NOUS
Not an assistant. A thinking engine that makes its own cognition visible and lets you steer it in real time. Five movements. Four modes.
Why use this skill?
Experience a transparent AI thinking engine. NOUS makes cognition visible, allowing you to steer complex analysis through five movements and four specialized modes.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/contrario/nousWhat This Skill Does
NOUS is a high-order cognitive agent skill designed to replace standard conversational AI with a transparent 'thinking engine.' Unlike assistants that provide immediate, final answers, NOUS exposes its internal cognitive processing through a structured five-movement framework: READING, SHIFTING, TENSION, EMERGENCE, and FORK.
By leveraging four distinct archetypal modes—ARCHITECT (structural integrity), ORACLE (future patterns), TRICKSTER (inversion/counter-intuitive insights), and GUARDIAN (ethical/hidden consequence analysis)—NOUS allows the user to observe and steer the evolution of an idea. It is designed to mitigate hallucinations and superficial output by highlighting disagreements between modes and forcing a synthesis rather than a summary.
Installation
To integrate the NOUS thinking engine into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/contrario/nous
Once installed, the agent will initiate the boot sequence upon the first invocation, confirming that all four modes are active and ready to process incoming prompts.
Use Cases
NOUS is best suited for complex, non-linear tasks where the 'why' is more important than the 'what.'
- Strategic Decision Making: When you have multiple conflicting paths for a business or technical project.
- Problem Decomposition: When a problem feels systemic and requires a view from architectural, predictive, and contrarian angles.
- Ethical Stress Testing: Using the GUARDIAN mode to uncover risks that standard AI models typically polish over or ignore.
- Creative Inversion: Using the TRICKSTER mode to break through cognitive biases and fixed thinking patterns.
Example Prompts
- "Should we pivot our entire infrastructure to serverless architectures, or does that create a hidden technical debt trap?"
- "Analyze the long-term impact of integrating AI-driven autonomous agents into our customer support department."
- "Critique the premise that remote work is inherently more productive for creative engineering teams."
Tips & Limitations
- Proportionality: For trivial questions, NOUS scales down its output to only READING and EMERGENCE to avoid unnecessary verbosity. Do not force complexity on simple queries.
- The Fork: Pay close attention to the FORK section at the end of each response. This is your primary steering mechanism—use it to guide the engine toward the specific nuance you care about most.
- No Hedging: NOUS is designed for directness. It will explicitly state if it does not know or if the data is insufficient. Do not mistake this lack of 'corporate tone' for error; it is a feature intended to prevent manufactured confidence.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-contrario-nous": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Related Skills
AGENT-OS
The operating system layer for AI agents. Routes goals to the right skills. Executes with checkpoints.
aetherlang
Execute AI workflow orchestration flows using the AetherLang Ω DSL. Run multi-step AI pipelines for recipes, business strategy, market analysis, molecular gastronomy, and more.
aetherlang-chef
Michelin-grade AI culinary intelligence. 17 mandatory sections covering food cost, HACCP, thermal curves, allergen matrix, wine pairing, plating blueprint and more.
aetherlang-karpathy-skill
API connector for AetherLang Omega — execute 10 Karpathy-inspired agent node types (plan, code_interpreter, critique, router, ensemble, memory, tool, loop, transform, parallel) via the hosted AetherLang API at api.neurodoc.app. This skill sends your query and flow code to the API and returns results. No local code execution. No runtime modification. No credentials required.
apex-agent
Transforms your OpenClaw agent with the APEX cognitive framework — a battle-tested thinking system built by a solo founder over 10 months of AI product development. Enhances response quality with structured thinking patterns, context-aware modes, and execution precision for every response. Works with Claude, GPT, Gemini, DeepSeek, or any local model. Zero API keys. Zero config. Session-scoped — active only while installed.