Deep Research Pro is a rigorous AI research skill that enforces mandatory full-text parsing, structured data extraction, and source verification to ensure maximum analytical depth.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install deep-research-v22
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-research-v22 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 Research Pro (v2.2 - True Depth)?
Deep Research Pro is a professional-grade research framework designed for Openclaw Skills users who require absolute data integrity. Unlike standard AI summaries, this skill operates on the core principle that true depth is impossible without direct primary source reading. It forces the AI agent to move beyond surface-level web snippets into deep document analysis.
The skill implements a strict quality gate, requiring full-text parsing of PDFs and structured extraction of sample sizes, statistical significance ($95%CI$), and direct quotes. By automating the verification of citations, it eliminates hallucinations and ensures every claim in a final report is backed by a validated source card.
Deep Research Pro (v2.2 - True Depth) Use Cases
- Academic literature reviews requiring $95%CI$ and statistical significance verification.
- Technical due diligence for software or hardware specifications.
- Market research involving deep analysis of lengthy industry PDF reports.
- Competitive intelligence requiring cross-referencing of multiple conflicting data points.
- Evidence-based policy research where source traceability is a legal or professional requirement.
How Deep Research Pro (v2.2 - True Depth) Works
- Research Planning: The agent generates a structured
research/plan.mdwith at least 5 targeted search queries which must be confirmed by the user. - Full-Text Acquisition: The system attempts to download and parse the full text of identified sources using specialized scripts like
extract-from-pdf.py. - Structured Extraction: Data is extracted into individual source cards, capturing specific metrics, sample sizes, and at least 50 words of direct quote per source.
- Sourcing Verification: A mandatory check is run to ensure every claim in the draft report maps directly to an existing source card.
- Cross-Analysis: The agent identifies at least 3 sets of contradictory data points to provide a balanced, synthesized view.
- Final Report Generation: A comprehensive report is produced where every data point is tagged with a
[[card-xxx]]reference.
Deep Research Pro (v2.2 - True Depth) Setup
To deploy Deep Research Pro within your Openclaw Skills environment, ensure the following dependencies are met:
# Install PDF processing dependencies
sudo apt-get install poppler-utils
pip install pdfplumber
# Initialize the research directories
mkdir -p research sources reports analysis scripts
# Verify the core extraction scripts exist
ls scripts/extract-from-pdf.py
ls scripts/check-sourcing.sh
Deep Research Pro (v2.2 - True Depth) Data Schema & Taxonomy
Deep Research Pro organizes information using a highly structured file taxonomy to ensure Openclaw Skills can track data lineage:
| Directory | File/Type | Description |
|---|---|---|
research/ |
plan.md |
Strategic roadmap and approved search queries. |
sources/ |
card-NNN.md |
Individual source metadata, including full_text status and 50+ word quotes. |
analysis/ |
synthesis.md |
Cross-source comparison and contradiction mapping. |
reports/ |
final-report.md |
The end-product featuring mandatory [[card-xxx]] citations. |
scripts/ |
.py & .sh |
Automation tools for extraction and verification. |
Deep Research Pro (v2.2 - True Depth) Advanced Features
- Mandatory Quality Gates: Automatically rejects report generation if fewer than 10 full-text sources are analyzed.
- Automated Sourcing Check: Includes a bash-based validation script that prevents unverified claims from entering the final output.
- Conflict Detection: Specifically programmed to find and highlight contradictions between different research sources.
- Structured Metadata Parsing: Extracts 95% Confidence Intervals and specific unit values directly from technical documents.
SKILL.md
Loading
Related Openclaw Skills
Git Commit Guard
A protective git-first workflow skill for AI agents that ensures repository integrity through rigorous pre-work inspection, multi-stage validation, and structured commits.
Project Ghost
A high-performance web reading layer that converts public URLs into structured, agent-ready intelligence via a single API call.
CamScanner
A specialized skill for extracting and organizing public product features, pricing structures, and help documentation from CamScanner to streamline office collaboration.
Deep Research Pro
A professional-grade research framework that automates systematic academic, market, and competitive analysis with mandatory quality gates.
Candy Crush Saga Skill
A specialized automation skill for tracking Candy Crush Saga game events, version updates, and official community guidelines.
OpenClaw Free Web Search
A cost-free web search utility that enables OpenClaw agents to access real-time web data without requiring Brave or Perplexity API keys.
Featured*
