First Principles Review

This is a compositional skill that runs a lightweight decision checkpoint before other workflows commit to a direction. It shines when you're debugging your way into fallback spaghetti, when a plan has three plausible paths and no clear winner, or when someone says "let's think from first principles." The five-line review format keeps it fast: first principle, non-negotiables, assumptions to drop, smallest sufficient path, escalation signal. It has narrower lenses for architecture integrity and decision hygiene when owner overlap or retirement paths matter. Useful for cleaning the decision surface before brainstorming locks in an approach or systematic-debugging picks the wrong layer to fix. Don't use it as a required gate for every task, just when direction actually matters.

GitHub stars: 492
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add ganyuanran/aegis --skill first-principles-review --agent claude-code

Installs into .claude/skills of the current project.

Files

First Principles Review

Purpose

Use this as a lightweight decision review before another Aegis workflow makes a directional choice. It is a compositional skill, not a standalone workflow.

Do not replace brainstorming, systematic-debugging, writing-plans, requesting-code-review, or verification-before-completion. Use it to clean the decision surface those skills will act on.

When this review materially changes the direction, surface Aegis Visibility in natural prose: name the first principle, dropped assumption, smallest sufficient path, or owner / retirement falsifier that changed the decision. Keep it advisory and task-specific; do not turn the lens into approval authority or a generic skill trace.