← 返回 Skills 市场
downdawn

serpshot

作者 Dylan · GitHub ↗ · v1.1.0 · MIT-0
cross-platform ✓ 安全检测通过
283
总下载
0
收藏
1
当前安装
3
版本数
在 OpenClaw 中安装
/install serpshot
功能描述
Use Serpshot Google Search API to perform web searches and image searches.
使用说明 (SKILL.md)

\r \r

Skill: Serpshot Google Search API\r

\r Perform Google web searches and image searches using the Serpshot API.\r \r

When to Use\r

\r

  • User says: search / find / google / lookup / research / look up / browse\r
  • User says: 查 / 搜 / 找 / 调研 / 查一下 / 搜索 / 查询 / 找一下 / 查资料\r
  • Need real-time web information not in training data\r
  • Need current news, prices, documentation, or any live data\r
  • Need image search results\r \r

Setup (run once)\r

\r

  1. Get API key: https://serpshot.com/dashboard\r
  2. Set environment variable:\r
    • Mac/Linux: export SERPSHOT_API_KEY=your_key\r
    • Windows CMD: set SERPSHOT_API_KEY=your_key\r
    • Windows PowerShell: $env:SERPSHOT_API_KEY="your_key"\r \r

Tools\r

\r

  • exec — Run Python to call Serpshot API\r \r

How to Use\r

\r

Web Search\r

\r

import requests\r
import os\r
\r
api_key = os.environ.get("SERPSHOT_API_KEY")\r
if not api_key:\r
    raise ValueError("SERPSHOT_API_KEY is not set. Get your key at https://serpshot.com/dashboard")\r
\r
response = requests.post(\r
    "https://api.serpshot.com/api/search/google",\r
    headers={"X-API-Key": api_key, "Content-Type": "application/json"},\r
    json={\r
        "queries": ["your search query here"],\r
        "type": "search",\r
        "num": 10,       # results per page (1-100)\r
        "gl": "us",      # country: us/cn/gb/jp/de/ca/fr/...\r
        "hl": "en",      # language: en/zh-Hans/ja/...\r
    }\r
)\r
\r
data = response.json()\r
if data.get("code") != 200:\r
    raise RuntimeError(f"API error {data.get('code')}: {data.get('msg')}")\r
\r
for r in data["data"]["results"]:\r
    print(f"{r['position']}. {r['title']}")\r
    print(f"   {r['link']}")\r
    print(f"   {r['snippet']}")\r
    print()\r
```\r
\r
### Image Search\r
\r
```python\r
import requests\r
import os\r
\r
api_key = os.environ.get("SERPSHOT_API_KEY")\r
\r
response = requests.post(\r
    "https://api.serpshot.com/api/search/google",\r
    headers={"X-API-Key": api_key, "Content-Type": "application/json"},\r
    json={\r
        "queries": ["your image query here"],\r
        "type": "image",\r
        "num": 10,\r
        "gl": "us",\r
    }\r
)\r
\r
data = response.json()\r
if data.get("code") != 200:\r
    raise RuntimeError(f"API error {data.get('code')}: {data.get('msg')}")\r
\r
for r in data["data"]["results"]:\r
    print(f"{r['position']}. {r['title']}")\r
    print(f"   Source: {r.get('source', '')}")\r
    print(f"   Link: {r['link']}")\r
    print(f"   Thumbnail: {r.get('thumbnail', '')}")\r
    print()\r
```\r
\r
## Parameters\r
\r
| Parameter | Default  | Description                                    |\r
|-----------|----------|------------------------------------------------|\r
| queries   | required | Search queries array (max 100)                 |\r
| type      | "search" | "search" or "image"                            |\r
| num       | 10       | Results per page (1-100)                       |\r
| page      | 1        | Page number for pagination                     |\r
| gl        | "us"     | Country code: us/cn/gb/jp/de/ca/fr/id/mx/sg    |\r
| hl        | "en"     | Language: en/zh-Hans/ja/ko/de/fr/...           |\r
\r
## Response Format\r
\r
```json\r
{\r
  "code": 200,\r
  "msg": "Success",\r
  "data": {\r
    "results": [\r
      {\r
        "title": "Result Title",\r
        "link": "https://example.com",\r
        "snippet": "Result description...",\r
        "position": 1\r
      }\r
    ],\r
    "total_results": "About 12,300,000 results",\r
    "search_time": 0.45,\r
    "credits_used": 1\r
  }\r
}\r
```\r
\r
## Example Tasks\r
\r
### Search for latest AI news (English)\r
```\r
queries: ["AI news 2026"]\r
gl: "us"\r
num: 5\r
```\r
\r
### Search Chinese results\r
```\r
queries: ["人工智能 最新消息"]\r
gl: "cn"\r
hl: "zh-Hans"\r
num: 10\r
```\r
\r
### Image search\r
```\r
queries: ["minimalist UI design"]\r
type: "image"\r
num: 10\r
```\r
\r
## Error Codes\r
\r
| Code | Meaning                  | Action                                      |\r
|------|--------------------------|---------------------------------------------|\r
| 400  | Bad request              | Check parameter format                      |\r
