← 返回 Skills 市场
kennyzir

exa search

作者 claw0x · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
146
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install exa-search-pro
功能描述
Advanced web search with precise date filtering and content type selection. Use when you need academic papers, GitHub repositories, research content, or spec...
使用说明 (SKILL.md)

\r \r

Exa Search\r

\r Cloud skill by Claw0x — powered by Claw0x Gateway API.\r \r Advanced web search with precise date filtering, content type selection, and neural search. Perfect for research, competitive analysis, and specialized content discovery.\r \r

Requires Claw0x API key. Sign up at claw0x.com to get your key.\r \r

Prerequisites\r

\r

  1. Sign up at claw0x.com\r
  2. Create API key in Dashboard\r
  3. Set environment variable:\r
    # Add to ~/.openclaw/.env\r
    CLAW0X_API_KEY=ck_live_...\r
    ```\r
    

\r

Pricing\r

\r $0.005 per successful call. Failed calls are free.\r \r

  • Pay only for successful responses (2xx status)\r
  • No monthly fees, no subscriptions\r
  • Get started with $5 free credit\r \r

Quick Reference\r

\r | When This Happens | Do This | What You Get |\r |-------------------|---------|--------------|\r | Need academic papers from specific dates | Use category: "research paper" + date range | Filtered research results |\r | Find GitHub projects from 2024 | Use category: "github" + start_published_date: "2024-01-01" | Recent open-source projects |\r | Semantic search for concepts | Use search_type: "neural" | Intent-based results |\r | Exact keyword matching | Use search_type: "keyword" | Traditional search results |\r \r

