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 zhuanggenhua/BoardGame --skill ui-design-pipelinegit clone --depth 1 https://github.com/zhuanggenhua/BoardGameWrote 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/zhuanggenhua/boardgame/ui-design-pipeline)<a href="https://agentmods.dev/skills/zhuanggenhua/boardgame/ui-design-pipeline"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/ui-design-pipeline/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/zhuanggenhua/boardgame/ui-design-pipeline"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/ui-design-pipeline.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 | $0.00065 | $0.02422 |
| Opus 5 | $0.00032 | $0.01211 |
| Sonnet 5 | $0.00013 | $0.00484 |
| Haiku 4.5 | $0.00006 | $0.00242 |
Grade A, and why
ui-design-pipeline 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 12d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Design Pipeline
本 skill 把复杂 UI 需求变成可执行、可评估、可回流的设计链路。它不替代项目 UI 规范、位图生图流程或前端实现;它负责在这些流程前锁定“做什么、为什么这样做、按什么验收”。
使用场景
使用本 skill:
- 新建或重做复杂页面、dashboard、游戏 Board、核心面板或主界面。
- 用户要求设计稿、视觉方向、多方案、先规划 UI、商业级或成熟产品级体验。
- UI 反复出现同类问题:状态缺失、对象职责混乱、模板味、素材没用、布局不可理解。
- 实现前需要沉淀视觉规格、信息架构、交互状态和验收标准。
不单独使用:
- 单个按钮、间距、文案或小样式修复。
- 用户只要求修 bug,且 UI 设计合同已锁定。
- 用户明确要求直接实现,且已有批准设计合同。
交付形态裁定
先裁定用户要的交付物:
- Open Design artifact:可编辑 HTML/CSS/JS 设计稿;导出截图只是验收证据,不是图片模型生成结果。
- 位图 / 生图设计稿:用户明确要生图、视觉稿、图片模型,或项目规则默认位图稿时使用。
- 前端实现:用户已批准设计并明确进入实现时才做。
- 文字 UI 设计:用户要求“先出 UI 设计,我看过再出设计稿/实现”时使用。
用户要“设计稿 / 视觉稿 / Open Design 稿 / 先看图”时,当前停在设计稿候选;未获人工批准前,不启动真实页面、不写前端、不跑实现 E2E,也不用运行页截图反推设计通过。
用户明确说“使用 Open Design / OD / opendesign,不要生图”时,走 Open Design artifact;不得调用 media generate,也不得把 media provider 问题当 artifact 阻塞。
开始前锁定
任何出图、写 brief、做 HTML 预览或实现前,先锁四项:
- 问题对象:哪个页面、组件、游戏、路由或设计稿。
- 真相来源:用户素材、规则、数据、截图、Figma、设计系统、现有页面或项目规范。
- 目标入口 / 环境:设计稿、真实页面、桌面端、移动端、项目 workflow 或通用 skill。
- 验收口径:用户批准、evaluator、截图复看、真实页面 E2E 或项目门禁。
缺任一项,只能补证据或问最小问题。
设计前置包
UI 依赖规则书、业务数据、用户素材、地图、棋盘、卡牌、物理配件、产品截图或其它领域真相源时,设计本身也受前置门禁约束。
前置包至少包含:
- 本轮读过的真相源和读取证据。
- 三条以上会改变画面的结论。
- 对象职责表:对象是什么、规则职责、何时操作/检视、隐藏信息边界、是否只是参考来源。
规则/数据/素材结论 -> 影响的主体 -> 设计决策 / 禁止项。- 素材账本:来源、路径或输入文件、状态、画面职责、允许替代方式。
- 当前玩家任务:现在要解决什么、下一次点击什么、点击后发生什么、取消/放弃路径是什么。
- 饱和状态预算:主舞台、候选集合、资源读数、结果反馈、溢出策略和让位顺序。
不能只做素材检索。只找到文件名、变量名、atlas frame、截图相似物或 CardID,不算领域理解完成。
设计不变量
- 真实素材必须进入图像输入、拼接基底、reference sheet、atlas crop 或运行时渲染来源,并在画面承担对应职责。只写路径、prompt 点名或把素材缩成角标,不算使用素材。
reference-only素材只帮助推导比例、颜色、规则或细节,不得在最终主界面作为常驻主体复现。- 动态读数可用
approved-programmatic-runtime-ui,但必须说明规则来源、对象语义和不替代物理主体。 - 可直接点击的真实对象,应优先由对象本体承接动作:进入模式、合法候选高亮、玩家直选对象、结算或有依据的确认。
- 代理面板、目标摘要、文字按钮、编号点和问号占位只在对象不可见、对象过多、无障碍入口或规则需要二次确认时出现。
- 当前结算主体必须靠近来源、目标或动作链;不能默认降到边栏、日志、工具栏或摘要区。
- 背景底图不是布局排斥体。先区分必须保护的规则热区与可被 overlay 覆盖的低权重纹理区。
- 当前可支配对象必须可读。候选卡、单位、物品、资源和行动入口不能缩成只能靠猜的缩略图。
- 大集合可降权为抽屉、分页、边缘入口或焦点预览,但入口必须让玩家知道还有多少可用对象、如何切换或展开。
- 公开归档默认是可回看入口,不常驻展开完整清单;隐藏信息、公开归档和当前候选必须先裁定再设计。
- 卡面或物件本体已经清楚印刷的信息,不机械复写成 UI chip;看不清时应放大、焦点预览或详情检视。
- 确认 / 取消 / 下一步按钮必须有规则或真实交互状态授权;无可撤销选择、无分支、无提交风险时,不为完整感造常驻确认按钮。
What ships with it
8 files 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.
- 12d ago First seen · 142 lines · 65 tokens per session scan A ef28b5ebfb5f
ui-design-pipeline is a skill published in the GitHub repository zhuanggenhua/BoardGame (23 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 2,422 once invoked, about $0.0003 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
roblox-ui
Build production Roblox interfaces with ScreenGui/PlayerGui lifecycle, responsive UDim2 layouts, safe insets, reusable editable Instances, cross-device input and selection, restrained motion, cleanup, and multi-viewport verification. Use for Roblox HUDs, inventories, shops, settings, ability bars, ScrollingFrames…
game-ui-ux
Design and build game UI/UX — HUDs, menus, and overlays — that survive every screen: anchor- based responsive layout, resolution/aspect scaling and safe areas, keyboard/gamepad focus navigation, a screen/menu state stack, and event-driven (not polled) HUD updates. Engine- neutral patterns that pair with the detected…
ux-design
Guided, section-by-section UX spec authoring for a screen, flow, or HUD. Reads game concept, player journey, and relevant GDDs to provide context-aware design guidance. Produces ux-spec.md (per screen/flow) or hud-design.md using the studio templates.
ux-review
Validates a UX spec, HUD design, or interaction pattern library for completeness, accessibility compliance, GDD alignment, and implementation readiness. Produces APPROVED / NEEDS REVISION / MAJOR REVISION NEEDED verdict with specific gaps.
unity-inspector
Advise on Unity Inspector authoring UX.
threejs-game-ui-designer
Design premium Three.js game UI: HUDs, menus, overlays, pause/win/lose screens, settings, icon controls, touch UI, typography, responsive layout, safe areas, text fit, and UI/world cohesion.