| 401  | Invalid API key          | Verify SERPSHOT_API_KEY is set correctly     |\r
| 402  | Insufficient credits     | Top up at https://serpshot.com/dashboard    |\r
| 429  | Rate limit exceeded      | Slow down requests                          |\r
\r
## Notes\r
\r
- Each search query uses 1 credit\r
- Check remaining credits: `GET https://api.serpshot.com/api/credit/available-credits`\r
- Full API docs: https://serpshot.com/docs\r
安全使用建议
This skill appears to do what it says: it sends search queries to Serpshot using your SERPSHOT_API_KEY. Before installing, verify serpshot.com and the API provider are trustworthy for your data, be aware search queries (and results) go to a third party, and understand billing/credits and rate limits. Ensure your agent runtime has Python and the requests library available (SKILL.md examples assume them) or adapt the calls to supported tools. Store the API key securely and revoke it if you later suspect misuse.
功能分析
Type: OpenClaw Skill Name: serpshot Version: 1.1.0 The serpshot skill is a legitimate integration for the Serpshot Google Search API. The instructions in SKILL.md provide standard Python code for performing web and image searches via the api.serpshot.com endpoint, using the SERPSHOT_API_KEY environment variable for authentication as intended. No malicious behaviors, data exfiltration, or prompt injection attacks were detected.
能力评估
Purpose & Capability
Name/description match the declared requirement (SERPSHOT_API_KEY) and the SKILL.md shows direct calls to Serpshot endpoints. Minor mismatch: the runtime examples use Python and the 'requests' library but the registry metadata lists no required binaries or install steps; this is a usability/declared-dependency omission rather than a functional mismatch.
Instruction Scope
SKILL.md instructs only how to call Serpshot API endpoints, how to set the API key, expected parameters, and how to handle responses. It does not ask the agent to read unrelated files, access other environment variables, or transmit data to unexpected endpoints.
Install Mechanism
Instruction-only skill with no install spec — lowest-risk delivery. There are no downloads, extract steps, or third-party install sources.
Credentials
Only a single credential (SERPSHOT_API_KEY) is required and used by the instructions. The key is appropriate for the stated purpose. No unrelated secrets or config paths are requested.
Persistence & Privilege
Skill does not request always:true or other elevated persistence. It is user-invocable and allows normal autonomous invocation; this is expected for a web-search integration.
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 serpshot
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /serpshot 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
v1.1.0
- Added structured front matter with name, description, version, license, and metadata. - No functional code changes; documentation update only. - Documentation now specifies required environment variable and API homepage/documentation links in metadata.
v1.0.1
- Improved documentation for setup, now clearly explains how to set the API key environment variable. - Expanded and clarified trigger phrases, including multiple languages. - Added concise example code snippets for both web and image searches. - Updated parameter descriptions and example tasks for better clarity. - Refined error handling section to use a table format. - Added notes on checking credits and referenced full API documentation.
v1.0.0
- Initial release of Serpshot Google Search API integration. - Perform Google web and image searches using the Serpshot API. - Support for up to 100 queries per request, with customizable location and language parameters. - Requires user-provided Serpshot API key for all searches. - Detailed usage instructions and example search tasks included.
元数据
Slug serpshot
版本 1.1.0
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 3
常见问题

serpshot 是什么?

Use Serpshot Google Search API to perform web searches and image searches. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 283 次。

如何安装 serpshot?

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

serpshot 是免费的吗?

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

serpshot 支持哪些平台?

serpshot 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 serpshot?

由 Dylan(@downdawn)开发并维护,当前版本 v1.1.0。

💬 留言讨论