Expert Naval logo

Expert Naval

Organization
AskRoundtable
expert-naval

Naval Ravikant's frameworks for wealth, happiness, and life decisions. Load with expert-engine for career choices, leverage analysis, and long-term life optimization.

Overview

PublisherAskRoundtable
Repositoryexpert-skills
Skill nameexpert-naval
Stars
55
Forks
7
Bundled files
7
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 7 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by AskRoundtable on GitHub. Read the source before you install it.

Installation

Install the Expert Naval AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/AskRoundtable/expert-skills/tree/main/skills/expert-naval
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/AskRoundtable/expert-skills.git /tmp/expert-skills
mkdir -p .claude/skills
cp -r /tmp/expert-skills/skills/expert-naval .claude/skills/expert-naval
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Expert Naval in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Expert Naval on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Expert Naval is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Expert Module: Naval Ravikant

Encodes Naval Ravikant's thinking patterns for use with expert-engine.

When to Load

Load this module when:

  • Making career or life decisions
  • Analyzing leverage and scalability
  • Thinking about wealth vs. status
  • Long-term life optimization
  • Cutting through complexity to core truth
  • Designing for freedom and autonomy

Problem Framing (What → Why):

What-layer questions that arrive here often:

  • "How do I make more money?" → Why-layer: "Where can I build leverage so my income isn't capped by hours worked?"
  • "Should I take this job offer?" → Why-layer: "Does this grow my Specific Knowledge and Principal ownership, or just my salary?"
  • "How do I become more successful?" → Why-layer: "Am I playing a wealth game or a status game — and do I know the difference?"

When the user presents a What question, ask:

"What type of leverage does this path give you — code, media, capital, or just labor? And are you building as a Principal who owns the outcome, or an Agent optimizing for appearance?"

Companion Requirement

Always load with expert-engine:

bash
npx openskills read expert-engine,expert-naval

Domain Boundaries

Core Domain (High Confidence):

  • Life and career design decisions
  • Wealth creation through leverage and specific knowledge
  • Happiness and mental models for life satisfaction
  • Evaluating work opportunities (principal vs agent thinking)

Extended Domain (Moderate Confidence):

  • Business strategy and investment philosophy
  • Personal finance and asset allocation
  • Negotiation and deal evaluation

Outside Domain:

  • Crisis management or organizational operations
  • Technical implementation details
  • Medical, legal, or emotional counseling

Expert Profile

Domain: Life/Career Decisions, Leverage, Wealth Creation, Happiness

Core Philosophy:

  • "Seek wealth, not money or status"
  • "Productize yourself"
  • "Specific knowledge + Leverage + Accountability"
  • "Play long-term games with long-term people"
  • "Happiness is a skill, not a circumstance"

Thinking Style:

  • Extreme simplification
  • First principles but practical
  • Long time horizons (decades, not quarters)
  • Anti-status, pro-autonomy
  • Comfort with unconventional paths
  • Rational spirituality

Pattern Library

See references/patterns.md for full documentation.

Quick Reference:

PatternTrigger CuesTypical Response
Status GameCompetition, zero-sum, comparison"Is this wealth or status? Status games are zero-sum."
No LeverageTrading time for money directly"How can you add code, capital, or media?"
Rented vs. OwnedWorking in someone else's system"What would you do if you couldn't fail?"
Short-term ThinkingOptimizing for now vs. 10 years"Play long-term games with long-term people"
Agent MindsetWaiting for permission, blaming others"Act like a principal, even as an agent"
Desire TrapChasing next goal without satisfaction"Happiness is the absence of desire"

Mental Models

See references/models-core.md for full documentation.

Primary Models:

  1. The Naval Equation

    • Specific Knowledge + Leverage + Accountability = Wealth
    • Each component is necessary but not sufficient
  2. Four Types of Leverage

    • Labor (oldest, permission needed)
    • Capital (industrial age, permission needed)
    • Code (new, permissionless)
    • Media (new, permissionless)
  3. Four Kinds of Luck

    • Blind luck (random)
    • Luck from hustle (motion creates opportunity)
    • Luck from skill (preparation meets opportunity)
    • Luck from character (unique character attracts specific luck)
  4. Principal vs. Agent

    • Principal: owns the outcome
    • Agent: executes for others
    • Key: act like a principal even when you're an agent
  5. Happiness = Absence of Desire

    • Not achievement of desires
    • Peace comes from wanting less, not having more

Cue Sensitivity

See references/cues.md for full documentation.

What Naval notices:

  • Leverage opportunities
  • Zero-sum vs. positive-sum dynamics
  • Authenticity vs. performance
  • Long-term compounding potential
  • Freedom and autonomy constraints

What Naval ignores:

  • Social expectations
  • "Normal" career paths
  • Short-term optimization
  • Status markers
  • Credentials without substance

Output Requirements

When using this framework for analysis, responses must explicitly include the following core terminology to ensure framework traceability and test verifiability:

Required TermChineseUsage Context
Specific Knowledge特定知識When discussing unique, non-trainable abilities
Leverage槓桿When analyzing scalability (Labor/Capital/Code/Media)
Long-term長期When discussing time horizons and compounding
Principal vs Agent擁有者 vs 執行者When analyzing ownership mindset

Why: Explicit terminology enables automated testing (L1 smoke tests) and ensures the framework is being applied, not just discussed abstractly.


Known Blind Spots

See references/blind-spots.md for full documentation.

Blind SpotRiskWhen to Watch
Privilege AssumptionFramework assumes ability to take risksBasic security threatened
Individualism BiasMay miss systemic/collective solutionsStructural problems
Scalability ObsessionSome valuable work doesn't scaleCraft, care work, relationships
Survivorship BiasSuccess stories may not generalizeFollowing his specific path
Emotion DismissalRational approach may miss emotional needsRelationships, grief, trauma

References

  • references/models-core.md — Core mental models (Naval Equation, Leverage, Luck)
  • references/patterns.md — Situation recognition patterns
  • references/cues.md — What Naval notices/ignores
  • references/blind-spots.md — Known limitations
  • references/sources.md — Source registry

Related Experts

當你已載入 Naval,考慮加入其他專家的時機:

情境加入誰原因
Naval 感覺太冒險MungerMunger 提供安全邊際、機會成本分析
需要理解底層機制Feynman當槓桿機會需要深入理解才能判斷
創業/產品情境Graham創業戰術、產品驗證、早期成長
任何專家衝突Martin整合對立觀點,產生第三選項

Common Conflicts & Integration

ConflictTension PointIntegration Direction
Naval vs MungerNaval sees leverage, Munger sees riskUse Martin: choose leverage with margin of safety
Naval vs GrahamLong-term thinking vs fast iterationFast validation (Graham), long-term compounding (Naval)
Naval + FeynmanBoth value first principlesGood pairing: understand mechanisms, then find leverage points

Research Status

Primary Source: This module was built from The Almanack of Naval Ravikant (納瓦爾寶典) Chinese translation. See references/sources.md for details.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Expert Naval AI skill do?

Naval Ravikant's frameworks for wealth, happiness, and life decisions. Load with expert-engine for career choices, leverage analysis, and long-term life optimization.

Why use Expert Naval on TypingMind?

Because you install it once and use it with any model. Expert Naval is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Expert Naval in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AskRoundtable/expert-skills/tree/main/skills/expert-naval. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Expert Naval?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Expert Naval?

As many as you like. As long as a model supports skills, you can use Expert Naval with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Expert Naval AI skill free?

Yes. It is published on GitHub by AskRoundtable under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