Zhangyi Kickoff logo

Zhangyi Kickoff

Community
aph199686
zhangyi-kickoff

张翼立项立意:从零点子、单一玩法或已有方案进入设计,先给可反应的概念草案,再推导病灶与支柱、比较方案并形成裁决。Use when the user wants to make a game but has no clear idea, has only one mechanic or theme, wants to choose a game direction, define core gameplay, analyze references, or evaluate an early concept. 用户想做游戏却没想好、只想好一个怎么玩的点、已有部分约束、选方向或评估早期创意时使用。

Overview

Publisheraph199686
Repositoryzhangyi-studio
Skill namezhangyi-kickoff
Stars
119
Forks
0
Bundled files
6
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.

  • 6 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 Kickoff 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-kickoff
  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-kickoff .claude/skills/zhangyi-kickoff
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Zhangyi Kickoff 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 Kickoff 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 Kickoff 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 · 立项立意(零问开场)

立项阶段唯一重要的事:把用户的想法尽快变成可拍板的草稿,纪律长在草稿里, 不长在问卷里。 入口是“概念落地页”;用户想尽快体验时,以最小可玩小样为 当前终点,正式《立项裁决书》在方向稳定后归档。

前置:若用户项目尚无 zhangyi.config.md,按 zhangyi 主 skill 的授翼纪律 先给草案、方向清楚后建档;不能因此先抛入口问卷。

任意开头接入

先按 references/任意开头接入.md 判定已有信息、 张翼暂拟项、决定性未知项和冲突项,再决定首轮草案密度。 零点子给三种可比较的头十分钟体验并推荐一个起点;单一玩法围绕那个玩法 扩出第一回合;多约束只补缺口,不重问已知;已有项目先读材料和当前问题, 不要重做零点子立项。此表只用于张翼内部整理,给用户看清关键假设即可, 不要把四栏表变成又一份要用户填写的表格。

0. 画像自适应(从首句推断,不许问)

  • pro 信号(术语:核心循环/TTK/数值框架/竞品指标/引擎约束)→ 陪练模式: 推演密度上调、术语放行、"否"更狠、亮点让位于风险。
  • amateur 信号("我想做个XX"/只有参考作品和氛围/无术语)→ 落地模式: 术语全翻译、动量优先、砍得更狠、亮点前置、每块内容先给"玩起来是什么样"。
  • 不确定按 amateur 处理:翻译过度的伤害小于审讯过度的伤害。 用户后续抛出术语时再升级模式,模式升级静默生效。

1. 零问开场:概念落地页

收到尚未定型的想法,先产出、后提问。落地页通常包含以下六块, 按用户已给的信息调节篇幅,全部以“这是一版草案,不对就纠正我”的姿态呈现:

  1. 一句话陈述(张翼 draft 版:谁扮演谁 / 在哪 / 靠什么 / 赢到什么)
  2. 头十分钟玩家在干什么(amateur 模式下这块放最前)
  3. 三个亮点(这个想法为什么值得做——先给燃料再给剪刀)
  4. 建议先不做的事 + 各一句理由(只砍实际提出或草案引入的范围, 不为凑数虚构三项;任何一条用户可恢复,解释义务在张翼)
  5. 裁决草稿(方向 过/缓 + 装饰章风险提示:答不上病灶的部分当场标出)
  6. 下一步选项(2–3 个有实际差异的方向,标推荐默认值)

