A rigorous 4-round reasoning protocol designed to guide AI agents through exhaustive landscape mapping, risk assessment, and strategic synthesis.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install shadows-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 shadows-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 Deep Research Protocol?
The Deep Research protocol is a specialized reasoning framework designed to empower AI agents with human-level strategic depth. As a core component of the Openclaw Skills ecosystem, this skill implements a structured 4-round process: Explorer, Devil's Advocate, Multi-Perspective Synthesis, and Crystallize. Unlike standard search queries, this protocol forces the agent to move beyond surface-level answers by actively seeking out risks, hidden costs, and alternative viewpoints.
By utilizing this skill, developers can transform an AI agent into a high-level consultant capable of handling architectural decisions, technology evaluations, and complex strategic planning. It is specifically designed for scenarios where the cost of a wrong decision is high, ensuring that Openclaw Skills provide more than just code—they provide actionable intelligence and validated roadmaps.
Deep Research Protocol Use Cases
- Evaluating major architectural decisions such as Monolith vs. Microservices or serverless migrations.
- Comparing multiple databases, languages, or cloud providers using standardized scoring.
- Strategic technology planning that requires a deep dive into community maturity and scaling limits.
- Responding to complex problem statements where no obvious solution exists.
- Executing thorough landscape analysis when a user triggers the "deep research" or "explore deeply" commands.
How Deep Research Protocol Works
- Round 1 - Explorer: The agent maps the technological landscape exhaustively, identifying 5-10 major options, tools, or approaches including emerging trends.
- Round 2 - Devil's Advocate: The agent ruthlessly stress-tests every discovered option, identifying failure modes, hidden costs, and scaling limitations.
- Round 3 - Multi-Perspective Synthesis: Options are evaluated through five professional lenses: Engineering, Architecture, Product, Security, and Business.
- Round 4 - Crystallize: All findings are synthesized into a final decision document featuring a primary recommendation, a confidence score, a fallback option, and concrete next steps.
Deep Research Protocol Setup
This protocol is a reasoning-based extension for AI agents and does not require external binaries or local filesystem access. To utilize this within the Openclaw Skills framework, ensure your agent's system prompt or tool-calling configuration includes the Deep Research definitions.
To trigger the protocol manually, use a prompt such as:
# Standard trigger command
"Apply the deep research protocol to evaluate [Technology A] vs [Technology B]"
Deep Research Protocol Data Schema & Taxonomy
The Deep Research skill generates a structured markdown report that organizes data into a clear hierarchy for stakeholders. This is a hallmark of high-quality Openclaw Skills.
| Phase | Output Type | Description |
|---|---|---|
| Landscape | List | Mapping of 5-10 discovered frameworks or tools. |
| Risk Matrix | Detailed Analysis | 3-5 identified weaknesses and failure modes per option. |
| Perspective Matrix | Table | Comparative scoring across 5 distinct professional viewpoints. |
| Final Recommendation | Synthesis | Actionable decision with a confidence level (X/10). |
| Action Plan | Checklist | Concrete next steps including PoC tasks and benchmarks. |
Deep Research Protocol Advanced Features
- Multi-lens evaluation ensures that technical merit is balanced against business cost and security compliance.
- Mandatory contrarian thinking prevents the agent from falling into confirmation bias or premature convergence.
- Evidence-based constraints require every claim to be backed by data points or community adoption metrics.
- Seamless integration with other Openclaw Skills for automated technical discovery and documentation.
- Built-in risk mitigation through the identification of fallback options for every major recommendation.
SKILL.md
Loading
Related Openclaw Skills
Context Optimizer
Context Optimizer is a token economy protocol designed to reduce redundancy and prioritize critical context for AI agents.
Bug Hunter
A multi-technique debugging protocol for AI agents designed to triage, investigate, and fix software defects with a mandatory cleanup guarantee.
Zhihu Assistant
An automated workflow tool designed to monitor Zhihu trending topics, generate AI-powered responses, and manage review queues via Feishu.
VibeTrader
VibeTrader is an AI-driven trading platform that enables users to build, backtest, and deploy automated trading bots for stocks and crypto using natural language.
Deploy Guardian
An automated 6-gate verification system designed to validate code health and security before any production or staging deployment.
Doc Forge
Doc Forge is an intelligent documentation engine that analyzes source code to generate professional READMEs, API references, and architectural overviews.
Featured*
