cjs research
{
  "input": "What are the latest developments in AI?",
  "model": "auto",
  "stream": false,
  "output_schema": {
    "properties": {
      "topic": {
        "type": "string",
        "description": "The main topic"
      },
      "key_findings": {
        "type": "array",
        "description": "List of key findings",
        "items": {
          "type": "string"
        }
      }
    },
    "required": ["topic"]
  },
  "citation_format": "numbered"
}
JSON

Environment Variables & API Key

Two ways to configure API Key (priority: environment variable > .env):

1. Environment variable: EXA_API_KEY
2. .env file: Place in .env, can copy from .env.example

Response Format

All endpoints return JSON with:

• requestId: Unique request identifier
• results: Array of search results
• searchType: Type of search performed (for search endpoint)
• context: LLM-friendly context string (if requested)
• costDollars: Detailed cost breakdown