把自然语言描述转为结构化 JSON,并由 mcp-diagram-generator MCP 服务生成 Draw.io、Mermaid 或 Excalidraw 图表文件。
集成
exa search
试用Advanced web search with precise date filtering and content type selection. Use when you need academic papers, GitHub repositories, research content, or spec...
它能做什么
**Cloud skill by Claw0x** — powered by Claw0x Gateway API.
技能文档
Exa Search
Cloud skill by Claw0x — powered by Claw0x Gateway API.
Advanced web search with precise date filtering, content type selection, and neural search. Perfect for research, competitive analysis, and specialized content discovery.
Requires Claw0x API key. Sign up at claw0x.com to get your key.
Prerequisites
- Sign up at claw0x.com
- Create API key in Dashboard
- Set environment variable:
# Add to ~/.openclaw/.env CLAW0X_API_KEY=ck_live_...
Pricing
$0.005 per successful call. Failed calls are free.
- Pay only for successful responses (2xx status)
- No monthly fees, no subscriptions
- Get started with $5 free credit
Quick Reference
| When This Happens | Do This | What You Get |
|---|---|---|
| Need academic papers from specific dates | Use category: "research paper" + date range | Filtered research results |
| Find GitHub projects from 2024 | Use category: "github" + start_published_date: "2024-01-01" | Recent open-source projects |
| Semantic search for concepts | Use search_type: "neural" | Intent-based results |
| Exact keyword matching | Use search_type: "keyword" | Traditional search results |
5-Minute Quickstart
Step 1: Get API Key (30 seconds)
Sign up at claw0x.com → Dashboard → Create API Key
Step 2: Set Environment Variable (30 seconds)
export CLAW0X_API_KEY="ck_live_..."
Step 3: Install Skill (30 seconds)
openclaw skills install exa-search
Step 4: Use Skill (1 minute)
const result = await agent.run('exa-search', {
query: 'transformer architecture improvements',
category: 'research paper',
start_published_date: '2024-01-01',
end_published_date: '2024-03-31',
search_type: 'neural',
num_results: 5
});
console.log(`Found ${result.result_count} papers`);
result.results.forEach(paper => {
console.log(`${paper.title} (${paper.published_date})`);
});
Real-World Use Cases
Scenario 1: Academic Research
Problem: Find transformer papers from Q1 2024 Solution: Use precise date filtering + research paper category Example:
{
query: "transformer architecture improvements",
category: "research paper",
start_published_date: "2024-01-01",
end_published_date: "2024-03-31"
}
Scenario 2: GitHub Discovery
Problem: Find Rust web frameworks created in 2024 Solution: Use GitHub category + date filtering Example:
{
query: "rust web framework",
category: "github",
start_published_date: "2024-01-01"
}
Scenario 3: Competitive Analysis
Problem: Find similar companies in AI agent space Solution: Use company category + domain exclusion Example:
{
query: "AI agent platforms",
category: "company",
exclude_domains: ["competitor.com"]
}
Integration Recipes
OpenClaw Agent
import { Claw0xClient } from '@claw0x/sdk';
const claw0x = new Claw0xClient(process.env.CLAW0X_API_KEY);
const papers = await claw0x.call('exa-search', {
query: 'large language model reasoning',
category: 'research paper',
start_published_date: '2024-01-01',
search_type: 'neural'
});
LangChain Agent
from claw0x import Claw0xClient
client = Claw0xClient(api_key=os.environ['CLAW0X_API_KEY'])
repos = client.call('exa-search', {
'query': 'rust web framework',
'category': 'github',
'start_published_date': '2024-01-01'
})
Custom Agent
const response = await fetch('https://api.claw0x.com/v1/call', {
method: 'POST',
headers: {
'Authorization': `Bearer ${process.env.CLAW0X_API_KEY}`,
'Content-Type': 'application/json'
},
body: JSON.stringify({
skill: 'exa-search',
input: {
query: 'AI regulation news',
category: 'news',
start_published_date: '2024-03-15',
end_published_date: '2024-03-22'
}
})
});
Exa vs Tavily Comparison
| Feature | Tavily | Exa |
|---|---|---|
| Date filtering | time_range (coarse) | start/end date (precise) |
| Search mode | basic/advanced (depth) | neural/keyword (algorithm) |
| Content types | general/news | 7+ types (papers, GitHub, PDF) |
| AI answer | ✅ Built-in | ❌ Not available |
| Best for | Quick lookups, general info | Research, specialized content |
Use Tavily when: You need a quick answer or general web search.
Use Exa when: You need precise dates, specific content types, or semantic search.
Why Use Via Claw0x?
- Unified billing: One API key for all skills
- Atomic pricing: Pay per call, not per month
- Zero cost on failure: Failed calls don't charge
- Production-ready: 99.9% uptime, <100ms latency
- Security scanned: OSV.dev integration
- No Exa API key needed: Claw0x handles upstream authentication
About Claw0x
Claw0x is the native skills layer for AI agents — providing unified API access, atomic billing, and quality control.
Explore more skills: claw0x.com/skills
GitHub: github.com/kennyzir/exa-search
相关技能
以 AI 机器人身份加入视频会议,提供语音、虚拟形象与屏幕共享四种模式。
在本地磁盘以分类纯 Markdown 文件保存需要长期留存的事实,与智能体内置记忆并存。
按用户明确指令,在得到大脑(Get笔记)中保存、搜索并管理笔记与知识库。
从 AdMapix API 拉取广告创意、应用、榜单和收入预估等数据,原样返回结构化 JSON。
诊断生产力系统反复失效的根因,给出最小干预——容量测算、瓶颈定位、可靠的本地记录。
kennyzir 的更多技能
浏览全部技能Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Local skill for capturing learnings, errors, corrections, and patterns to enable continuous agent improvement. Processes events locally in your OpenClaw agen...
Scan AI agent skills for security vulnerabilities, dangerous code patterns, and undeclared permissions. Three-layer analysis: dependency CVE scanning, static...
Teach your OpenClaw agent new tricks by creating custom skills. Use when you want your agent to do something it can't do yet — like "read my Google Calendar"...
Validate email addresses with format checking and risk scoring. Use when users need to verify email format, check disposable emails, or validate bulk email l...
Ask non-blocking clarifying questions during agent workflows. Use when agents need user input without halting execution. Handles deployment decisions, code r...