编排打磨团队:协调 performance-analyst、technical-artist、sound-designer 和 qa-tester,对功能或区域进行优化、打磨和加固,以达到发布品质。

MITAuto-check: notes

Install Team Polish

skills CLI
$ npx skills add pixel-cellar/Claude-Code-Game-Studios --skill team-polish -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install pixel-cellar/Claude-Code-Game-Studios team-polish --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/pixel-cellar/Claude-Code-Game-Studios.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/team-polish .claude/skills/team-polish && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
team-polish
GitHub stars
346
Token cost
~495 tokens
SKILL.md length
106 words
Files
1
Skills in repo
23
Repo updated
First seen
Licence
MIT

At a glance

编排打磨团队:协调 performance-analyst、technical-artist、sound-designer 和 qa-tester,对功能或区域进行优化、打磨和加固,以达到发布品质。

  • SKILL.md covers 团队组成, 如何委派, 管线 and 输出
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Team Polish is an agent skill from pixel-cellar/Claude-Code-Game-Studios. 编排打磨团队:协调 performance-analyst、technical-artist、sound-designer 和 qa-tester,对功能或区域进行优化、打磨和加固,以达到发布品质。

Its SKILL.md is about 500 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: 48 协同代理管理独立游戏开发的 Claude Code 架构 (中文本地化版本). The licence is MIT.

Example prompts

  • “/team-polish”

Requirements

  • Pre-approved tools (allowed-tools): Read, Glob, Grep, Write, Edit, Bash, Task, AskUserQuestion, TodoWrite

What it can do on your machine

Read from SKILL.md and the folder at commit 2c016ef. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Glob
    • Grep
    • Write
    • Edit
    • Bash
    • Task
    • AskUserQuestion
    • TodoWrite

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Team Polish loads about 495 tokens when it runs. Until then it costs about 28 tokens; SKILL.md has 106 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~28
When it runs · the whole SKILL.md, loaded when a task matches
~495

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Glob, Grep, Write, Edit, Bash, Task, AskUserQuestion, TodoWrite

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from pixel-cellar/Claude-Code-Game-Studios at commit 2c016ef, republished under its MIT licence (© pixel-cellar). 106 words, ~495 tokens.

Download SKILL.mdSave it as .claude/skills/team-polish/SKILL.md (or your agent's skills folder).
name
team-polish
description
编排打磨团队:协调 performance-analyst、technical-artist、sound-designer 和 qa-tester,对功能或区域进行优化、打磨和加固,以达到发布品质。
allowed-tools
Read, Glob, Grep, Write, Edit, Bash, Task, AskUserQuestion, TodoWrite
argument-hint
[需要打磨的功能或区域]
user-invocable
true

当此技能被调用时,通过结构化管线编排打磨团队。

决策点: 在每个阶段转换时,使用 AskUserQuestion 将子代理的提案作为可选项展示给用户。在对话中写出代理的完整分析,然后用简洁的标签记录决策。用户必须批准后才能进入下一阶段。

团队组成

  • performance-analyst(性能分析师) — 性能分析(Profiling)、优化、内存分析、帧预算
  • technical-artist(技术美术) — 视觉特效(VFX)打磨、着色器(Shader)优化、视觉品质
  • sound-designer(音效设计师) — 音频打磨、混音(Mixing)、环境音层、反馈音效
  • qa-tester(QA 测试员) — 边界情况测试、回归测试(Regression Testing)、长时间压力测试(Soak Testing)

如何委派

使用 Task 工具将每位团队成员生成为子代理:

  • subagent_type: performance-analyst — 性能分析、优化、内存分析
  • subagent_type: technical-artist — 视觉特效打磨、着色器优化、视觉品质
  • subagent_type: sound-designer — 音频打磨、混音、环境音层
  • subagent_type: qa-tester — 边界情况测试、回归测试、长时间压力测试

始终在每个代理的提示中提供完整上下文(目标功能/区域、性能预算、已知问题)。在管线允许的情况下并行启动独立代理(例如第 3 阶段和第 4 阶段可以同时运行)。

管线

阶段 1:评估

委派给 performance-analyst(性能分析师):

  • 使用 /perf-profile 对目标功能/区域进行性能分析
  • 识别性能瓶颈和帧预算违规
  • 测量内存使用情况并检查内存泄漏
  • 对照目标硬件规格进行基准测试
  • 输出:附带优先级排序的优化清单的性能报告
阶段 2:优化

