exa-entities

📁 ejirocodes/agent-skills 📅 Jan 24, 2026
17
总安装量
9
周安装量
#19890
全站排名
安装命令
npx skills add https://github.com/ejirocodes/agent-skills --skill exa-entities

Agent 安装分布

claude-code 7
opencode 6
windsurf 5
gemini-cli 5
antigravity 5
codex 5

Skill 文档

Exa Entity Search

Quick Reference

Topic When to Use Reference
Company Search Finding companies, competitive research company-search.md
People Search Finding profiles, recruiting people-search.md
Websets Data collection at scale, monitoring websets.md

Essential Patterns

Company Search

from exa_py import Exa

exa = Exa()

results = exa.search_and_contents(
    "AI startups in healthcare series A funding",
    category="company",
    num_results=20,
    text=True
)

for company in results.results:
    print(f"{company.title}: {company.url}")

People Search

results = exa.search_and_contents(
    "machine learning engineers San Francisco",
    category="linkedin_profile",
    num_results=20,
    text=True
)

for profile in results.results:
    print(f"{profile.title}: {profile.url}")

Websets for Lead Generation

# Create a webset for company collection
webset = exa.websets.create(
    name="AI Healthcare Companies",
    search_query="AI healthcare startups",
    category="company",
    max_results=100
)

# Monitor for new matches
exa.websets.add_monitor(
    webset_id=webset.id,
    schedule="daily"
)

Category Reference

Category Use Case Index Size
company Company websites, about pages Millions
linkedin_profile Professional profiles 1B+ profiles
personal_site Individual blogs, portfolios Millions
github Repositories, developer profiles Millions

Common Mistakes

  1. Not using category filter – Always set category="company" or category="linkedin_profile" for entity search
  2. Expecting structured data – Exa returns web pages; parse text for structured fields
  3. Over-broad queries – Add location, industry, or role specifics for better results
  4. Ignoring rate limits – Batch requests and implement backoff for large-scale collection
  5. Missing domain filters – Use include_domains=["linkedin.com"] for profile-only results