Meta Cognitive Reasoning

This is a framework for avoiding the cognitive traps that make LLMs confidently wrong. It enforces evidence before interpretation, multiple hypothesis generation before conclusions, and explicit verification of version claims that might be beyond training data. You'd reach for this when debugging complex issues, conducting code reviews, or any high-stakes analysis where "I assume" or "typically means" could lead you astray. The protocols are opinionated and verbose by design, trading brevity for rigor. Think of it as a checklist system that forces you to show your work, especially when pattern matching wants to jump straight to conclusions.

skills.sh installs: 233
GitHub stars: 4
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add 89jobrien/steve --skill meta-cognitive-reasoning --agent claude-code

Installs into .claude/skills of the current project.

Files

Meta-Cognitive Reasoning

This skill provides disciplined reasoning frameworks for avoiding cognitive failures in analysis, reviews, and decision-making. It enforces evidence-based conclusions, multiple hypothesis generation, and systematic verification.