
FirstPrinciples
This is Elon Musk's physics-based reasoning framework turned into a systematic workflow. It forces you to break problems into constituent parts, classify every constraint as hard physics or soft assumption, then rebuild solutions from scratch instead of copying what others do. The three workflows (Deconstruct, Challenge, Reconstruct) are especially useful when you're stuck inheriting questionable architecture decisions or when pentesters need to identify actual attack surfaces versus assumed security boundaries. The constraint classification table alone is worth it. Fair warning: this will make you question every "that's just how we do it" in your codebase, which is either exactly what you need or going to drive your team crazy.
- skills.sh installs
- 190
- GitHub stars
- 14.6K
- last updated
- Jun 3, 2026
Install
$ npx -y skills add danielmiessler/personal_ai_infrastructure --skill FirstPrinciples --agent claude-codeInstalls into .claude/skills of the current project.
Files
FirstPrinciples
Contents: Ideal State · Intent Routing · Constraint Classification · The Core Distinction · The Load-Bearing Rules · Output Format · Data & Config · Gotchas · Examples
Breaks a problem down to its fundamental truths and rebuilds the solution from there, instead of copying what already exists. Three steps, each an intent: DECONSTRUCT (break it into constituent parts and real values), CHALLENGE (classify every element as hard constraint, soft constraint, or unvalidated assumption; only physics is truly immutable), and RECONSTRUCT (build the optimal solution from the fundamentals alone). Outputs a parts breakdown, a constraint table, and a reconstructed solution. It is analysis, not implementation: a request to fix something is done directly, not through this skill. Other skills call it when inherited assumptions may be limiting the solution space: architecture work asking "constraint or convention?", RedTeam and pentests attacking assumed boundaries, RedTeam building counter-proposals with Reconstruct, and engineering escaping a local maximum.
Ideal State
Sponsors
Details
- Repository
- github.com/danielmiessler/personal_ai_infrastructure
- Categories
- AI & Agent Building, Cloud & Infrastructure
- First seen
- Jun 3, 2026