메뉴
Good vs. bad behavioral examples showing what excellent play looks like vs. common mistakes. Derived from xuyuzhuang-Werewolf contrastive prompting and Avalon-LLM self-play reflection.
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
Good vs. bad behavioral examples showing what excellent play looks like vs. common mistakes. Derived from xuyuzhuang-Werewolf contrastive prompting and Avalon-LLM self-play reflection.
Faction-conditional strategies for deception and detection, derived from xuyuzhuang-Werewolf and LLMWereWolf role strategies. Evil agents get deflection and alibi techniques; good agents get detection heuristics.
3-tier memory tracking (STM/Episodic/Semantic) derived from ai-traitors-v2 and ai-town generative agent reflection. Helps agents maintain beliefs about each player and synthesize round memories into strategic conclusions.
Enriches GameMaster narration with awareness of social dynamics, derived from Sotopia 7-dimensional social intelligence evaluation. Tracks influence shifts, trust erosion, and narrative tension cues.
Internal 5-step reasoning pipeline derived from xuyuzhuang-Werewolf. Agent performs Situation-Suspicion-Reflection-Strategy-Response analysis implicitly before generating any output.
Faction-conditional strategies for deception and detection, derived from xuyuzhuang-Werewolf and LLMWereWolf role strategies. Evil agents get deflection and alibi techniques; good agents get detection heuristics.
| id | contrastive_examples |
| name | Contrastive Behavioral Examples |
| description | Good vs. bad behavioral examples showing what excellent play looks like vs. common mistakes. Derived from xuyuzhuang-Werewolf contrastive prompting and Avalon-LLM self-play reflection. |
| tags | ["reasoning","quality","examples"] |
| targets | ["character_agent","vote_prompt"] |
| priority | 15 |
| dependencies | [] |
| conflicts | [] |
| behavioral_rules | ["Reference specific past statements and voting patterns when making accusations","Avoid generic, evidence-free suspicion — always tie claims to observable behavior"] |
