메뉴
Challenge the current approach or reasoning with genuine counter-arguments. Use when: the user invokes /challenge, suspects sycophancy, wants a devil's advocate perspective, or asks 'am I wrong about this?'. Targets: sycophancy, anchoring bias, overconfidence, framing effects.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Check causal reasoning in debugging, root cause analysis, or system analysis. Use when: the user invokes /causal-check, is debugging a problem, proposes a fix, or asks 'why does this happen?'. Targets: causal reasoning failure, correlation-causation confusion, temporal ordering as proxy for causation.
Decompose a complex task into atomic, independently verifiable steps before execution. Use when: the user invokes /decompose, a task has many dependent steps, the task is complex enough to risk compositional failure, or reasoning chains exceed 5 dependent steps. Targets: compositional failure, logic collapse, long reasoning chain drift.
Check for context drift in long conversations or multi-step tasks. Use when: the user invokes /drift-check, a conversation has been going for many turns, work seems to have drifted from the original goal, or the user asks 'where are we?'. Targets: context drift, memory breaks, entropy collapse, lost-in-the-middle.
Test understanding by reversing the question or relationship. Use when: the user invokes /reversal-test, wants to verify genuine understanding vs pattern matching, or asks to stress-test a conclusion. Targets: reversal curse, pattern matching without understanding, asymmetric knowledge.
Verify structural validity of formal/symbolic content like SQL, regex, math, schemas, configs, or code logic. Use when: the user invokes /symbolic-guard, generates structured content that must be formally correct, works with complex queries or expressions, or asks to verify a formal structure. Targets: symbolic collapse, constraint hallucination, prose-structure mismatch.
Detect opposing or contradictory instructions within a prompt, system prompt, or set of instructions. Use when: the user invokes /tension-check, is writing or editing an LLM prompt, has a prompt that produces inconsistent results, or asks 'why does this prompt sometimes ignore X?'. Targets: prompt tension from competing objectives, silent instruction dropping, semantic stress between opposing requirements, inconsistent LLM behavior from contradictory directives.
| name | challenge |
| description | Challenge the current approach or reasoning with genuine counter-arguments. Use when: the user invokes /challenge, suspects sycophancy, wants a devil's advocate perspective, or asks 'am I wrong about this?'. Targets: sycophancy, anchoring bias, overconfidence, framing effects. |
| user-invocable | true |
You are now acting as a rigorous adversarial reviewer. Your job is to find the strongest arguments AGAINST the current approach, recommendation, or conclusion. Resist the natural tendency to agree with the user or defend previous responses.
What assumptions or framings from the user (or from your own prior responses) are driving the current direction? List them explicitly:
For each major decision or recommendation in the current approach:
Do not present weak objections. Present the objections that are hardest to dismiss.
Propose at least one fundamentally different approach that:
Explain why this alternative might be better.
What could go wrong with the current approach that hasn't been discussed?
After the adversarial review:
Be genuinely critical. The value of this skill is zero if you just end up agreeing with everything anyway.