5-Minute Quickstart\r

\r

Step 1: Get API Key (30 seconds)\r

Sign up at claw0x.com → Dashboard → Create API Key\r \r

Step 2: Set Environment Variable (30 seconds)\r

export CLAW0X_API_KEY="ck_live_..."\r
```\r
\r
### Step 3: Install Skill (30 seconds)\r
```bash\r
openclaw skills install exa-search\r
```\r
\r
### Step 4: Use Skill (1 minute)\r
```typescript\r
const result = await agent.run('exa-search', {\r
  query: 'transformer architecture improvements',\r
  category: 'research paper',\r
  start_published_date: '2024-01-01',\r
  end_published_date: '2024-03-31',\r
  search_type: 'neural',\r
  num_results: 5\r
});\r
\r
console.log(`Found ${result.result_count} papers`);\r
result.results.forEach(paper => {\r
  console.log(`${paper.title} (${paper.published_date})`);\r
});\r
```\r
\r
## Real-World Use Cases\r
\r
### Scenario 1: Academic Research\r
**Problem**: Find transformer papers from Q1 2024\r
**Solution**: Use precise date filtering + research paper category\r
**Example**:\r
```typescript\r
{\r
  query: "transformer architecture improvements",\r
  category: "research paper",\r
  start_published_date: "2024-01-01",\r
  end_published_date: "2024-03-31"\r
}\r
```\r
\r
### Scenario 2: GitHub Discovery\r
**Problem**: Find Rust web frameworks created in 2024\r
**Solution**: Use GitHub category + date filtering\r
**Example**:\r
```typescript\r
{\r
  query: "rust web framework",\r
  category: "github",\r
  start_published_date: "2024-01-01"\r
}\r
```\r
\r
### Scenario 3: Competitive Analysis\r
**Problem**: Find similar companies in AI agent space\r
**Solution**: Use company category + domain exclusion\r
**Example**:\r
```typescript\r
{\r
  query: "AI agent platforms",\r
  category: "company",\r
  exclude_domains: ["competitor.com"]\r
}\r
```\r
\r
## Integration Recipes\r
\r
### OpenClaw Agent\r
```typescript\r
import { Claw0xClient } from '@claw0x/sdk';\r
\r
const claw0x = new Claw0xClient(process.env.CLAW0X_API_KEY);\r
\r
const papers = await claw0x.call('exa-search', {\r
  query: 'large language model reasoning',\r
  category: 'research paper',\r
  start_published_date: '2024-01-01',\r
  search_type: 'neural'\r
});\r
```\r
\r
### LangChain Agent\r
```python\r
from claw0x import Claw0xClient\r
\r
client = Claw0xClient(api_key=os.environ['CLAW0X_API_KEY'])\r
\r
repos = client.call('exa-search', {\r
    'query': 'rust web framework',\r
    'category': 'github',\r
    'start_published_date': '2024-01-01'\r
})\r
```\r
\r
### Custom Agent\r
```javascript\r
const response = await fetch('https://api.claw0x.com/v1/call', {\r
  method: 'POST',\r
  headers: {\r
    'Authorization': `Bearer ${process.env.CLAW0X_API_KEY}`,\r
    'Content-Type': 'application/json'\r
  },\r
  body: JSON.stringify({\r
    skill: 'exa-search',\r
    input: {\r
      query: 'AI regulation news',\r
      category: 'news',\r
      start_published_date: '2024-03-15',\r
      end_published_date: '2024-03-22'\r
    }\r
  })\r
});\r
```\r
\r
## Exa vs Tavily Comparison\r
\r
| Feature | Tavily | Exa |\r
|---------|--------|-----|\r
| Date filtering | time_range (coarse) | start/end date (precise) |\r
| Search mode | basic/advanced (depth) | neural/keyword (algorithm) |\r
| Content types | general/news | 7+ types (papers, GitHub, PDF) |\r
| AI answer | ✅ Built-in | ❌ Not available |\r
| Best for | Quick lookups, general info | Research, specialized content |\r
\r
**Use Tavily when**: You need a quick answer or general web search.\r
\r
**Use Exa when**: You need precise dates, specific content types, or semantic search.\r
\r
## Why Use Via Claw0x?\r
\r
- **Unified billing**: One API key for all skills\r
- **Atomic pricing**: Pay per call, not per month\r
- **Zero cost on failure**: Failed calls don't charge\r
- **Production-ready**: 99.9% uptime, \x3C100ms latency\r
- **Security scanned**: OSV.dev integration\r
- **No Exa API key needed**: Claw0x handles upstream authentication\r
\r
## About Claw0x\r
\r
[Claw0x](https://claw0x.com) is the native skills layer for AI agents — providing unified API access, atomic billing, and quality control.\r
\r
**Explore more skills**: [claw0x.com/skills](https://claw0x.com/skills)\r
\r
**GitHub**: [github.com/kennyzir/exa-search](https://github.com/kennyzir/exa-search)\r
安全使用建议
This skill appears to be a thin client that forwards your query to Claw0x's API using the CLAW0X_API_KEY. Before installing: confirm you trust claw0x.com (the API endpoint and billing model will be tied to that provider), keep your CLAW0X_API_KEY secret and scoped/rotated if possible, and monitor usage/billing since calls are billable. If you want extra assurance, review the public repository referenced in SKILL.md to validate authorship and examine any upstream code. Finally, remember queries and returned content will transit the Claw0x service—do not send highly sensitive secrets in search queries.
功能分析
Type: OpenClaw Skill Name: exa-search-pro Version: 1.0.0 The skill is a legitimate API wrapper for the Exa Search service provided via the Claw0x gateway. The code in handler.ts correctly implements a standard HTTPS POST request to api.claw0x.com, using the required CLAW0X_API_KEY for authentication as described in the documentation. No evidence of data exfiltration, unauthorized execution, or prompt injection was found.
能力评估
Purpose & Capability
Name/description (advanced web search) match the code and SKILL.md which call the Claw0x Gateway API. The single required credential (CLAW0X_API_KEY) and the documented endpoint (https://api.claw0x.com/v1/call) are coherent with the stated purpose.
Instruction Scope
SKILL.md instructs the agent/user to set CLAW0X_API_KEY and shows example calls. The runtime instructions and handler.ts only reference that env var and a network call to Claw0x; they do not instruct reading unrelated files, scanning local data, or sending data to unexpected endpoints.
Install Mechanism
No install spec is provided (instruction-only), and the single TypeScript handler is a small client wrapper. No downloads, package installs, or archive extraction are present. The only runtime effect is an outbound API call to api.claw0x.com, which is expected for this skill.
Credentials
Only CLAW0X_API_KEY is required, which is proportional to a gateway API client. The README suggests storing it in ~/.openclaw/.env but the code reads process.env.CLAW0X_API_KEY; no other secrets or unrelated credentials are requested.
Persistence & Privilege
always:false and default agent invocation are used. The skill does not request permanent/system-wide privileges or modify other skills. Autonomous invocation is allowed (platform default) but is not combined with other concerning factors.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install exa-search-pro
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /exa-search-pro 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Exa Search 1.0.0 — Major Upgrade & Claw0x Integration - Now powered by Claw0x Gateway API: unified billing and simple API key setup - Adds support for advanced search options: precise date filtering, content type selection (papers, GitHub, news, PDFs), neural vs. keyword search - Updates documentation for new API usage, real-world scenarios, and integration recipes (OpenClaw, LangChain, custom agents) - Exa API key requirement removed; only Claw0x API key needed - Local Node script removed; all calls now routed via Claw0x platform - Full pricing transparency & failure cost protections introduced
元数据
Slug exa-search-pro
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

exa search 是什么?

Advanced web search with precise date filtering and content type selection. Use when you need academic papers, GitHub repositories, research content, or spec... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 146 次。

如何安装 exa search?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install exa-search-pro」即可一键安装,无需额外配置。

exa search 是免费的吗?

是的,exa search 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

exa search 支持哪些平台?

exa search 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 exa search?

由 claw0x(@kennyzir)开发并维护,当前版本 v1.0.0。

💬 留言讨论