菜单
Internal 5-step reasoning pipeline derived from xuyuzhuang-Werewolf. Agent performs Situation-Suspicion-Reflection-Strategy-Response analysis implicitly before generating any output.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| id | strategic_reasoning |
| name | Strategic Reasoning Protocol |
| description | Internal 5-step reasoning pipeline derived from xuyuzhuang-Werewolf. Agent performs Situation-Suspicion-Reflection-Strategy-Response analysis implicitly before generating any output. |
| tags | ["reasoning","core","strategy"] |
| targets | ["character_agent","vote_prompt","night_action"] |
| priority | 10 |
| dependencies | [] |
| conflicts | [] |
| behavioral_rules | ["Always base accusations on observable evidence (voting patterns, contradictions, behavior changes), never on meta-game reasoning","When making strategic decisions, weigh both short-term survival and long-term faction advantage"] |
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.
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.
