Agent skill

exa-search

Semantic search skill using Exa API for embeddings-based search, similar content discovery, and structured research. Use when you need semantic search, find similar pages, or category-specific searches. Triggers: exa, semantic search, find similar, research paper, github search, 语义搜索, 相似内容

View SKILL.md on GitHub Repository
Stars 4
Forks 0

Install this agent skill to your Project

npx add-skill https://github.com/BenedictKing/exa-search/tree/main/.claude/skills/exa-search

SKILL.md

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 .claude/skills/exa-search/exa-api.cjs <search|contents|findsimilar|answer|research>
  { ...payload... }
  JSON

Payload Examples

1) Search

bash
cat <<'JSON' | node .claude/skills/exa-search/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

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

3) Find Similar

bash
cat <<'JSON' | node .claude/skills/exa-search/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

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

5) Research

bash
cat <<'JSON' | node .claude/skills/exa-search/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 .claude/skills/exa-search/.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

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

BenedictKing/firecrawl-scraper

firecrawl-scraper

Web scraping skill using Firecrawl API for deep content extraction, format conversion, and page interaction. Use when you need to scrape web pages, extract structured data, take screenshots, parse PDFs, or crawl entire websites. Triggers: firecrawl, scrape, extract content, screenshot, parse pdf, crawl website, 抓取网页, 提取内容, 网页截图

5 2
Explore
BenedictKing/codex-review

codex-review

Professional code review skill for Claude Code. Automatically collects file changes and task status. Triggers when working directory has uncommitted changes, or reviews latest commit when clean. Triggers: code review, review, 代码审核, 代码审查, 检查代码

12 0
Explore
BenedictKing/context7-auto-research

context7-auto-research

Automatically fetches up-to-date documentation from Context7 when users ask about libraries, frameworks, APIs, or need code examples. Triggers proactively without explicit user request.

14 2
Explore
BenedictKing/tavily-web

tavily-web

Web research skill using Tavily API for search, extract, crawl, map, and structured research tasks. Use when you need latest information, extract content from URLs, or discover site structure. Triggers: tavily, web search, search web, latest info, extract, crawl, map, research, 搜索网页, 查资料, 最新

2 1
Explore
mattpocock/skills

edit-article

Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.

111,310 9,758
Explore
mattpocock/skills

obsidian-vault

Search, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize notes in Obsidian.

111,310 9,758
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results