A high-performance search skill that retrieves Google results and extracts full-page readable text for deep context research.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install openclaw-serper
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install openclaw-serper using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Openclaw Serper Search & Extraction?
The openclaw-serper skill is a sophisticated tool designed for the Openclaw Skills ecosystem that bridges the gap between simple search snippets and full-text understanding. Unlike standard search tools that only provide titles and descriptions, this skill utilizes the Serper API in conjunction with the trafilatura library to scrape and clean the actual content of the web pages it finds. This allows AI agents to ingest entire articles, documentation, or news stories directly into their context window without requiring additional browsing steps.
By providing a streamlined interface for both evergreen research and time-sensitive news, this skill ensures that developers building with Openclaw Skills can provide their agents with the most accurate and up-to-date information available on the internet. It is engineered for query discipline, encouraging precise interactions that maximize information density while minimizing redundant API usage.
Openclaw Serper Search & Extraction Use Cases
- Performing deep technical research by extracting full documentation pages rather than just search snippets.
- Monitoring current events and breaking news using the specialized news-focused search mode.
- Conducting multi-language market research by utilizing specific country and language locale flags.
- Building product comparison engines that require reading full review articles to gather detailed specifications.
How Openclaw Serper Search & Extraction Works
- The user provides a query which the agent processes into a single, high-quality search term.
- The skill invokes a Python script that communicates with the Serper API to fetch relevant Google Search or Google News results.
- For every URL returned, the system uses trafilatura to perform real-time content extraction, removing ads and navigation to find the core text.
- The results are aggregated into a structured JSON array, including metadata like the source URL, title, and the full extracted content.
- The AI agent receives this rich dataset, allowing it to answer complex questions without needing to perform follow-up web fetches.
Openclaw Serper Search & Extraction Setup
To integrate this search capability into your Openclaw Skills environment, ensure you have Python 3 installed and follow these steps:
# Install the required extraction library
pip install trafilatura
# Set up your Serper API key in the skill directory
echo "SERPER_API_KEY=your_api_key_here" > .env
Openclaw Serper Search & Extraction Data Schema & Taxonomy
The skill returns a JSON array where the first object contains query metadata and subsequent objects contain page data.
| Attribute | Description |
|---|---|
| title | The title of the web page or news article. |
| url | The direct link to the source material. |
| source | Categorized as web, news, or knowledge_graph. |
| content | The full-text extracted content (falls back to snippet if extraction is blocked). |
| date | The publication date, primarily for news results. |
Openclaw Serper Search & Extraction Advanced Features
- Dual-mode execution allowing a choice between default all-time search (5 results) and current news-focused search (6 combined results).
- Granular locale support using ISO country codes (--gl) and language codes (--hl) to ensure relevant results for non-English queries.
- Smart extraction fallback that ensures the agent receives at least a search snippet if a website blocks full scraping.
- Integrated metadata streaming that provides the agent with context about the search parameters used for the result set.
SKILL.md
Loading
Related Openclaw Skills
Openclaw Feeds: RSS News Aggregator
A lightweight RSS aggregator that fetches real-time headlines across news, gaming, and finance categories without requiring external API keys.
Drafts CLI
A macOS-native command-line interface for the Drafts app that enables programmatic note management and workflow automation.
Beeper API CLI
A specialized command-line interface and LLM-friendly wrapper that enables AI agents to read, search, and send messages across all chat networks connected to Beeper.
FTdesign HTML Generator
An automated interface builder that generates standardized HTML preview pages for lists, forms, and details using the FTdesign system.
Serper Search & Extraction
A high-speed Google search integration that extracts full-text web content for comprehensive AI research.
PR Code Reviewer
An automated senior-level code review assistant for Bitbucket Pull Requests that identifies bugs, security risks, and style violations.
Featured*
