A comprehensive toolset for converting web pages to LLM-friendly markdown and performing multi-step deep research.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install jina-ai
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 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 AI Reader & Search?
The Jina AI skill for Openclaw Skills provides a powerful interface for AI agents to interact with web content. By utilizing Jina's specialized APIs, this skill allows agents to bypass complex HTML structures and retrieve clean, markdown-formatted text from any URL, including JavaScript-heavy sites and PDF documents. It serves as a bridge between the raw web and large language models, ensuring that data is delivered in a highly digestible format.
Beyond simple page reading, this Openclaw Skills integration includes advanced search capabilities and a multi-step research agent. These tools enable agents to perform broad web searches that return LLM-optimized results or engage in DeepSearch, which combines searching, reading, and reasoning to solve complex queries that require synthesizing information from multiple sources.
Jina AI Reader & Search Use Cases
- Converting documentation pages or blog posts into clean markdown for RAG or context injection.
- Performing web searches that provide full-page content immediately available for agent analysis.
- Conducting deep, multi-source research on technical topics or current events using the DeepSearch agent.
- Extracting specific data from web pages by targeting custom CSS selectors.
- Parsing remote PDF files directly into text for document processing within Openclaw Skills.
How Jina AI Reader & Search Works
- The agent or user invokes one of the helper scripts (reader, search, or deepsearch) with a target URL or query.
- The skill attaches the JINA_API_KEY to the request header for authentication with Jina AI services.
- For URL reading, the request is sent to the Reader API which renders the page and strips away non-essential elements like ads and navigation.
- For searches, the query is processed through the Search API to find and parse the most relevant web results into markdown.
- For complex tasks, DeepSearch runs a multi-step reasoning chain to gather and synthesize data from across the web.
- The resulting clean text or structured JSON is returned to the environment for the agent to use in its workflow.
Jina AI Reader & Search Setup
To integrate this skill into your Openclaw Skills environment, follow these steps:
# 1. Get your API key from the Jina AI Dashboard (https://jina.ai/)
# 2. Set the environment variable
export JINA_API_KEY="your_jina_api_key_here"
# 3. Test the reader script
./scripts/jina-reader.sh https://example.com
# 4. Test the search script
./scripts/jina-search.sh "latest news about Openclaw Skills"
Jina AI Reader & Search Data Schema & Taxonomy
The skill organizes web data into structured formats optimized for AI consumption. The following table describes the primary data outputs:
| Output Format | Description |
|---|---|
| Text/Markdown | The default output; a clean, stripped-down version of the webpage content. |
| JSON Object | Contains metadata such as title, url, content, and timestamp. |
| DeepSearch Response | An OpenAI-compatible chat completion object containing synthesized research results. |
| Screenshots | Visual captures of pages when the X-Respond-With: screenshot header is used. |
Jina AI Reader & Search Advanced Features
- Custom CSS selectors (
X-Target-Selector,X-Remove-Selector) for precise data extraction. - Image and link summary generation to manage token budgets effectively within Openclaw Skills.
- Support for authenticated content through cookie forwarding using the
X-Set-Cookieheader. - Multi-format output support including markdown, plain text, HTML, and screenshots.
- DeepSearch reasoning agent for autonomous, multi-turn research tasks.
SKILL.md
Loading
Related Openclaw Skills
MacPilot Skills
A suite of automation skills that allow AI agents to control macOS via Accessibility APIs, handling everything from window management to OCR-based interactions.
Halocard Virtual Cards
Generate single-use virtual credit cards on the fly to complete secure online payments during automated agent tasks.
MenuVision
MenuVision transforms restaurant menus from any source into interactive, visually rich HTML digital menus using advanced AI vision and image generation.
Grok Imagine Extended
A comprehensive tool for generating high-fidelity images and cinematic videos using xAI's Grok Imagine Extended models.
Maps
A location-intelligence skill providing geocoding and routing capabilities without requiring external API keys.
Markdown Anything
A high-performance conversion tool that turns PDFs, Office documents, images, and audio into LLM-ready Markdown.
METADATA
Featured*
