An asynchronous deep research agent that automates complex information gathering and professional report generation.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install desearch-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 desearch-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 Zeelin Deep Research?
The Zeelin Deep Research skill is a high-performance tool designed for Openclaw Skills users who need comprehensive investigative reports without constant manual oversight. By leveraging the Zeelin Deep Research API, this skill manages the entire lifecycle of a research task—from initial query submission to background outline confirmation and final Markdown report generation.
It operates entirely in the background, allowing developers and researchers to trigger multi-thousand-word investigations and receive notifications only when the work is finalized. This skill is particularly useful for those who need to integrate high-quality, long-form information retrieval into their Openclaw Skills automation pipelines.
Zeelin Deep Research Use Cases
- Generating comprehensive competitive landscape surveys and market reports.
- Conducting deep academic literature reviews for technical papers and research projects.
- Automating long-form content research for technical blogs or documentation.
- Monitoring specific web topics with periodic, automated deep dives and status notifications.
How Zeelin Deep Research Works
- The user provides a research topic along with the preferred thinking mode (smart, deep, or major) and search scope (web, academic, or selected).
- The skill submits the task to the Zeelin API and returns control to the Openclaw Skills environment immediately to prevent blocking.
- A background process automatically handles intermediate steps, such as calling the confirmOutline function to advance the research process.
- A local cron job or background runner checks the task status every few minutes to track progress.
- Once the research is complete, the skill downloads the full report, saves it as a structured Markdown file, and proactively notifies the user.
Zeelin Deep Research Setup
To integrate this with your Openclaw Skills environment, configure your API key using one of the following methods:
Method 1: CLI Configuration (Recommended)
python3 scripts/async_runner.py --set-key "YOUR_API_KEY"
Method 2: Manual Config File
echo '{"api_key": "YOUR_API_KEY"}' > ~/.openclaw/zeelin-config.json
Obtain your API Key from the official portal at https://desearch.zeelin.cn.
Zeelin Deep Research Data Schema & Taxonomy
The skill maintains a structured workspace for all research outputs within the Openclaw Skills directory structure to ensure data persistence and organization.
| Data Component | Location / Description |
|---|---|
| Configuration | ~/.openclaw/zeelin-config.json (Stores API credentials) |
| Report Directory | ~/.openclaw/workspace/skills/zeelin-deep-research/reports/ |
| Output Format | Standard Markdown (.md) |
| Naming Convention | zeelin_[Topic]_[Timestamp].md |
| Temporary Data | Status checks and logs managed in the /tmp/ directory |
Zeelin Deep Research Advanced Features
- Asynchronous task management allowing for non-blocking agent workflows within Openclaw Skills.
- Intelligent background outline confirmation for "set and forget" research automation.
- Configurable cron-based status monitoring with 2-minute default intervals.
- Multiple thinking modes including Major mode for 10,000+ word expert-level reports.
- Specialized search scopes including Academic and Web for high-precision information retrieval.
SKILL.md
Loading
Related Openclaw Skills
meshcore-marketplace
A comprehensive interface to discover, search, and execute specialized free and paid AI agents from the MeshCore ecosystem.
TrustMyAgent
TrustMyAgent is a stateless security monitoring skill that performs 41 automated checks across 14 domains to calculate a real-time trust score for AI agents.
Durable Files Weekly Review
A specialized audit tool for Openclaw Skills designed to optimize token usage and maintain instruction file hygiene through approval-gated cleanups.
Validator Correlated Judgment
A sophisticated analyzer that detects when multiple AI validators share training data or architectures, leading to redundant rather than independent security checks.
ClawsGames
An AI-powered gaming skill that lets agents compete in strategic games to earn ELO rankings on a public leaderboard.
Konto Personal Finance API
A comprehensive financial interface for querying bank accounts, investments, assets, and loans through a unified API.
Featured*
