An expert research analyst skill that transforms natural language queries into structured, evidence-scored, and decision-ready markdown reports.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install deep-researcher-pro
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 deep-researcher-pro 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 Deep Researcher v1?
Deep Researcher is a high-fidelity research engine designed for the Openclaw Skills ecosystem. It goes beyond simple summarization by executing a multi-angle research protocol that investigates consensus, identifies divergences, and tracks failed paths within a specific domain. By simulating a professional analyst, it ensures every claim is traceable to a source and validated through a rigorous evidence-scoring framework.
The skill is uniquely engineered to handle global research tasks by automatically detecting the relevant region of a topic and performing searches in the official local language. Whether comparing complex technologies or updating existing market reports, Deep Researcher delivers a falsifiable and structured .md file optimized for executive decision-making.
Deep Researcher v1 Use Cases
- Conducting deep dives into specific market sectors like Southeast Asia e-commerce or German SaaS.
- Performing head-to-head comparative analysis between multiple technical subjects or vendors.
- Updating existing research reports with the latest data while preserving historical context.
- Verifying facts and evidence across user-provided local documents without using external web search.
- Identifying core tensions and non-negotiable constraints within a specific industry or technology stack.
How Deep Researcher v1 Works
- Semantic Intent Analysis: The skill parses the user's natural language query to determine the number of subjects, primary intent (research, compare, or update), and the target region.
- Startup & Scope: It verifies search tool availability and defines the domain boundaries, including the detection of necessary research languages based on the region.
- Multi-Angle Collection: It executes five distinct search angles (Factual, Critical, Practitioner, Forward-looking, and Cross-domain) to ensure a 360-degree view.
- Evidence Scoring: Collected data is scored (High, Medium, Low) based on source authority and independent cross-verification.
- Synthesis & Extraction: The agent identifies consensus, highlights minority-view divergences, and documents failed paths or known constraints.
- Report Generation: A structured markdown report is compiled using localized templates and saved directly to the user's local filesystem.
Deep Researcher v1 Setup
Deep Researcher requires a functional web search tool. Configure one of the following environment variables before execution:
# For Serper (Recommended)
export SERPER_API_KEY=your_key_here
# For Tavily (Research Optimized)
export TAVILY_API_KEY=your_key_here
# For Brave Search
export BRAVE_API_KEY=your_key_here
Once configured, invoke the skill within your agent using:
/deep-researcher [your research topic]
Deep Researcher v1 Data Schema & Taxonomy
The skill organizes research into structured markdown files with the following taxonomy:
| Section | Description |
|---|---|
| SCOPE | Defines domain boundaries, region focus, and research languages. |
| CONSENSUS | Top 5 evidence-backed facts that affect decision-making. |
| DIVERGENCES | Highlights conflicting reports and minority positions with evidence strength. |
| FAILED_PATHS | Documents historically unsuccessful approaches and reasons for failure. |
| DECISION_READINESS | Provides a confidence index (0-10) and next concrete actions. |
| SOURCES | A complete table of URLs, source types, and access status (Full-text vs Snippet). |
Deep Researcher v1 Advanced Features
- Local Language Enforcement: Automatically conducts a portion of searches in the domain's native language to capture insider insights.
- Evidence Traceability: Every numeric value and key claim is tagged with a source URL or citation to prevent hallucination.
- Decision Matrix: In comparison mode, it generates a multi-column matrix for head-to-head evaluation across various dimensions.
- Update Persistence: Intelligently reads existing reports and appends [Updated: date] tags to maintain a living research document.
- Privacy-First Research: All analysis and report generation happen locally; only search queries leave the device.
SKILL.md
Loading
Related Openclaw Skills
Klein Tools Knowledge Base
An expert knowledge skill providing deep historical and business insights into Klein Tools, the premier brand for professional electricians.
Lenox Industrial Cutting Knowledge Base
A comprehensive industrial intelligence skill providing deep insights into Lenox's 275-year history and technical cutting tool specifications.
Interior Design Automated Budget Generator
Automatically transform CAD DXF floor plans into itemized Excel budgets using historical pricing data and spatial analysis.
Generate Executive Recruiting Boutique Client Education Handout
An automated workflow for executive recruiters to generate high-quality, visual client education handouts and FAQ guides.
Makita Market Intelligence & Strategy
An analytical intelligence module for researching Makita's global power tool ecosystem, battery platform strategies, and manufacturing history.
Interior Design Engineering Budget Automation
An automated tool for generating detailed interior design engineering budgets and itemized project lists based on standardized studio templates.
Featured*
