Search

PythonReactSEOPDF
OpenClaw

serpshot

Use Serpshot Google Search API to perform web searches and image searches. Use when user needs to search Google for information, research topics, or get search results. Supports up to 100 queries per request, various locations and languages.

downdawn0 source installs☆ 0 Repository stars

Installation

Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.

SkillHub CLI

skillhub install downdawn/serpshot

Inspect the source and compatibility requirements, then follow its installation steps.

Give your agent the source link and ask it to inspect instructions and dependencies before explaining the installation steps.

View source ↗Guides

Skill instructions

Skill: Serpshot Google Search API

Perform Google searches using Serpshot API.

When to Use

  • User asks to "search", "google", "查一下", "调研" something
  • Need to get web search results for a topic
  • Need image search results

Tools

  • exec - Run Python to call Serpshot API

How to Use

Basic Search
import requests
import json
import os

# Get API key - YOU MUST ASK USER FOR API KEY
api_key = os.environ.get("SERPSHOT_API_KEY", "YOUR_API_KEY")

url = "https://api.serpshot.com/api/search/google"

headers = {
    "X-API-Key": api_key,
    "Content-Type": "application/json"
}

payload = {
    "queries": ["your search query here"],
    "type": "search",  # or "image"
    "num": 10,  # results per page (1-100)
    "page": 1,
    "location": "US",  # US, CN, JP, GB, DE, etc.
    "lr": "en",  # language restriction
    "gl": "us"  # geolocation
}

response = requests.post(url, headers=headers, json=payload)
data = response.json()

# Parse results
for result in data.get("data", {}).get("results", []):
    print(f"{result['position']}. {result['title']}")
    print(f"   {result['link']}")
    print(f"   {result['snippet']}")
    print()
Parameters
Parameter Type Required Description
queries array[string] Yes Search queries (max 100)
type string No "search" or "image", default: "search"
num integer No Results per page (1-100), default: 10
page integer No Page number, default: 1
location string No Country code (US, CN, JP, GB, DE, etc.), default: US
lr string No Language restriction (en, zh-Hans, etc.), default: en
gl string No Geolocation (us, cn, etc.), default: us
Response Format
{
  "code": 200,
  "msg": "Success",
  "data": {
    "results": [
      {
        "title": "Result Title",
        "link": "https://example.com",
        "snippet": "Result description...",
        "position": 1
      }...

Source information

Source
github
Repository
openclaw/skills
Path
skills/downdawn/serpshot
Version
—
Commit
d35794a7db7504ae906ae08e10d63bcc7a73c685
Classification source
rules
Status
active
Visibility
public

These signals come from indexed source analysis and may lag behind changes. Check the current source files.

Extracted content

SKILL.md
# Skill: Serpshot Google Search API

Perform Google searches using Serpshot API.

## When to Use

- User asks to "search", "google", "查一下", "调研" something
- Need to get web search results for a topic
- Need image search results

## Tools

- `exec` - Run Python to call Serpshot API

## How to Use

### Basic Search

```python
import requests
import json
import os

# Get API key - YOU MUST ASK USER FOR API KEY
api_key = os.environ.get("SERPSHOT_API_KEY", "YOUR_API_KEY")

url = "https://api.serpshot.com/api/search/google"

headers = {
    "X-API-Key": api_key,
    "Content-Type": "application/json"
}

payload = {
    "queries": ["your search query here"],
    "type": "search",  # or "image"
    "num": 10,  # results per page (1-100)
    "page": 1,
    "location": "US",  # US, CN, JP, GB, DE, etc.
    "lr": "en",  # language restriction
    "gl": "us"  # geolocation
}

response = requests.post(url, headers=headers, json=payload)
data = response.json()

# Parse results
for result in data.get("data", {}).get("results", []):
    print(f"{result['position']}. {result['title']}")
    print(f"   {result['link']}")
    print(f"   {result['snippet']}")
    print()
```

### Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| queries | array[string] | Yes | Search queries (max 100) |
| type | string | No | "search" or "image", default: "search" |
| num | integer | No | Results per page (1-100), default: 10 |
| page | integer | No | Page number, default: 1 |
| location | string | No | Country code (US, CN, JP, GB, DE, etc.), default: US |
| lr | string | No | Language restriction (en, zh-Hans, etc.), default: en |
| gl | string | No | Geolocation (us, cn, etc.), default: us |

### Response Format

```json
{
  "code": 200,
  "msg": "Success",
  "data": {
    "results": [
      {
        "title": "Result Title",
        "link": "https://example.com",
        "snippet": "Result description...",
        "position": 1
      }...

Related skills

OpenClaw

ai-maestro

23blocks-os

AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agent-to-agent messaging. Manage Claude, Codex or any AI Agent from one dashboard. Move Agents between c...

OpenClaw

registry-broker-skills

hashgraph-online

AI agent skills for the Universal Registry - search, chat, and register 72,000+ agents across 14+ protocols. Works with Claude, Codex, Cursor, OpenClaw, and any AI assistant.

OpenClaw

skills-manager

rito-w

A cross-platform skills manager for AI IDEs. Search marketplace, download locally, and install to Claude, Cursor, Windsurf, and more with one click.