Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add pixel-cellar/Claude-Code-Game-Studios --skill team-polishgit clone --depth 1 https://github.com/pixel-cellar/Claude-Code-Game-StudiosWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/pixel-cellar/claude-code-game-studios/team-polish)<a href="https://agentmods.dev/skills/pixel-cellar/claude-code-game-studios/team-polish"><img src="https://agentmods.dev/badge/skills/pixel-cellar/claude-code-game-studios/team-polish/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pixel-cellar/claude-code-game-studios/team-polish"><img src="https://agentmods.dev/badge/skills/pixel-cellar/claude-code-game-studios/team-polish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.01146 |
| Opus 5.5 | $0.00018 | $0.00458 |
| Sonnet 5.5 | $0.00009 | $0.00229 |
| Haiku 4.5 | $0.00004 | $0.00115 |
Grade A, and why
team-polish scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
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。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 79 lines · 44 tokens per session scan A 9cb171b8d99b
team-polish is a skill published in the GitHub repository pixel-cellar/Claude-Code-Game-Studios (361 stars, last pushed 6mo ago), licensed MIT. It adds 44 tokens to every session and 1,146 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
minecraft-debug-mcp
Operate and debug the live Minecraft bot through its built-in MCP REPL server. Use when work requires starting the bot with pnpm dev, connecting to the local MCP endpoint, inspecting cognitive state/logs/history, injecting synthetic chat/events, or running targeted REPL code against the running brain during…
cli-anything-nsight-graphics
Windows-first CLI harness for Nsight Graphics capture, GPU Trace summary, and ngfx-replay analysis.
unity-console
Capture and query the Unity Editor console.
diagnosing-bgs-problems
A symptom-first guide for investigating crashes, frame-rate drops, stuttering, freezes, and startup failures in Bethesda Game Studios games with mods.
axiom-audit-spritekit
Use when the user wants to audit SpriteKit game code for common issues — physics bitmask issues, draw call waste, node accumulation, and action leaks.
performance-optimization
Find and fix game performance problems methodically — measure with the engine profiler first, reason about the frame-time budget, locate the CPU-vs-GPU bottleneck, then apply the right fix: object pooling, draw-call batching, fewer allocations/GC spikes, and asset budgets. Engine- neutral method that pairs with each…