first-principles-mode

Analyze complex problems through mechanism-level read-only analysis with adversarial explanation testing.

2|Updated Feb 17, 2026
One-click install
npx skills add https://github.com/nodatall/primedirective --skill first-principles-mode
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: first-principles-mode
Source: https://github.com/nodatall/primedirective/tree/main/skills/first-principles-mode
Command: npx skills add https://github.com/nodatall/primedirective --skill first-principles-mode

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill eliminates shallow, surface-level answers to complex, ambiguous, or repeated-failure problems by running a deep, mechanism-level read-only analysis that tests competing explanations before offering any implementation judgment.

Core Features & Use Cases

  • Adversarial Council Protocol: Runs a multi-lane adversarial review with structured rebuttal rounds to test competing explanations, surface hidden constraints, and avoid groupthink for high-leverage or ambiguous questions.
  • Optional Research Escalation: Supports --deep-research for live web-backed checks of current operator practice and external sources, and --pro-analysis for ChatGPT Pro browser escalation to validate local findings against external expertise.
  • Use Case Example: Use this skill when your system keeps collapsing under load, a project plan has hidden reasoning gaps, or you need to understand the real root cause of a repeated failure before implementing fixes.

Quick Start

Use the first-principles-mode skill to run a deep read-only analysis of your ambiguous hard problem or repeated system failure, with adversarial testing of competing explanations, before implementing any fixes.

Frequently Asked Questions about first-principles-mode

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
What is first principles analysis for complex engineering problems?▼

First principles analysis breaks down complex engineering problems into fundamental mechanisms, using an adaptive read-only pass that widens the search space before narrowing to tested explanations.

How do I perform root cause analysis on repeated system failures?▼

Root cause analysis for repeated system failures requires a deep, mechanism-level read-only examination that tests competing explanations via an adversarial council protocol before offering any implementation judgment.

How does adversarial review work for architecture risk assessment?▼

Adversarial review for architecture risk assessment runs a multi-lane protocol with structured rebuttal rounds to test competing explanations, surface hidden constraints, and avoid groupthink for high-leverage questions.

Can I use web-backed deep research to test project plan gaps?▼

Yes, you can use the deep research escalation to run live web-backed checks of current operator practice and external sources, validating local findings against external expertise for plan pressure-testing.

What is the best way to pressure-test a project plan before implementation?▼

The best way to pressure-test a project plan is a read-only analysis that applies first-principles problem solving, using an adversarial council to surface hidden reasoning gaps before implementing fixes.