A cognitive enhancement skill that forces AI agents to engage in internal pro-and-con debates to ensure high-quality, balanced outputs.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install devil-advocate
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 devil-advocate 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 Devil's Advocate?
The Devil's Advocate skill is a sophisticated cognitive framework designed for AI agents within the Openclaw Skills library. It mandates a 'think first, output later' philosophy, requiring the agent to conduct a rigorous internal debate before presenting a final answer. By actively seeking flaws and challenging its own logic, the agent moves beyond superficial responses to deliver deep, well-vetted insights.
This skill is rooted in the principles of Red Teaming and critical thinking. It transforms the standard linear generation process into a dialectic workflow where the agent acts as its own harshest critic, ensuring that the final output has survived a multi-angle review and rigorous self-challenge.
Devil's Advocate Use Cases
- Designing complex technical solutions that require multi-faceted validation.
- Conducting deep-dive code reviews to identify non-obvious optimization opportunities.
- Performing root cause analysis where initial assumptions must be challenged.
- Evaluating strategic decisions and trade-offs to ensure a balanced perspective.
- Any high-stakes scenario where accuracy and risk assessment are more important than speed.
How Devil's Advocate Works
- Receive the initial User Request and initialize the thinking protocol.
- Draft an internal 'Pro' answer representing the most likely or immediate solution.
- Execute a 'Self-refutation' (Con) phase to find logical flaws, counterexamples, and hidden risks.
- Integrate the findings from the debate to refine and synthesize a superior response.
- Deliver the final, polished output to the user.
Devil's Advocate Setup
To integrate this skill into your agentic workflow, add the definition to your Openclaw Skills manifest:
# Clone the repository
git clone https://github.com/openclaw/skills.git
# Navigate to the devil-advocate directory
cd skills/devil-advocate
# Initialize the skill in your local environment
openclaw install devil-advocate
Devil's Advocate Data Schema & Taxonomy
The Devil's Advocate skill organizes its internal reasoning using a structured cognitive taxonomy:
| Data Component | Description |
|---|---|
| Logic Verification | Metadata tracking logical consistency and reasoning chains. |
| Assumption Log | A list of challenged implicit assumptions identified during the 'Con' phase. |
| Risk Profile | A set of potential negative impacts or edge cases discovered. |
| Alternative Matrix | Data regarding secondary solutions considered during the debate. |
Devil's Advocate Advanced Features
- Multi-angle review capabilities that analyze problems from at least three distinct perspectives.
- Automated counterexample searching to disprove premature conclusions.
- Integrated risk assessment modules that flag potential downsides of suggested actions.
- Seamless integration with other Openclaw Skills to provide a 'Debate Hook' for complex multi-agent workflows.
SKILL.md
Loading
Related Openclaw Skills
clip-path-generate
A specialized tool for generating precise CSS clip-path values for complex shapes and layouts.
CIDR Calculator
A comprehensive network utility for calculating subnet parameters, host ranges, and IP classifications from CIDR notation.
Sci-Hub Downloader
A streamlined command-line utility for Openclaw Skills that retrieves academic papers from multiple Open Access and shadow library sources.
OpenAI Whisper (CLI)
A local, privacy-focused speech-to-text engine that leverages the Whisper CLI to transcribe and translate audio without external API dependencies.
Agent Autoresearch
An autonomous self-research loop that enables AI agents to propose, test, and integrate their own behavioral and technical improvements.
Trending BBQ Guide
A specialized AI skill providing curated recommendations, real-time queue data, and optimized travel routes for trending BBQ destinations.
Featured*
