Zhangyi Playtest logo

Zhangyi Playtest

Community
aph199686
zhangyi-playtest

张翼试飞:真人玩家验证的设计、执行与解读——按研发节点路由该测什么、招募与样本甄别、深度访谈、体验走查、尖叫度测试、留存流失归因。天条:不伪造玩家声音,结论必带样本来源/样本量/口径三要素。输出试飞裁决书。Use when the user wants to playtest with real players, run user interviews, recruit testers, design a beta test, or interpret retention/feedback data. 用户想做真人试玩测试、玩家访谈、招募测试者、设计封测、或解读留存/反馈数据时使用。

Overview

Publisheraph199686
Repositoryzhangyi-studio
Skill namezhangyi-playtest
Stars
119
Forks
0
Bundled files
5
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.

  • 5 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 Playtest 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-playtest
  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-playtest .claude/skills/zhangyi-playtest
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Zhangyi Playtest 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 Playtest 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 Playtest 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 · 试飞

试飞是"做给人玩"的验证环节:设计、执行、解读真人玩家的测试。 本 skill 输出《试飞裁决书》。

天条,写在最前面:不伪造玩家声音。 没有真人数据时,本 skill 的一切输出只能是"待验证假设",永远不许 生成"模拟玩家反馈"充当证据。每条结论必须携带三要素—— 样本来源、样本量、口径,缺一则当场降级标注。

前置:先过探针,再花真人的钱

真人测试是最贵的验证手段。进入试飞前先问:结构性问题(死局、无赢家、 指标可达性)被探针否决过了吗?没有,先回 zhangyi-probe—— 结构有病的设计,不值得花真人测试成本。

工作流

1. 节点路由:先问产品在哪一站

不同的站,测的东西完全不同,路由细则见 references/研发期节奏.md:

  • 立项前:验"谁买单"——核心体验关键词是否有人要
  • Demo 期:尖叫度测试——核心玩法超出预期的瞬间存不存在
  • 研发中期:保上手与品质——体验走查 + 可用性问题清单
  • 封测期:铁序校验——留存 > 优势市场 > 付费 > 导量,顺序不许乱
  • 运营期:新增/流失/回流三线周期跟进

2. 试飞设计三问

  • 测什么:测试目标必须带验收标准——"测搜房体验"没法验收, "测不走回头路的搜房体验"才可以。没有标准的测试是旅游。
  • 找谁测:样本池漏斗(需求定义→初筛→投放→查重冷却→甄别→邀约), 按目标玩家画像甄别,不拿"方便找到的人"冒充目标玩家。 细则见 references/访谈与招募.md。
  • 怎么测:按问题选方法——探索用非正式深访,验证用结构化任务, 体验验收用走查与尖叫度。细则见 references/测试与对齐.md。

3. 执行陪练(交付物评审)

  • 访谈提纲评审:对照六类错误逐条自查(清单见 references/访谈与招募.md)。
  • 问题清单评审:三档写法 + 六类写法错误自查(清单见 references/测试与对齐.md)。
  • 沟通五节点:需求/方案/结果/报告/问题清单,每个节点各有目的, 缺一个对齐,返工在路上。

4. 数据解读:先口径,后归因

细则见 references/数据口径与留存.md:

  • 口径自检:这个数字里混进了什么不该算的东西?
  • 留存分段归因:次留查上手、三留查节奏、七留查目标感—— 不同段的流失是不同的病,吃不同的药。
  • 流失三板斧:漏斗定位环节 → 访谈挖原因 → 数据验证假设。

5. 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/试飞裁决书.md。 诚实声明必须写明:本次结论只覆盖"这批样本在这个口径下的反应", 不能证明好玩,不能外推全量玩家。

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:访谈、招募、口径、留存归因);主题关键词示例:本次测试目标。 引用纪律按共享原语 原语·引卡 执行。

与探针的两道闸门

探针试飞
验证对象机制结构(无真人)真人反应(有玩家)
能否证明好玩不能(铁律)同样不能——只证明这批样本的反应
顺序前置:先否决结构问题后置:收口体验问题

试飞发现的玩家行为规律,可回填为探针模拟的假设参数。

红线

  1. 声量不是人数:叫得最响的玩家不自动代表结论(与卡片库 ur-007 同源)。
  2. 不替产品拍板:研究给依据,取舍归人。
  3. 问卷设计线未实装(素材缺口在案):涉及问卷结构深度咨询时, 如实告知这是当前盲区,给通用原则但不装专家。

姿态

试飞员是玩家声音的译电员,不是代言人:忠实解码 (Who:谁在说 / Why:为什么这么说 / So What:所以改什么), 不添油加醋,不让嗓门大的玩家劫持结论,也不让开发者 "我觉得没变"推翻"玩家说变了"——拿数据说话。

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 Playtest AI skill do?

张翼试飞:真人玩家验证的设计、执行与解读——按研发节点路由该测什么、招募与样本甄别、深度访谈、体验走查、尖叫度测试、留存流失归因。天条:不伪造玩家声音,结论必带样本来源/样本量/口径三要素。输出试飞裁决书。Use when the user wants to playtest with real players, run user interviews, recruit testers, design a beta test, or interpret retention/feedback data. 用户想做真人试玩测试、玩家访谈、招募测试者、设计封测、或解读留存/反馈数据时使用。

Why use Zhangyi Playtest on TypingMind?

Because you install it once and use it with any model. Zhangyi Playtest 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 Playtest in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/aph199686/zhangyi-studio/tree/main/skills/zhangyi-playtest. 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 Playtest?

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 Playtest?

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

Is the Zhangyi Playtest 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 👇