Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/guiguiyan930-source/game-ui-design-workflownpx agentmods add skills/guiguiyan930-source/game-ui-design-workflow/game-ui-sprite-sheet-splitterWrote 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/guiguiyan930-source/game-ui-design-workflow/game-ui-sprite-sheet-splitter)<a href="https://agentmods.dev/skills/guiguiyan930-source/game-ui-design-workflow/game-ui-sprite-sheet-splitter"><img src="https://agentmods.dev/badge/skills/guiguiyan930-source/game-ui-design-workflow/game-ui-sprite-sheet-splitter/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/guiguiyan930-source/game-ui-design-workflow/game-ui-sprite-sheet-splitter"><img src="https://agentmods.dev/badge/skills/guiguiyan930-source/game-ui-design-workflow/game-ui-sprite-sheet-splitter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00085 | $0.01562 |
| Opus 5 | $0.00043 | $0.00781 |
| Sonnet 5 | $0.00017 | $0.00312 |
| Haiku 4.5 | $0.00009 | $0.00156 |
Grade A, and why
game-ui-sprite-sheet-splitter 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
游戏 UI 雪碧图拆分与 PNG 打包
把组件拆解阶段生成的整张雪碧图进一步切成独立透明 PNG,并打包成可下载 ZIP。不要把“生成组件清单”误当成“已经完成像素级切图”。
前置条件
读取:
- 已批准的组件拆解结果
contracts/style-contract.yamlcontracts/component-contract.yamlcontracts/asset-manifest.yamlcontracts/sprite-contract.yaml(存在时)
输入雪碧图必须是实际存在的图片文件。若只有提示词或组件列表,先完成组件图生成。
最终单元素 PNG 必须去掉全部文字,包括标题、按钮文案、数字标签、占位文字、水印和说明编号。文字不是组件图形的一部分。
适用输入
- 透明背景雪碧图:优先按 Alpha 通道识别。
- 纯色或近似纯色背景:采样四周背景色并移除。
- 同一张图上的按钮、图标、卡片、装饰、特效和角色。
不适合:
- 元素互相遮挡或粘连严重的完整 UI 页面。
- 带复杂场景背景且元素没有间隔的合成图。
- 需要恢复被遮挡像素的素材。
遇到这些情况,应重新生成留有间距的组件雪碧图,而不是强行切割。
输入雪碧图规范
组件生图时优先要求:
- 所有元素完整、互不接触、四周留白。
- 统一纯色背景或透明背景。
- 不要文字、编号、水印和说明线。
- 阴影不要跨越到相邻组件。
- 相似状态按固定顺序排列,但不绘制网格线。
- 不要把一个组件拆散成多个远离的碎片。
自动拆分
执行:
python3 scripts/split_sprite_sheet.py <source.png> \
--output-dir <project>/assets/sprites/<pack-id>/items \
--zip <project>/packages/<pack-id>-png.zip \
--mode auto \
--prefix <pack-id>
默认行为:
- 输入有透明通道时按 Alpha 检测。
- 输入不透明时采样边缘背景色。
- 合并距离较近的像素区域。
- 过滤过小噪点。
- 每个元素增加安全边距。
- 导出独立透明 PNG。
- 生成
sprite-manifest.yaml。 - 生成包含 manifest 和全部 PNG 的 ZIP。
语义 mapping
自动序号不能作为最终资产名。准备按检测顺序排列的 YAML:
items:
- semantic_name: shop-buy-button-normal
component_id: shop-buy-button
category: button
state: normal
slice: {type: 9-slice, margins: [36, 36, 28, 28]}
执行时增加:
--mapping mappings/shop-components.yaml
工具会用 semantic_name 作为 PNG 文件名,并把组件 ID、分类、状态与 slice 写入 manifest。命名和切图方式分别遵循组件技能的语义命名规范与切图规则。
自动切割不会自动识别或修复文字。源雪碧图仍有文字时,先执行以下任一操作,再开始切割:
- 优先重新生成无文字雪碧图。
- 无法重生时,对文字区域做蒙版修复或内容填充,补回底板纹理。
- 修复后重新检查,不能只把文字裁掉而留下透明洞、色块或残影。
不得把含文字的切片标记为批准。
参数调整
元素被拆得太碎:
--connect-gap 6
多个元素被粘成一张:
--connect-gap 0
背景残留:
--mode background --background-tolerance 16
浅色组件被误删:
--background-tolerance 8
小图标被过滤:
--min-area 16
需要更多裁切留白:
--padding 8
重新输出时显式使用 --force,不得静默覆盖已批准包。
项目契约
将结果写入 contracts/sprite-contract.yaml:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 207 lines · 85 tokens per session scan A 0ade5ffa92ad
game-ui-sprite-sheet-splitter is a skill published in the GitHub repository guiguiyan930-source/game-ui-design-workflow (170 stars, last pushed 1mo ago), licensed MIT. It adds 85 tokens to every session and 1,562 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
uw-ui-toolkit-binder
Generate Unity 6+ UI Toolkit Runtime Data Binding code using MVVM pattern with [CreateProperty], DataBinding, and PropertyPath. Use when creating UI screens, HUDs, menus, inventories, settings panels, or any data-bound UI elements with UI Toolkit. Triggers on requests like "create a health bar", "build the HUD", "make…
uw-unity-test-runner
Generates EditMode and PlayMode tests using NUnit, mapped from GDD Gherkin scenarios. Use when writing tests, validating features, ensuring code quality, or verifying behavior after changes. Triggers on requests like "write tests for this", "test the health system", "add unit tests", "verify this works", "add PlayMode…
uw-dependency-injection
Opt-in DI architecture using Reflex for Unity 6+. Covers container setup, scoping, injection, command pattern, update management, and class taxonomy. Use when ProjectConfig.yaml -> architecturepattern is "di-first", or when the user asks about dependency injection, inversion of control, service architecture, or…
uw-network-setup
Generates networking boilerplate adapted to the project's chosen networking package (NGO, Mirror, Photon). Use when setting up multiplayer systems, syncing state, writing RPCs, building lobbies, or designing an authority matrix. Triggers on requests like "add multiplayer", "sync player health", "create an RPC", "set…
uw-state-machine
Interface-based state machine patterns for Unity game states, character controllers, and UI flows. Use when implementing game flow (menu -> gameplay -> game over), character states (idle -> run -> jump -> fall), AI behavior states, or UI screen transitions. Triggers on "state machine", "game states", "character…
uw-game-feel-integrator
Inject juice and game feel into gameplay code using the project's chosen middleware. Use when adding screen shake, tweens, particles, audio feedback, haptics, hitstop, or any form of "juice" to gameplay events. Triggers on requests like "add juice", "make this feel better", "add screen shake", "polish this feature"…