<Devsly/>
NotebookLM Watermark Remover
Remove the NotebookLM watermark from PDF slide exports — free, unlimited, and 100% in your browser.
View
NotebookLM Video Watermark Remover
Remove the NotebookLM watermark from every frame of your MP4 and auto-trim the end card — free and unlimited.
View
Gemini Watermark Remover
Remove the Gemini (Veo) sparkle watermark from every frame of your AI-generated MP4 — free and unlimited.
View
MCP https://devsly.io/mcp MCP Tools Best Skills API Docs

Keyboard Shortcuts

Navigation

Quick Search
⌘ / Ctrl + K
Toggle Dark Mode
⌘ / Ctrl + D
Close Dialogs
Esc

Tool Actions

Execute / Process
⌘ / Ctrl + Enter
Clear Input
⌘ / Ctrl + Shift + C
Copy Output
⌘ / Ctrl + Shift + X

Editor

Select All
⌘ / Ctrl + A
Undo
⌘ / Ctrl + Z
Redo
⌘ / Ctrl + Shift + Z

Updated 2w ago

by aph199686

zhangyi-studio

「张翼 · 游戏设计陪练 skill 与本地工作台」

View on GitHub (opens in a new tab)

119 GitHub stars (119)

+37 in 21 days

Stars gained per day · daily snapshots since Oct 16
Stars gained per day, Oct 16 to Nov 6: +37 in total; the busiest day was Oct 17 with +32 stars.Oct 17: +32 starsOct 18: +4 starsOct 19: +1 starsOct 20: 0 starsOct 21: 0 starsOct 22: 0 starsOct 23: 0 starsOct 24: 0 starsOct 25: 0 starsOct 26: 0 starsOct 27: 0 starsOct 28: 0 starsOct 29: 0 starsOct 30: 0 starsOct 31: 0 starsNov 1: 0 starsNov 2: 0 starsNov 3: 0 starsNov 4: 0 starsNov 5: 0 starsNov 6: 0 stars
Stars gained between daily snapshots
PeriodNew stars
Oct 17+32
Oct 18+4
Oct 19+1
Oct 200
Oct 210
Oct 220
Oct 230
Oct 240
Oct 250
Oct 260
Oct 270
Oct 280
Oct 290
Oct 300
Oct 310
Nov 10
Nov 20
Nov 30
Nov 40
Nov 50
Nov 60
  • 9 skills (9 skills found in its SKILL.md files)
  • 0 forks (0 forks)
  • 2w ago last update (Last updated 2w ago)

Install

Skills CLI

npx skills add aph199686/zhangyi-studio

Asks which skills and agents to install. Just one: npx skills add aph199686/zhangyi-studio --skill zhangyi-kickoff — add -g for every project.

Claude Code

git clone https://github.com/aph199686/zhangyi-studiocp -r "zhangyi-studio/skills/zhangyi-kickoff" ~/.claude/skills/

Copies the zhangyi-kickoff skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.

Plugin

/plugin marketplace add aph199686/zhangyi-studio

Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.

Skills can run code on your machine — read the SKILL.md first.

What it does

In the author's own words, from each skill's SKILL.md.

  • 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。

    skills/zhangyi-kickoff/SKILL.md on GitHub (opens in a new tab)
  • zhangyi-narrative

    张翼叙事设计:叙事即机制的判别与落地、角色塑造(角色意志)、世界观与命名纪律、剧本结构与信息释放节奏、叙事仪式感与工程化。输出叙事裁决书。Use when the user writes game story/plot, designs characters or worldview, names things in the game, structures scripts/dialogue, or asks how narrative and gameplay fit together. 用户写剧情、设计角色或世界观、给游戏事物命名、排剧本结构、或纠结叙事与玩法怎么结合时使用。

    skills/zhangyi-narrative/SKILL.md on GitHub (opens in a new tab)
  • 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。

    skills/zhangyi-playtest/SKILL.md on GitHub (opens in a new tab)
  • 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。

    skills/zhangyi-probe/SKILL.md on GitHub (opens in a new tab)
  • zhangyi-relay

    张翼接力:跨会话的项目连续性管理。新会话开局生成交接提示词(开场白九模块)、核验上一会话遗留状态、每批工作收尾时沉淀交接段(遗留待办/新红线/新环境坑)。Use when the user starts a new session to continue existing work, asks to sync project status, wants a handoff/continuation prompt, or finishes a batch of work. 用户开新会话继续旧项目、需要交接提示词、同步项目进度、或一批工作收尾时使用。不限于游戏项目。

    skills/zhangyi-relay/SKILL.md on GitHub (opens in a new tab)
  • zhangyi-review

    张翼审查收尾:发布前或阶段节点的全面审查——范围与证据口径先行、六级结论分级、每条结论带证据引用、执行摘要与'未来两周 N 件事'。输出审查裁决书。Use when the user prepares for release/launch, wants a full project audit, checks store/platform readiness, reviews builds/CI/saves/rights, or asks whether the project is ready. 用户准备上架发布、想做全面项目审查、检查平台就绪度、核查构建/CI/存档/权利链、或问'现在能发了吗'时使用。

    skills/zhangyi-review/SKILL.md on GitHub (opens in a new tab)
  • zhangyi-systems

    张翼机制与系统设计:核心循环细化、新机制评审过闸、数值纪律与平衡裁决。每个机制必须回答'解决哪个病灶'、区分'强化内核还是堆系统'、推演诱发的玩家行为与情绪,输出系统裁决书。Use when the user designs mechanics/systems, tunes numbers or balance, evaluates adding a new mechanic, designs core loop details, or asks whether a feature is worth building. 用户设计机制与系统、调数值做平衡、纠结加不加某个机制、细化核心循环、或问某个功能值不值得做时使用。

    skills/zhangyi-systems/SKILL.md on GitHub (opens in a new tab)
  • zhangyi-takeover

    张翼接管:接手已在开发中、方向已定的项目,跳过立项——只读核验现状、免立项确认、深度建立框架与目录理解、经显式授权后整理目录、任务编排与接续台账(ledger)。Use when the user has an existing in-progress game project (possibly built with another AI or a previous developer), wants to skip kickoff, and needs takeover, project management, task orchestration, or continuation development. 用户带着做了一半的游戏工程、想跳过立项、需要接管/项目管理/统筹/排期/任务拆解/接续开发时使用。

    skills/zhangyi-takeover/SKILL.md on GitHub (opens in a new tab)
  • zhangyi

    张翼总入口:让不同起点的创作者进入游戏设计陪练,先给可反应的草案或现状诊断,再路由立项、机制、叙事、验证、收尾与跨会话接力;维护口吻、裁决和首次使用纪律。Use when the user wants to make or design a game, brings a partial idea or existing project, asks what this skill does, or continues game work. 用户想做游戏、只有一个玩法点子、已有企划或原型、询问张翼用途、或跨会话继续开发时使用。

    skills/zhangyi/SKILL.md on GitHub (opens in a new tab)

Review before you install

A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.