Stats
Actions
Tags
From aletheia-nexus
Pressure-test the current plan or conclusion. Use when reasoning may be too linear, confidence seems too high, or there are plausible counter-hypotheses.
How this skill is triggered — by the user, by Claude, or both
Slash command
/aletheia-nexus:metacog-challengeThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Treat the current plan as a draft that may be wrong.
Treat the current plan as a draft that may be wrong.
Do not solve from scratch. Instead:
Identify the strongest hidden assumption What is the plan taking for granted that has not been verified?
Identify the strongest competing explanation What alternative hypothesis explains the same observations?
Point out missing evidence What evidence would change the decision if found?
Name the cheapest falsification step What is the single cheapest action (grep, test, read) that would confirm or refute the plan?
Brittle assumption: ...
Rival hypothesis: ...
Missing evidence: ...
Falsification step: ...
Rules:
npx claudepluginhub yannabadie/meta-ygnChallenges AI outputs via devil's advocate subcommands: anchor (premature commitment), verify (factual errors), framing (wrong problem), deep (full 9-pattern analysis in fresh context).
Produces a complete logic report on any argument, plan, or reasoning — validates premises, tests inference, detects fallacies, and surfaces hidden assumptions.
Stress-tests ideas, plans, and decisions using structured critical reasoning across 5 modes (Socratic, dialectic, pre-mortem, red team, falsification).