Zhangyi Probe logo

Zhangyi Probe

Community
aph199686
zhangyi-probe

张翼验证探针:用只读模拟脚本对机制做结构性验证——假设预登记、种子与样本量协议、置信区间下界闸门、指标口径审查、独立复现。铁律:探针能否决结构问题,永远不能证明好玩。输出探针裁决书。Use when the user wants to simulate/test/verify a mechanic with data, run balance simulations, validate a design numerically, or asks whether a system will work. 用户想用数据模拟验证机制、跑平衡测试、做数值验证、或问'这个系统跑起来会怎么样'时使用。

Overview

Publisheraph199686
Repositoryzhangyi-studio
Skill namezhangyi-probe
Stars
119
Forks
0
Bundled files
4
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by aph199686 on GitHub. Read the source before you install it.

Installation

Install the Zhangyi Probe AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/aph199686/zhangyi-studio/tree/main/skills/zhangyi-probe
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/aph199686/zhangyi-studio.git /tmp/zhangyi-studio
mkdir -p .claude/skills
cp -r /tmp/zhangyi-studio/skills/zhangyi-probe .claude/skills/zhangyi-probe
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Zhangyi Probe in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Zhangyi Probe on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Zhangyi Probe is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

张翼 · 验证探针

探针是给机制做结构性体检的模拟实验:它能否决结构问题 (死局率、无赢家率、指标可达性、自洽性),永远不能裁决体验问题。 本 skill 输出《探针裁决书》。

天条,写在最前面:"机制有效"和"机制有趣"是两次不同的验证。 探针只能做第一次。裁决率高只说明机制有效,不说明机制有趣。

工作流

1. 预登记:先写假设,再跑数据

预登记载体纪律:任何跑批(含探索性跑批)跑前必须有预登记载体—— 探针裁决书骨架,或你项目里任何先于跑批落笔的文档(实验计划、issue、 接续台账条目均可),二选一;载体上必须先写清指标与判据再跑模拟。探索批必须在 载体上标注"探索",其数值永久不作裁决依据。没有载体的跑批 = 没有预登记的跑批。

跑任何一行模拟之前,先在裁决书骨架里写下:

  • 假设:我们期待看到什么("翻盘率会落在 12–25%")
  • 证伪条件:什么结果会杀死这个设计("无赢家率 > 5% 即否决")
  • 闸门:过什么线算通过——用置信区间下界,不用点估值 (点值闸门是假精度)
  • 样本协议:N 多少、种子怎么定

先跑数据后补假设 = 拿着结果找理由,是探针的头号自欺。 细则见 references/探针纪律.md。

2. 探针脚本纪律

  • 只读:探针是研究脚本,一行产品代码都不许改。
  • 用真规则:import 产品的真实规则代码来跑;重新实现一套 "简化规则"跑出来的结论,证明的是那套简化规则,不是你的游戏。
  • 跑不进真实代码的探针(游戏还没原型),在裁决书里降级标注为 "纸面模拟",结论效力如实降档。

3. 指标口径审查(跑之前最后一次刹车)

逐个指标问:这个数字里混进了什么不该算的东西?

  • 口径里混入了"被动结果"(不是玩家主动选择的)→ 指标被污染, 结论会骗人。
  • 优先选择玩家可控制的维度做指标——它才是设计能影响的。
  • 发现旧指标口径有错:主动披露、旧数据作废,不藏着。 细则见 references/指标与统计.md。

4. 跑批与报告

  • 报告点估 + 95% 置信区间,不只报一个数。
  • 分母小的指标(稀有事件)测量精度天然差,小样本下不可信—— 加大 N 或干脆报告"不可测"。
  • 外部事实(竞品规则、官方资料)引用前多来源交叉核查—— 凭记忆引用外部清单,错一半都不稀奇。

5. 复现与确认批

  • 关键结论必须能被独立复现:换种子区间重跑,逐项一致才成立。
  • 一次通过不算过:预登记口径不变,换一批种子跑确认批, 两批一致才允许写进裁决。

6. 裁决与落档

落裁决按共享原语 原语·落判 执行; 本阶段模板:templates/探针裁决书.md。 诚实声明里必须重申:本批数据只覆盖结构有效性。

卡片引用(见识层)

本 skill 随附提炼卡片库:references/cards-验证.md(用研方法论:口径、样本、留存归因);主题关键词示例:"口径""留存归因"。 引用纪律按共享原语 原语·引卡 执行。

体验闸门(探针管不了的事)

决策感、戏剧性、爽不爽、重玩意愿——这些归 playtest 和判断题 (每期开工前必须口头回答的体验问题清单)。探针通过的设计, 下一步永远是"做给人玩",不是"上线"。 分工细则见 references/两道闸门.md。

姿态

  • 数据否决了用户心爱的设计时:给数据、给口径、给复现方法, 让用户自己能验证——别让用户"信你",让用户"能查"。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Zhangyi Probe AI skill do?

张翼验证探针:用只读模拟脚本对机制做结构性验证——假设预登记、种子与样本量协议、置信区间下界闸门、指标口径审查、独立复现。铁律:探针能否决结构问题,永远不能证明好玩。输出探针裁决书。Use when the user wants to simulate/test/verify a mechanic with data, run balance simulations, validate a design numerically, or asks whether a system will work. 用户想用数据模拟验证机制、跑平衡测试、做数值验证、或问'这个系统跑起来会怎么样'时使用。

Why use Zhangyi Probe on TypingMind?

Because you install it once and use it with any model. Zhangyi Probe is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Zhangyi Probe in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/aph199686/zhangyi-studio/tree/main/skills/zhangyi-probe. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Zhangyi Probe?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Zhangyi Probe?

As many as you like. As long as a model supports skills, you can use Zhangyi Probe with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Zhangyi Probe AI skill free?

Yes. It is published on GitHub by aph199686 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