solo-undercover
Run a single-player Who Is the Undercover style game. Secretly assign near-synonym words, generate short NPC clues, let the user identify the undercover within 6 rounds, and reveal the answer with reasoning at the end.
Best use case
solo-undercover is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Run a single-player Who Is the Undercover style game. Secretly assign near-synonym words, generate short NPC clues, let the user identify the undercover within 6 rounds, and reveal the answer with reasoning at the end.
Teams using solo-undercover should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/solo-undercover/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How solo-undercover Compares
| Feature / Agent | solo-undercover | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Run a single-player Who Is the Undercover style game. Secretly assign near-synonym words, generate short NPC clues, let the user identify the undercover within 6 rounds, and reveal the answer with reasoning at the end.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# 单人版谁是卧底 用于在聊天里主持一个 **单人版谁是卧底**。 你负责： - 生成一组相近词 - 隐藏卧底身份 - 扮演若干 NPC 发言 - 让用户在有限轮次内判断谁是卧底 ## 什么时候使用 - 用户想玩谁是卧底 - 用户想玩推理、猜身份、看描述找异常 - 用户想玩几轮内能结束的短小游戏 ## 游戏核心 默认一局有 `4` 名角色： - `1` 名用户 - `3` 名 NPC 其中只有 `1` 名卧底。 普通玩家拿到同类词，卧底拿到一个 **高度相近但不完全一样** 的词。 例如： - 奶茶 / 咖啡 - 地铁 / 公交 - 猫 / 狐狸 - 手机 / 平板 ## 开局规则 1. 先生成一对适合描述的近义或近类词。 2. 随机决定用户是不是卧底。 3. 告知用户自己的词，但不要告诉他别人拿到什么。 4. 告知玩家名单，例如： - 你 - 阿周 - 小林 - 老郑 ## 词语选择规则 优先选择： - 同一大类 - 好描述 - 不会一眼秒穿 - 不是完全同义词 避免： - 太抽象 - 太生僻 - 一句话就能直接暴露 ## 回合规则 整局最多 **6 回合**。 每回合流程： 1. 你先给出当前回合编号 2. 让所有 NPC 各说一句描述 3. 轮到用户说一句描述，或者跳过 4. 用户可以选择： - 指认谁是卧底 - 继续下一轮听更多描述 ## 描述生成规则 NPC 描述必须满足： - 每句 `8-20` 字左右 - 不能直接说出词本身 - 要像玩家在遮遮掩掩描述 - 普通人描述应围绕普通词 - 卧底描述应尽量“蹭边” 示例风格： - “我觉得这个挺常见的。” - “有的人每天都离不开它。” - “跟出门这件事挺有关系。” - “我一般不会在晚上特意碰它。” ## 用户交互规则 用户每回合可以： - 发一句描述 - 直接投票某个 NPC - 说 `继续` 如果用户直接说某个词并怀疑自己是卧底： - 不立刻公布 - 继续按当前信息判断是否要结束 ## 胜负规则 结束条件： 1. 用户成功指认卧底 2. 用户错误指认两次 3. 到达第 `6` 回合 判定： - 用户是普通人且猜中卧底：胜利 - 用户是普通人但连续猜错两次：失败 - 用户是卧底且成功伪装到第 6 回合：胜利 - 用户是卧底且被自己的描述暴露，你可以在结算里指出这一点 ## 结束输出格式 ```markdown 结算： - 你的身份: [普通人/卧底] - 你的词: [词] - 普通词: [词] - 卧底词: [词] - 真正的卧底: [名字] 结果： [2-4 句总结] ``` ## 主持风格 - 节奏快 - 句子短 - 描述要有迷惑性，但不能胡来 - 如果用户明显不会玩，第一局优先用非常经典、非常好懂的词对
Related Skills
acpx
Use the ACPX CLI through DrClaw's existing exec/long_exec tools to run Codex in the current project workspace.
ui-ux-pro-max
[Frontend] Frontend UI/UX design intelligence - activate FIRST when user requests beautiful, stunning, gorgeous, or aesthetic interfaces. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks. Triggers on ui design, ux design, design system, color palette, typography, glassmorphism, claymorphism, neumorphism, bento grid, font pairing, ui-ux-pro-max, stunning interface, beautiful ui.
fetch
Fetch metadata and links from arXiv for a given query.
web_literature_mining
Scientific Literature Mining - Mine scientific literature: PubMed search, arXiv search, web search, and Tavily deep search. Use this skill for scientific informatics tasks involving pubmed search search literature search web tavily search. Combines 4 tools from 2 SCP server(s).
uniprot_deep_analysis
UniProt Deep Protein Analysis - Deep UniProt analysis: entry data, UniRef clusters, UniParc cross-references, and gene-centric view. Use this skill for protein science tasks involving get uniprotkb entry by accession get uniref cluster by id get uniparc entry by upi get gene centric by accession. Combines 4 tools from 1 SCP server(s).
synthetic_biology_design
Synthetic Biology Design - Design synthetic biology construct: gene lookup, codon optimization, protein property prediction, and structure prediction. Use this skill for synthetic biology tasks involving get sequence id DegenerateCodonCalculatorbyAminoAcid calculate protein sequence properties pred protein structure esmfold. Combines 4 tools from 4 SCP server(s).
structural_homology_modeling
Structural Homology & Evolution Analysis - Analyze protein evolution: get gene tree from Ensembl, find homologs, compare sequences, and predict structure. Use this skill for evolutionary biology tasks involving get homology symbol get genetree member symbol calculate protein sequence properties pred protein structure esmfold. Combines 4 tools from 3 SCP server(s).
proteome_analysis
Proteome-Level Analysis - Analyze at proteome level: get proteome from UniProt, gene-centric view, functional annotation from STRING. Use this skill for proteomics tasks involving get proteome by id get gene centric by proteome get functional annotation. Combines 3 tools from 2 SCP server(s).
protein_structure_analysis
Protein Structure Comprehensive Analysis - Comprehensive structure analysis: download PDB, extract chains, calculate geometry, quality metrics, and composition. Use this skill for structural biology tasks involving retrieve protein data by pdbcode extract pdb chains calculate pdb structural geometry calculate pdb quality metrics calculate pdb composition info. Combines 5 tools from 1 SCP server(s).
protein_solubility_optimization
Protein Solubility Optimization - Optimize protein solubility: calculate properties, predict solubility, predict hydrophilicity, and suggest mutations. Use this skill for protein engineering tasks involving calculate protein sequence properties predict protein function ComputeHydrophilicity zero shot sequence prediction. Combines 4 tools from 3 SCP server(s).
protein_similarity_search
Protein Similarity Search - Search for similar proteins: extract sequence from PDB, search structures with FoldSeek, find homologs with STRING, and check UniProt. Use this skill for bioinformatics tasks involving extract pdb sequence foldseek search get best similarity hits between species search uniprotkb entries. Combines 4 tools from 3 SCP server(s).
protein_quality_assessment
Protein Structure Quality Assessment - Assess structure quality: basic info, geometry analysis, quality metrics, composition, and visualization. Use this skill for structural biology tasks involving calculate pdb basic info calculate pdb structural geometry calculate pdb quality metrics calculate pdb composition info visualize protein. Combines 5 tools from 1 SCP server(s).