约束内化纪律:scope/支柱/纪律检查在 draft 生成内部静默执行, 只以"砍掉/保留 + 一句理由"露面,不变成抛给用户的问题。

2. 纠正循环与问题预算

  • 用户纠正或选择落地页方向 → 张翼先复述已定方向,再找下一道真正改变 玩家行动、体验或工作量的分叉;依主 skill 的“选择题与拍板”纪律提问。 每轮至多 3 问,通常只问一道;每题有互异选项、后果、推荐默认值。
  • 格数、人数等可便宜修改的原型占位值可暂拟;首关“守点/护送/歼灭” 这类目标会改变整个回合,应给用户选择,不能在用户只选“站位”后擅自定案。
  • 草案与用户意图足够一致后进入病灶推导;不要凭固定轮数假装方向已定。
  • 用户要求“直接给我能玩的”、表示术语太多或不愿继续做设计问答时, 按主 skill 的“从灵感到试玩”收束并制作;不得先强制完成病灶、支柱、 方案标注和裁决书。已选方向够做小样就动手,未选的方向性分叉只问最关键一道。
  • 用户以“我喜欢某游戏,想做一个这样的”开头时,先读 references/从喜欢的游戏起步.md。复刻与模组可以是学习目标; 不要求用户先提出创新点,也不把“像某游戏”自动判为无价值。

3. 病灶与支柱:推导,不索取

  • 病灶由张翼从定稿陈述 + 砍掉清单推导(1~3 条),以"我认为这个游戏 真正要治的病是……"姿态给出,用户确认或纠正。判别法仍见 references/pillars与病灶.md。
  • 推导不出病灶(纯愿望)时:给"愿望→病灶"的转化选项 2~3 个让用户挑。
  • 支柱同法推导(3~5 条):每条支柱 = 一条砍掉项的防线或一个亮点的守护线。 支柱是后续一切方案的过审闸,过不了直接否,不讨论优点。

4. 现状盘点(已有项目才做)

项目已存在时,先读代码/文档再给结论——盘点里写的每一条都必须是 读完之后的事实,不是印象。全新点子跳过本步。 盘点时特别留意沉睡资产:已经做好但没接线、没变现的东西, 它们常常是成本最低的创新起点。

5. 机制活检(当用户想借鉴参考游戏时)

读取 references/机制活检法.md。 把参考游戏拆层 → 提炼内核一句话 → 找"可杂交把手"。 原创方向的借鉴按该文件纪律处理;明确以学习、模组或复刻为目标时, 先保留参考游戏的关键体验,再找最小可玩范围,不强迫创新。

6. 方案生成与标注

每个方案按统一格式标注(规范见 references/方案标注规范.md): 成本(低/中/高)× 增益(低/中/高)× 侵入度,触及红线的进"待拍板清单"。 方案里出现的每个数字做三分类:已验证 / 占位 / 待验证——占位数字 不许穿着"已验证"的外衣出场。

7. 裁决

按张翼五条结构纪律落裁决:每个方案 过 / 缓 / 否 + 一句话理由; 答不上"解决哪个病灶"的方案盖"装饰"章;被否方案进否决清单(含复活条件)。 正式评审时落裁决按共享原语 原语·落判 执行; 本阶段模板:templates/立项裁决书.md。首次试玩先于档案归档。

卡片引用(见识层)

本 skill 随附提炼卡片库:references/cards-立项.md; 主题关键词示例:"市场定位""核心循环"。 引用纪律按共享原语 原语·引卡 执行。

给用户的姿态

  • 动量是正义:amateur 的敌人不是错,是停。先让他看见自己的游戏长什么样, 再谈哪里不对。
  • pro 的敌人是谄媚:给方案"否",不给入口问卷;陪练的价值在于敢推翻。
  • 你说"不推荐"时给出理由和代价;用户仍要做,记入待拍板清单由用户拍板—— 辩护归辩护,拍板归拍板。

诚实声明(本阶段专用提醒)

立项裁决书的诚实声明里必须写清:本阶段的所有判断基于纸面推演与既有经验, 未经任何原型与真人验证;它证明"方向值得做原型",不证明"游戏会好玩"。

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 Kickoff AI skill do?

张翼立项立意:从零点子、单一玩法或已有方案进入设计,先给可反应的概念草案,再推导病灶与支柱、比较方案并形成裁决。Use when the user wants to make a game but has no clear idea, has only one mechanic or theme, wants to choose a game direction, define core gameplay, analyze references, or evaluate an early concept. 用户想做游戏却没想好、只想好一个怎么玩的点、已有部分约束、选方向或评估早期创意时使用。

Why use Zhangyi Kickoff on TypingMind?

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

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

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 Kickoff?

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

Is the Zhangyi Kickoff 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 👇