A high-performance deep search skill for AI agents to retrieve grounded information using Jina AI's advanced search models.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install jina-deepsearch
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-deepsearch 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 DeepSearch?
Jina DeepSearch provides a robust interface for AI agents to perform complex, grounded web searches. By leveraging the AIHubMix gateway, this skill allows for seamless integration of the jina-deepsearch-v1 model into any automated workflow.
This ensures that your Openclaw Skills have access to the most relevant and up-to-date data available on the web, bridging the gap between static LLM knowledge and real-time facts. It is designed for developers who need reliable, programmatic access to search-optimized models without complex SDK overhead.
Jina DeepSearch Use Cases
- Fact-checking and grounding AI responses with live web data.
- Conducting deep technical research for coding and documentation tasks.
- Automating market research or competitive analysis within an AI agent workflow.
- Enhancing retrieval-augmented generation (RAG) pipelines with high-quality search results.
How Jina DeepSearch Works
- The user or agent initiates a search query within the environment.
- The skill constructs an authenticated HTTP request using curl directed at the AIHubMix endpoint.
- The jina-deepsearch-v1 model processes the query and performs a deep web search.
- Grounded search results are returned as a structured JSON payload for the agent to consume, analyze, or summarize.
Jina DeepSearch Setup
First, obtain an API key from AIHubMix. Then, configure your environment by setting the required variable:
export AIHUBMIX_API_KEY="sk-..."
You can verify the installation and connectivity of this search skill by running a direct curl command:
curl https://aihubmix.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $AIHUBMIX_API_KEY" \
-d '{
"model": "jina-deepsearch-v1",
"messages": [{"role": "user", "content": "Your search query"}]
}'
Jina DeepSearch Data Schema & Taxonomy
The skill utilizes the OpenAI-compatible chat completion schema via AIHubMix to deliver search results. Below is the primary metadata and request structure:
| Parameter | Type | Description |
|---|---|---|
| model | string | Must be set to jina-deepsearch-v1 for deep search functionality. |
| messages | array | Contains the role (user) and the search query content. |
| headers | object | Requires Content-Type: application/json and Bearer Authorization. |
All Openclaw Skills in this category prioritize clean JSON outputs for easy parsing by LLMs.
Jina DeepSearch Advanced Features
- Direct integration with AIHubMix for unified API management across multiple models.
- Lightweight execution via curl, ensuring compatibility with minimal containerized environments.
- Support for complex search queries that require deep crawling and indexing via Jina AI.
- High reliability and low-latency performance when incorporated into multi-agent Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Training Manager
A comprehensive workspace orchestration tool for scaffolding, maintaining, and optimizing the training lifecycle of AI agents.
TrustLog Guard
A privacy-first financial governance tool that monitors OpenClaw API spending, enforces budgets, and detects cost anomalies locally.
Book Debate (Multi-Lens)
A sophisticated analytical engine that uses multi-perspective debating to help users deeply understand ideas from books, thinkers, or personal notes.
Visual File Sorter
An intelligent file management agent that uses computer vision to identify, rename, and archive messy local files.
Wheels Router Transit Planner
A high-performance transit routing skill for AI agents providing global trip planning with deep integration for Hong Kong transportation.
QMD Search
A local indexing tool that uses BM25 and vector embeddings to search markdown collections efficiently while minimizing token usage.
Featured*
