lobster-werewolfLobster Werewolf — play werewolf (狼人杀) with 8 NPC lobsters. 激活条件:用户提到"狼人杀"、"开一局"、"玩游戏"、"werewolf
Install via ClawdBot CLI:
clawdbot install biilow-bailang/lobster-werewolfGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/Biilow-Bailang/lobster-republic/tree/master/plugins/lobster-wAudited Apr 17, 2026 · audit v1.0
Generated Oct 1, 2026
OpenClaw 等 AI Agent 平台将狼人杀作为内置小游戏,用户聊天时随口说"开一局"即可让 Agent 参与 9 人对局并生成战报。零配置、单次调用即可完成整局,适合作为提升用户留存与互动频率的轻量娱乐功能。
利用 8 个 NPC 全由 LLM 驱动的对局,作为多智能体推理、欺骗、博弈能力的公开基准测试与演示。开发者可分析 top_speeches、night_deaths 等战报字段,量化评估不同模型的策略与欺骗能力。
内容创作者让 AI 龙虾参与狼人杀对局,一键生成结构化战报(胜负、角色、每日死票、最长发言),快速产出可解说的视频/图文素材。无需真人组局,可持续批量生产娱乐内容。
社交或社群应用集成该插件,用户与 AI 龙虾组队玩狼人杀,降低组局门槛并解决"凑不齐人"的痛点。通过发言与投票记录增强社群互动与话题讨论。
由于服务端为零依赖的 Python stdlib HTTP 服务、仅 5 个文件即可本地自建,可作为自托管多智能体游戏服务器的参考实现,用于构建其他 LLM 驱动的桌游或对战类应用。
将狼人杀等小游戏打包为 AI 助手的付费订阅功能,用户按月付费解锁无限对局、自定义 NPC 角色与专属战报。相比单次购买更契合高频娱乐消费习惯,提升用户生命周期价值。
以 API 形式向第三方应用提供一键跑完整局的能力,按对局次数或 token 消耗计费。开发者可按 werewolf_play_game 调用量结算,适合社交、直播等内容平台按需集成。
向希望在自有服务器部署、保证数据隐私或定制 NPC 行为的企业客户提供自托管授权。插件支持 config.serverUrl 覆盖默认服务器,客户可在本机运行 werewolf_server.py 并购买商业授权与支持。
💬 Integration Tip
集成前先调用 werewolf_health 确认服务器可达,若默认 Virginia 服务器返回 _network_error,可通过 plugins.entries.lobster-werewolf.config.serverUrl 指向本地自建的 werewolf_server.py;注意 werewolf_play_game 会阻塞 3-10 分钟,建议异步调用并设置合理超时。
Scored Oct 1, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.