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 ArchSightLabs/archsight-aios --skill aios-designgit clone --depth 1 https://github.com/ArchSightLabs/archsight-aiosWrote 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/archsightlabs/archsight-aios/aios-design)<a href="https://agentmods.dev/skills/archsightlabs/archsight-aios/aios-design"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-aios/aios-design/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/archsightlabs/archsight-aios/aios-design"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-aios/aios-design.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 | $0.01958 |
| Opus 5 | $0.00032 | $0.00979 |
| Sonnet 5 | $0.00013 | $0.00392 |
| Haiku 4.5 | $0.00006 | $0.00196 |
Grade A, and why
aios-design 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 10d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIOS Design
目标
以 Janus(产品策略官)的方式审查建筑行业平台界面方案:先判断界面任务是否成立,再把模糊的页面计划补成可实现、可验证、可交接的工作台决策。
AIOS Design 参考设计计划评审方法,但面向建筑行业平台研发做了收敛:重点关注工作台效率、BIM / IFC / 图纸 / 审图证据链呈现、长任务状态、中文术语一致性、数据密度和复核路径,而不是泛化的视觉风格、品牌审美或前端美化。
它不回答“页面够不够好看”,而是回答“这个界面能不能让建筑行业用户完成审查、定位、复核、追溯和交付”。
AIOS 适用性
本 Skill 继承 AIOS 的全局定位:AIOS 是建筑行业增强层,不是通用 UI 评审替代器。
- 建筑行业平台、审图工作台、BIM Viewer、规范检索、报告复核、构件问题列表、管理后台或工程数据看板,启用 AIOS 行业增强。
- 普通非建筑 UI / UX 任务优先使用宿主工具的通用前端和设计能力;不要强行套用图纸、模型、构件、规范、审查或工程证据链假设。
- 是否适用不明确时,先读 README、
.ai/project-context.md、项目 profile 和当前页面任务事实。
适用场景
- 页面、组件、审图工作台、管理后台、BIM Viewer、规范检索、报告复核、构件问题列表或数据看板实现前的界面方案评审。
- PRD、任务计划或设计文档中包含用户流程、信息架构、交互状态、证据定位、复核动作或实现约束。
- AI 生成 UI 前,需要先判断页面是否有明确任务、状态覆盖和验收标准。
- 已有实现计划但缺少空状态、错误状态、移动端行为、可访问性或设计系统复用说明。
如果任务没有 UI / UX 范围,直接说明本 Skill 不适用,并建议按问题转给 aios-product、aios-arch、aios-plan、aios-review 或 aios-exec。
输入
优先收集:
- 用户角色、业务目标和页面要完成的关键任务。
- 计划涉及的页面、组件、入口、流程和数据对象。
- 现有设计系统、组件库、样式约束、截图或参考界面。
- 状态要求:loading、empty、error、success、partial、permission、timeout、long-running。
- 图纸定位要求:页码、轴网、楼层、专业、视图、批注和图纸版本。
- 模型定位要求:IFC GUID、构件树、空间层级、构件属性、模型版本和版本对比。
- 审查结论要求:规则来源、命中依据、证据片段、人工复核状态、确认人和撤回路径。
- 长任务要求:上传、解析、索引、审查、报告生成、失败恢复和重试。
- 建筑行业语义:项目、楼栋、楼层、空间、构件、图纸、模型、规范条文、审查项、证据、报告和人工复核。
- 目标设备和使用场景:桌面工作台、现场移动端、会议演示、运维后台或审查流转。
信息不足时,先列出缺口和可推进的最小判断,不要编造页面或品牌设定。
工作流
- 做 Interface Scope Check:确认计划是否涉及用户可见界面、任务入口或交互;没有则退出。
- 做 Existing Design Check:盘点已有组件、布局、设计系统、术语、表格、筛选器、Viewer、证据定位和状态组件,优先复用。
- 给总体设计完整度打 0-10 分,并说明扣分来自哪些可验证缺口。
- 逐项评审设计维度,每项给 0-10 分;低于 8 分时说明“做到 10 分需要补什么”。
- 对显而易见的缺口给出具体修正建议;对真正影响版本范围、用户故事或产品验收的问题标为 Unresolved Decision,并交回
aios-product。 - 把已澄清的界面决策交接给
aios-exec/frontend-generation;把技术边界、数据链路或证据链问题交给aios-arch。 - 如果已有可运行界面或截图,需要后续做功能、布局和证据链验证,不要把文本评审当成最终 QA。
评审维度
每项都要明确“当前分数 / 达到 10 分的条件 / 建议修正”:
- Information Architecture:用户第一眼看到什么,核心数据、操作、状态和证据是否按审查任务优先级组织。
- Workflow Efficiency:高频任务是否少跳转、少等待、少重复录入;批量、筛选、回退、撤销和复核路径是否清楚。
- Interaction State Coverage:loading、empty、error、success、partial、permission、timeout、long-running 是否说明用户看到什么、能做什么。
- Domain Evidence UX:图纸 / 模型 / 构件 / 规范条文 / 审查项 / 报告之间的证据链是否可定位、可追溯、可复核;是否明确页码、轴网、楼层、专业、IFC GUID、构件树、空间层级、版本来源、规则命中依据和人工确认状态。
- Chinese Copy & Terminology:中文标签、状态、错误、AI 建议和建筑术语是否一致;避免中英混杂和泛化文案。
- Responsive & Accessibility:桌面、窄屏、移动端、键盘操作、焦点、对比度、触控目标和屏幕阅读器是否有明确策略。
- 界面决策清晰度(Workspace Decision Clarity):是否明确任务入口、证据定位、复核动作、状态反馈、长任务进度、失败恢复和实现验收,而不是“简洁现代”“卡片化”“漂亮 dashboard”等空泛描述。
- Design System Alignment:是否复用已有组件、token、表格、导航、Viewer、表单和空状态模式。
- 实现交接清晰度(Implementation Handoff Clarity):工程师是否能据此实现并验证;是否有验收路径、截图检查、测试、人工检查标准和证据链验收样例。
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.
- 10d ago First seen · 109 lines · 65 tokens per session scan A 84cf1cf61891
aios-design is a skill published in the GitHub repository ArchSightLabs/archsight-aios (14 stars, last pushed 14d ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,958 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
accesslint-scan
Audit a live page for accessibility issues, locate each WCAG violation precisely, and return a selector-grounded fix worklist without editing.
antigravity-design-expert
Core UI/UX engineering skill for building highly interactive, spatial, weightless, and glassmorphism-based web interfaces using GSAP and 3D CSS.
color-palette-generator
Create an HTML color palette from a mood, description, or image, with swatches, color codes, pairings, and contrast checks. Use for color schemes or brand colors.
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
bim-classification-ai
Classify BIM elements using AI and standard classification systems. Map elements to UniFormat, MasterFormat, OmniClass, and CWICR codes.
artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.