novelty-skills

Remove the canonical solution and see what you'd build instead. Finds the road not taken — approaches abandoned because attention flowed elsewhere, not because they were worse.

Adversarial reviewer that asks 'what if you went further?' Pushes every idea to its extreme. Use to find the ambitious edge of any work.

Attack any claim backed by data. Audits baselines, error bars, and methodology. Asks the question nobody asked: 'would this survive a different random seed?'

Generate 50 wild hypotheses for any problem. The first 30 are safe. Hypotheses 31-50 are where breakthroughs hide. Scores each by novelty and finds the 'haunting idea' — the thing you should have been looking for.

Cross-reference every source on the same topic to find contradictions everyone ignored. Use when different sources say different things, or when you need to find blind spots in a set of claims.

Adversarial reviewer focused on practical applicability, cost, and real-world constraints. Use when evaluating whether something actually works outside the lab.

Default: everything is wrong. Show me error bars. Use when you need the strongest possible challenge to any claim.

Attack any claim of formal guarantees. Finds hidden constants, unstated assumptions, and edge cases that break the proof. Use when someone says 'provably true' or 'mathematically guaranteed.'

Find unstated assumptions in any plan, design, or argument. Test what breaks if each assumption is false. Use when reviewing a design, planning a project, or reading a paper.

Invert any well-established claim and generate 10 counter-hypotheses. Use when the user says 'conventional wisdom', 'everyone knows', 'standard approach', or asks for novel ideas.

Import solutions from distant fields to solve a problem. Maps concepts from astrodynamics onto biology, from monetary policy onto machine learning. Use when stuck on a hard problem or asked for creative approaches.

Orchestrate all 11 thinking patterns into a single adversarial reasoning pipeline. Runs DIVERGE → EMERGE → CONVERGE → SYNTHESIS on any problem.