委派给 performance-analyst(性能分析师)(按需配合相关程序员):

  • 修复阶段 1 中发现的性能热点
  • 优化绘制调用(Draw Call),减少过度绘制(Overdraw)
  • 修复内存泄漏并降低分配压力
  • 验证优化未改变游戏行为
  • 输出:附带优化前后指标的优化代码
阶段 3:视觉打磨(与阶段 2 并行)

委派给 technical-artist(技术美术):

  • 审查视觉特效的品质和与美术圣经(Art Bible)的一致性
  • 优化粒子系统和着色器效果
  • 在适当位置添加屏幕震动、镜头效果和视觉冲击感(Visual Juice)
  • 确保效果在较低设置下优雅降级
  • 输出:打磨后的视觉效果
阶段 4:音频打磨(与阶段 2 并行)

委派给 sound-designer(音效设计师):

  • 审查音频事件的完整性(是否有任何操作缺少声音反馈?)
  • 检查音频混音级别——没有任何内容相对于整体混音过大或过小
  • 添加环境音层以营造氛围
  • 验证音频在空间定位下正确播放
  • 输出:音频打磨清单和混音说明
阶段 5:加固

委派给 qa-tester(QA 测试员):

  • 测试所有边界情况:边界条件、快速输入、异常操作序列
  • 长时间压力测试:长时间运行该功能,检查是否存在性能退化
  • 压力测试:最大实体数量、最坏情况场景
  • 回归测试:验证打磨变更未破坏现有功能
  • 在最低规格硬件上进行测试(如可用)
  • 输出:测试结果及剩余问题
阶段 6:签核
  • 收集所有团队成员的结果
  • 将性能指标与预算进行对比
  • 报告:可以发布 / 需要更多工作
  • 列出所有剩余问题及其严重程度和建议

输出

一份涵盖以下内容的总结报告:性能前后指标、视觉打磨变更、音频打磨变更、测试结果以及发布就绪评估。

© pixel-cellar, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/team-polish of pixel-cellar/Claude-Code-Game-Studios.

Open the folder on GitHubat commit 2c016ef

Compare with similar skills

Team Polish next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Team Polish compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Team Polish this skillpixel-cellar/Claude-Code-Game-Studios346—~495Automated safety check: NotesMIT
Frontend Slideszarazhangrui/frontend-slides30k16 repos~7kAutomated safety check: PassMIT
Algorithmic Art with p5.jsanthropics/skills180k38 repos~4.9kAutomated safety check: PassApache-2.0
Canvas Designanthropics/skills180k52 repos~3kAutomated safety check: PassApache-2.0
Impeccablebestofjs/bestofjs3.1k27 repos~2.6kAutomated safety check: PassMIT
Brand and Design Toolkitnextlevelbuilder/ui-ux-pro-max-skill134k1 repos~3.5kAutomated safety check: PassMIT

Similar skills

  • Frontend Slides

    zarazhangrui/frontend-slides

    Builds animated HTML slide decks that run in the browser with no dependencies, or converts PowerPoint files to the web, starting from visual style previews.

    30k GitHub starsUsed in 16 repos~7k tokens
    Documents & OfficeAuto-check passed
  • Official

    Creates original generative art in two steps: a written algorithmic philosophy, then a p5.js sketch with seeded randomness and an interactive viewer for exploring parameters.

    180k GitHub starsUsed in 38 repos~4.9k tokens
    Media & CreativeAuto-check passed
  • Canvas Design

    anthropics/skills

    Official

    Creates original posters and static art as PNG or PDF by first writing a short design philosophy, then expressing it visually on a canvas.

    180k GitHub starsUsed in 52 repos~3k tokens
    Media & CreativeAuto-check passed
  • Impeccable

    bestofjs/bestofjs

    A skill your agent uses when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a…

    3.1k GitHub starsUsed in 27 repos~2.6k tokens
    Frontend & DesignAuto-check passed
  • Brand and Design Toolkit

    nextlevelbuilder/ui-ux-pro-max-skill

    Bundles design tasks behind one skill: brand identity, tokens, UI styling, logos, corporate identity mockups, slides, banners, icons and social images.

    134k GitHub starsUsed in 1 repo~3.5k tokens
    Media & CreativeAuto-check passed
  • HyperFrames Animation

    heygen-com/hyperframes

    Collects motion rules, scene blueprints, transitions and runtime adapters for HyperFrames video compositions, with GSAP as the default animation runtime.

