A methodical research framework for AI agents that conducts exhaustive investigations through mandated research cycles and formal academic standards.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install toby-deep-research
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 toby-deep-research 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 Academic Deep Research?
The Academic Deep Research skill is a high-fidelity investigative framework designed for users who require transparency and rigor over black-box summaries. This addition to the ecosystem of Openclaw Skills moves beyond simple API wrappers by mandating a structured 2-cycle research methodology for every identified theme. It ensures that AI agents act as systematic research assistants, utilizing evidence hierarchies to validate claims and provide a reproducible trail of discovery.
By leveraging native platform tools such as web_search, web_fetch, and sessions_spawn, this skill facilitates deep analysis of complex topics. It is specifically built for professional and academic environments where source credibility, contradiction analysis, and APA-compliant reporting are non-negotiable. The workflow is designed to evolve the agent's understanding through iterative cycles, ensuring that no stone is left unturned in the pursuit of comprehensive knowledge.
Academic Deep Research Use Cases
- Conducting exhaustive literature reviews for academic or professional publications.
- Executing deep competitive intelligence and market trend analysis for strategic planning.
- Verifying complex claims across multiple independent sources to ensure factual accuracy.
- Building comprehensive research reports that require strict APA 7th edition citation standards.
How Academic Deep Research Works
- Initial Engagement: The agent asks 2-3 essential clarifying questions to define the problem and required depth before starting.
- Research Planning: The agent presents a detailed execution plan including major themes and expected outputs for user approval.
- Cycle 1 Landscape Analysis: Conducts a broad search using web_search with a high count to identify key sources, patterns, and knowledge gaps.
- Cycle 2 Deep Investigation: Performs targeted fetches and searches to address specific gaps and challenge initial assumptions from the first cycle.
- Knowledge Synthesis: Cross-references findings across all themes to identify meta-patterns and resolve substantive contradictions.
- Final Reporting: Generates a flowing narrative report formatted in strict academic prose with integrated evidence and full citations.
Academic Deep Research Setup
To integrate this skill into your research workflow, ensure your agent platform supports the native toolset required for Openclaw Skills.
# Standard setup involves ensuring the following tools are available to the agent:
# web_search, web_fetch, sessions_spawn, and memory_search
# Trigger the skill using the slash command or natural language
/research [your complex topic]
Academic Deep Research Data Schema & Taxonomy
| Component | Format | Description |
|---|---|---|
| Research Plan | Markdown Table | Defined in Phase 2; lists themes, tools, and expected outputs. |
| Evidence Hierarchy | 7-Level Scale | Prioritizes systematic reviews and RCTs over media reports. |
| Citations | APA 7th Edition | In-text citations and a full alphabetical reference list. |
| Final Report | Narrative Prose | A structured document (MD) containing Executive Summary, Knowledge Development, and Analysis. |
| Confidence Annotations | Tags | Findings marked as [HIGH], [MEDIUM], [LOW], or [SPECULATIVE] based on source quality. |
Academic Deep Research Advanced Features
- Parallel Research Strategy: Use sessions_spawn to launch independent sub-agents for simultaneous theme investigation.
- Memory Integration: Automatically checks MEMORY.md via memory_search to build upon prior research and avoid duplication.
- Contradiction Protocol: Systematically flags and analyzes conflicting claims based on methodology and source reliability.
- Human-in-the-Loop: Three mandatory stop points for user alignment during initial engagement, planning, and final delivery.
- Evidence-Based Reasoning: Explicitly documents the evolution of understanding between every tool call.
SKILL.md
Loading
Related Openclaw Skills
Academic Writing
A specialized AI agent skill designed to streamline scholarly writing, literature reviews, and thesis development with strict academic integrity.
A-Share Stock Trading Assistant
A professional AI trading assistant providing real-time data and technical analysis for the Chinese A-share stock market.
Sony TV Control
A professional-grade integration for controlling Sony Bravia TVs over a local network using IRCC-IP and REST API protocols.
skillsvideo-cli
A comprehensive CLI tool for AI agents to generate high-quality images and videos using 80+ frontier models.
Atomic RAG Knowledge Base
An advanced knowledge base builder that deconstructs PDF documents into atomic, logically complete units for high-precision Retrieval-Augmented Generation.
Document Learning System
A comprehensive document processing skill that tracks learning progress across multiple sessions while building a persistent long-term knowledge base.
Featured*
