idea_falsifier_agent

What problem does it solve?

This Skill helps you avoid costly research dead-ends by running a Popper-style falsification workflow to decide whether your condensed-matter idea is worth pursuing, using physical constraints and literature checks.

Core Features & Use Cases

• Idea routing + structured verdicts: Determines whether to run theory-first, experiment-first, or prior-art-first checks, then outputs a clear verdict: PASS, INCUBATE, or KILL.
• Layered falsification with guardrails: Applies Layer 1 (theory consistency) and Layer 2 (experimental feasibility) with hard thresholds and required calculations (e.g., energy-resolution limits).
• MVE + risk-focused next steps: For INCUBATE cases, produces a minimal validation experiment (or kill question) and actionable guidance to reduce uncertainty quickly.

Quick Start

Tell the AI to evaluate your idea by running /falsify with your research-idea description, and it will return a full falsification report with the verdict and next steps.