    59k GitHub starsUsed in 3 repos~2.1k tokens
    Media & CreativeAuto-check passed

More from pixel-cellar/Claude-Code-Game-Studios

All 23 skills in this repo
  • Patch Notes

    pixel-cellar/Claude-Code-Game-Studios

    从 git 历史记录、Sprint 数据和内部更新日志生成面向玩家的补丁说明。将开发者语言转化为清晰、有吸引力的玩家沟通内容。

    346 GitHub stars~498 tokensUpdated 6 mo ago
    Auto-check: notes
  • Setup Engine

    pixel-cellar/Claude-Code-Game-Studios

    配置项目的游戏引擎和版本。将引擎锁定到 CLAUDE.md 中,检测知识缺口,当版本超出 LLM 训练数据时通过 WebSearch 填充引擎参考文档。

    346 GitHub stars~1.5k tokensUpdated 6 mo ago
    Auto-check passed
  • Estimate

    pixel-cellar/Claude-Code-Game-Studios

    通过分析复杂度、依赖关系、历史速度和风险因素来估算任务工作量。生成包含置信水平的结构化估算. An agent skill from pixel-cellar/Claude-Code-Game-Studios.

    346 GitHub stars~751 tokensUpdated 6 mo ago
    Auto-check passed
  • Perf Profile

    pixel-cellar/Claude-Code-Game-Studios

    结构化的性能分析工作流。识别瓶颈、与性能预算对比测量,并生成带有优先级排序的优化建议. An agent skill from pixel-cellar/Claude-Code-Game-Studios.

    346 GitHub stars~466 tokensUpdated 6 mo ago
    Auto-check: notes
  • Release Checklist

    pixel-cellar/Claude-Code-Game-Studios

    生成全面的发布前验证清单,涵盖构建验证、合规要求、商店元数据和发布准备就绪情况. An agent skill from pixel-cellar/Claude-Code-Game-Studios.

    346 GitHub stars~696 tokensUpdated 6 mo ago
    Auto-check passed
  • Retrospective

    pixel-cellar/Claude-Code-Game-Studios

    通过分析已完成的工作、速率、阻碍因素和模式来生成 Sprint 或里程碑回顾。产出可执行的洞见以指导下一次迭代. An agent skill from pixel-cellar/Claude-Code-Game-Studios.

    346 GitHub stars~767 tokensUpdated 6 mo ago
    Auto-check passed

Questions about Team Polish

What does Team Polish do?

编排打磨团队:协调 performance-analyst、technical-artist、sound-designer 和 qa-tester,对功能或区域进行优化、打磨和加固,以达到发布品质。. Team Polish is an agent skill from pixel-cellar/Claude-Code-Game-Studios.

How do I install Team Polish in Claude Code?

Run `npx skills add pixel-cellar/Claude-Code-Game-Studios --skill team-polish -a claude-code`. Or copy the skill folder (.claude/skills/team-polish in pixel-cellar/Claude-Code-Game-Studios) into .claude/skills/team-polish in your project. Claude Code loads it when a task matches its description.

How do I install Team Polish in Codex?

Run `npx skills add pixel-cellar/Claude-Code-Game-Studios --skill team-polish -a codex`. Or copy the skill folder (.claude/skills/team-polish in pixel-cellar/Claude-Code-Game-Studios) into .agents/skills/team-polish in your project. Codex loads it when a task matches its description.

Can I use Team Polish in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add pixel-cellar/Claude-Code-Game-Studios --skill team-polish -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/team-polish, .gemini/skills/team-polish, .github/skills/team-polish and .opencode/skills/team-polish in your project.

What does Team Polish need to run?

SKILL.md names no scripts, command-line tools or credentials: Team Polish is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Glob, Grep, Write, Edit, Bash, Task, AskUserQuestion, TodoWrite.

Does Team Polish access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Team Polish safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Team Polish use?

Team Polish is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Team Polish use?

About 495 tokens (SKILL.md is roughly 2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Team Polish?

Skills that share tags, products or a category with Team Polish: Frontend Slides (zarazhangrui/frontend-slides, 30k stars), Algorithmic Art with p5.js (anthropics/skills, 180k stars), Canvas Design (anthropics/skills, 180k stars) and Impeccable (bestofjs/bestofjs, 3.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Team Polish?

pixel-cellar (a GitHub organization) maintains it in pixel-cellar/Claude-Code-Game-Studios, which has 346 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on March 30, 2026.

Source: pixel-cellar/Claude-Code-Game-Studios on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.