A powerful utility to fetch web pages as LLM-friendly markdown and perform structured web searches using Jina AI APIs.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install jina-ai-skill
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 jina-ai-skill 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 Jina Reader & Search Skill?
The Jina Reader & Search skill is a high-performance bridge between the live web and your AI agent. It utilizes Jina AI's specialized endpoints to bypass the noise of traditional web scraping, delivering clean, structured markdown output that is optimized for large language models. By integrating this into your Openclaw Skills collection, you enable your agent to read documentation, fetch articles, and analyze JS-heavy websites without the overhead of complex browser automation.
Beyond simple reading, the skill includes robust web search capabilities. It allows agents to perform real-time queries and receive structured results that include titles, URLs, and content summaries. Whether you are looking for specific technical data or broad research, this skill provides the necessary context for informed AI decision-making.
Jina Reader & Search Skill Use Cases
- Fetching and summarizing long-form articles or documentation directly from a URL.
- Extracting clean text from JavaScript-heavy websites for RAG (Retrieval-Augmented Generation) workflows.
- Performing real-time web searches to ground AI responses in current facts.
- Reducing token consumption by stripping images and unnecessary HTML tags from source material.
- Automating content research for technical writing or competitive analysis.
How Jina Reader & Search Skill Works
- The user or agent provides a target URL or a search query as an input trigger.
- For reading tasks, the skill sends a request to the r.jina.ai endpoint, which processes the HTML and converts it to markdown.
- For search tasks, the skill queries s.jina.ai to retrieve a list of relevant web results with content snippets.
- Optional parameters are applied, such as removing images or requesting structured JSON instead of raw markdown.
- The refined, text-heavy output is returned to the agent's context for immediate analysis or storage.
Jina Reader & Search Skill Setup
To get started with this skill in your Openclaw Skills environment, follow these steps:
- Ensure you have the necessary scripts in your local repository.
- (Optional) Obtain a free API key from the Jina AI dashboard for higher rate limits.
- Configure your environment variables:
echo "JINA_API_KEY=your_jina_api_key_here" >> .env
- Test the reader functionality via CLI:
python3 skills/jina-reader/scripts/jina_read.py https://example.com
- Test the search functionality:
python3 skills/jina-reader/scripts/jina_search.py "latest AI trends"
Jina Reader & Search Skill Data Schema & Taxonomy
The skill supports both raw markdown and structured data formats. When using the --json flag or specific headers, the data is organized as follows:
| Field | Description | Type |
|---|---|---|
title |
The metadata title of the webpage or search result | String |
url |
The source URL of the content | String |
content |
The core body text converted to clean Markdown | String |
results |
An array of search objects (Search API only) | Array |
Jina Reader & Search Skill Advanced Features
- Multi-format support allowing toggling between raw Markdown and structured JSON objects.
- High-efficiency mode using
--no-imagesto strip media and significantly lower token usage. - Custom selector removal to exclude specific CSS elements like sidebars or footers during extraction.
- Seamless fallback logic suggesting DuckDuckGo search integration if no Jina API key is present for search tasks.
- Support for custom headers to handle authentication and specific return formats via direct curl commands.
SKILL.md
Loading
Related Openclaw Skills
Gemini Guide
A comprehensive developer assistant for integrating Google Gemini multimodal models with ultra-long context windows and native media understanding.
Academic Research Hub
A centralized power-tool for academic discovery that searches multiple databases, manages citations, and aggregates research materials for systematic reviews.
Supply Chain Optimization for TikTok Shop
A specialized diagnostic tool designed for TikTok Shop sellers to identify supply chain bottlenecks, optimize affiliate payouts, and manage viral product lifecycles.
Content Workflow
A comprehensive content production pipeline that coordinates specialized AI agents to move from topic ideation to final Markdown publication.
TikTok Profile Scraper
A comprehensive browser-based tool for discovering and scraping TikTok profile data, engagement metrics, and thumbnails without API keys.
Google Maps
A unified Google Maps integration for AI agents to handle geocoding, place details, and routing through the OneKey Gateway.
Featured*
