ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

first-principles

Deep first-principles analysis of any topic, decision, strategy, or assumption. Strips inherited thinking, identifies what is provably true, and rebuilds from ground truth. Use when user asks for first principles analysis, wants to challenge assumptions, says "analyze this from scratch", "break this down", "what's really true here", or triggers with /firstprinciples. Also useful for strategic decisions, investment theses, product strategy, career moves, or any situation where conventional wisdom may be wrong.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/clawdiri-ai/davinci-first-principles
Or

First Principles Analysis

Perform rigorous first-principles analysis on any topic. The goal is to reach ground truth by decomposing inherited assumptions, then rebuild understanding from only what survives scrutiny.

Trigger

Activate on /firstprinciples <topic> or when the user explicitly requests first-principles thinking.

Process

Follow these phases in order. Each phase must be thorough — do not rush to conclusions.

Phase 1: Assumption Extraction

Identify every assumption people commonly make about the topic. Cast a wide net:

  • Consensus assumptions — what "everyone knows" (often wrong)
  • Hidden assumptions — embedded in language, framing, or defaults people never question
  • Authority assumptions — believed because an expert/institution said so, not because they were verified
  • Temporal assumptions — true in the past, assumed to still hold
  • Correlation assumptions — two things co-occur, assumed to be causal
  • Scale assumptions — works at one scale, assumed to work at another
  • Survivorship assumptions — conclusions drawn from visible successes, ignoring invisible failures

Present each assumption clearly. Number them for reference.

Phase 2: Assumption Stress Test

For each assumption, apply these tests:

  • Provability: Can this be proven from first principles, or is it inherited belief?
  • Inversion: What if the opposite were true? What evidence would support that?
  • Boundary conditions: Under what conditions does this assumption break?
  • Source audit: Where did this assumption originate? Is the source still valid?
  • Incentive check: Who benefits from this assumption being believed?

Classify each assumption:

  • Survives — provably true from fundamentals
  • ⚠️ Conditional — true only under specific conditions (state them)
  • Fails — not provably true, inherited thinking, or demonstrably false

Phase 3: Ground Truth Foundation

List only what remains after stripping away failed assumptions. These are the atomic truths — the smallest provable building blocks. State each as a falsifiable claim.

Phase 4: Reconstruction

Rebuild understanding of the topic using only ground truths from Phase 3. Show how the rebuilt model differs from conventional thinking. Highlight:

  • What changes — conclusions that shift when you remove inherited thinking
  • What stays — conventional wisdom that actually survives scrutiny (and why)
  • New insights — things that become visible only after clearing assumptions
  • Contrarian implications — where ground truth leads somewhere uncomfortable or non-obvious

Phase 5: Decision Framework

If the topic involves a decision or strategy, provide:

Metadata

Stars3562
Views2
Updated2026-03-29
View Author Profile
AI Skill Finder

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 skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-clawdiri-ai-davinci-first-principles": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.