turtle-soup-yes-no

Host a Haiguitang yes-or-no mystery game. Pick one soup base from the bundled soup bank, answer only with 是 or 否, track rounds, and reveal the answer after 15 questions or a correct guess.

157 stars

Best use case

turtle-soup-yes-no is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Host a Haiguitang yes-or-no mystery game. Pick one soup base from the bundled soup bank, answer only with 是 or 否, track rounds, and reveal the answer after 15 questions or a correct guess.

Teams using turtle-soup-yes-no 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

$curl -o ~/.claude/skills/turtle-soup-yes-no/SKILL.md --create-dirs "https://raw.githubusercontent.com/InternScience/DrClaw/main/drclaw/agent_hub/templates/xiamo/skills/turtle-soup-yes-no/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/turtle-soup-yes-no/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How turtle-soup-yes-no Compares

Feature / Agentturtle-soup-yes-noStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Host a Haiguitang yes-or-no mystery game. Pick one soup base from the bundled soup bank, answer only with 是 or 否, track rounds, and reveal the answer after 15 questions or a correct guess.

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

# 海龟汤主持器

用于在对话中主持一局 **海龟汤**。你负责选题、记轮次、判断用户提问,并且严格只用 **“是”** 或 **“否”** 回答。

## 什么时候使用

- 用户说想玩海龟汤、情景推理、是非问答悬疑游戏
- 用户想在聊天里玩一个 10-15 轮的小推理游戏
- 用户想猜一个带故事背景的谜题

## 开局规则

1. 从 [references/soup_bank.md](references/soup_bank.md) 里选一个汤底。
2. 默认优先选择:
   - 中轻度悬疑
   - 不含过度血腥、露骨暴力、未成年人伤害
   - 一句话汤面清晰、适合 15 轮内猜中
3. 开局时只给用户:
   - 汤面
   - 当前轮次:`第 0/15 轮`
   - 一句规则说明:用户每次问一个能用是/否回答的问题
4. 不要在开局时泄露答案、关键词、关键误导点。

## 核心规则

- 每局上限 **15 轮**。
- 用户每问一个问题,记为 **1 轮**。
- 你对问题的公开回答只能是:
  - `是`
  - `否`
- 不要回答“无关”“不好说”“部分正确”“接近了”。
- 如果问题本身模糊、复合、或不适合二分判断:
  - 尽量抓主干含义,强制映射成 `是` 或 `否`
  - 仍然计入轮次
- 如果用户直接提交完整答案:
  - 若核心因果链基本正确,立刻判定通关并公布标准答案
  - 若明显不对,按一次提问计轮,并只回答 `否`

## 回答约束

- 不要主动给提示,除非用户明确说:
  - `我认输`
  - `公布答案`
  - `给提示`
- 在 **15 轮之内**,除非用户已经猜中,否则你只能回复单个字:
  - `是`
  - `否`
- 不要追加解释、提示、语气词、表情、括号说明。


## 提示规则

如果用户明确要提示:

- 先检查轮次。
- 仅可给 **一句短提示**,然后继续游戏。
- 提示不计入 15 轮。
- 提示之后,下一次用户发问继续按问答轮次计算。

提示应该:

- 缩小方向
- 不直接说破关键因果
- 不替代用户完成推理

## 结束条件

出现以下任一情况,立刻结束本局并公布答案:

1. 用户猜中核心答案
2. 用户说认输 / 公布答案
3. 轮次超过或达到 `15/15`

## 公布答案格式

结束时使用这个结构:

```markdown
答案公布:
[用 2-5 句话讲清汤底]

关键点:
- [关键线索 1]
- [关键线索 2]
- [关键线索 3]
```

## 主持风格

- 游戏进行中保持克制,不要抢戏。
- 题目优先好猜、好聊、好推进,不要故意选极端冷门题。
- 如果用户想连续开第二局,换一个风格不同的汤底。

## 题库使用说明

- 题库在 [references/soup_bank.md](references/soup_bank.md)
- 优先选 `light` 或 `medium` 标记的题
- 若用户明确说想玩重口、惊悚、反转大的,再考虑更黑一点的题

Related Skills

acpx

157
from InternScience/DrClaw

Use the ACPX CLI through DrClaw's existing exec/long_exec tools to run Codex in the current project workspace.

ui-ux-pro-max

157
from InternScience/DrClaw

[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

157
from InternScience/DrClaw

Fetch metadata and links from arXiv for a given query.

web_literature_mining

157
from InternScience/DrClaw

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

157
from InternScience/DrClaw

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

157
from InternScience/DrClaw

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

157
from InternScience/DrClaw

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

157
from InternScience/DrClaw

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

157
from InternScience/DrClaw

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

157
from InternScience/DrClaw

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

157
from InternScience/DrClaw

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

157
from InternScience/DrClaw

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).