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 eiway112/prefab-interior-skills --skill prefab-storage-systemgit clone --depth 1 https://github.com/eiway112/prefab-interior-skillsWrote 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/eiway112/prefab-interior-skills/prefab-storage-system)<a href="https://agentmods.dev/skills/eiway112/prefab-interior-skills/prefab-storage-system"><img src="https://agentmods.dev/badge/skills/eiway112/prefab-interior-skills/prefab-storage-system/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/eiway112/prefab-interior-skills/prefab-storage-system"><img src="https://agentmods.dev/badge/skills/eiway112/prefab-interior-skills/prefab-storage-system.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 | $0.00136 | $0.09201 |
| Opus 5.5 | $0.00054 | $0.03680 |
| Sonnet 5.5 | $0.00027 | $0.01840 |
| Haiku 4.5 | $0.00014 | $0.00920 |
Grade A, and why
prefab-storage-system 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 29d 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 — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.
装配式收纳系统
v2 认知模型升级：从"技术顾问式回答"转变为"决策方法论 + 验证引擎"。旧模型："你有什么需求 → 我给出经验建议"；新模型："你有任何收纳方案 → 我帮你系统验证 → 你做出决策"。技能的知识分三层处理：原则红线层（不可逾越的硬约束）、方法论层（核心能力输出）、演示示例层（方法论运作载体）。
版本说明：v2.1.3（CG-20260923-005，2026-09-23）：PL-061 锚固承载面收窄——撤出无条件单点承载值（原§3.1）与通用安全系数（原§2.2），立锚固核查入口与缺参停止判据。锚固承载力系多参数派生量、无可无条件套用的普适单值（内容性质使然，与标准是否收录于索引无关）；JGJ 145-2013《混凝土结构后锚固技术规程》的价值在于给出验算方法与破坏模式判据（混凝土锥体、钢材、胶筋界面、劈裂、群锚折减），应据其验算确定承载力，而非从中摘取一个无条件数值。
v2.1.1（CG-20260813-033，2026-08-13）：在 §7 跨技能路由中新增 IC-06 接口契约引用（收纳技能 → 隔墙技能），消除"契约有定义、运行时无锚点"漂移。
历史：v2.1.0：完成 v2 架构落地——新增多文件协同架构、全局编号红线体系、D/E 层示例与产品解决方案库。
1. 角色定位
本技能专注于模块化收纳部品与空间接口协调，核心职责：
- 收纳部品的模块化选型与配置
- 尺寸模数体系与空间适配
- 与墙面/楼地面/吊顶系统的接口收口设计
- 安装顺序与基层条件确认
- 非标风险识别与预警
边界声明：结构承载力验算（壁挂柜体锚固、悬挑构件）须由注册结构工程师确认；柜体深化设计由家具设计师完成；本技能仅提供装配式装修层面的接口协调与安装控制建议。
2. 知识体系
2.1 系统分类
按空间分类
| 空间 | 典型部品 | 核心关注 | 特殊要求 | 数据来源 |
|---|---|---|---|---|
| 玄关 | 玄关柜、鞋柜、换鞋凳、挂衣区 | 与门套关系、深度控制 | 通风（鞋柜）、照明 | S2：行业通用做法 |
| 卧室 | 衣柜、床头柜、梳妆台、家政柜 | 模数化、内部功能分区 | 与空调/窗帘盒关系 | S2：行业通用做法 |
| 厨房 | 橱柜（地柜+吊柜+高柜）、五金拉篮 | 设备嵌入、管线避让、防潮 | 与厨卫系统深度协同 | S2：行业通用做法与设计文件 |
| 卫浴 | 浴室柜、镜柜、壁龛、置物架 | 防潮、防水接口、检修 | 防水等级、防潮板材 | S2：行业通用做法与设计文件 |
| 阳台 | 阳台柜、洗衣机柜、工具柜 | 防晒、防潮、排水 | 耐候性、与排水点位关系 | S2：行业通用做法 |
| 办公 | 文件柜、储物柜、隔断柜 | 模数统一、灵活组合 | 与隔断系统协同 | S3：经验数据 |
按构造分类
| 构造类型 | 定义 | 适用场景 | 安装要求 | 承载特点 | 数据来源 |
|---|---|---|---|---|---|
| 落地式 | 柜体底部直接落地，通过踢脚调平 | 衣柜、玄关柜、橱柜地柜 | 地面平整度≤3mm/2m | 自重落地，顶部/背部辅助固定 | S3：本合集接口控制值（柜体安装基准面要求，取值口径见 reference.md 落地式柜体行） |
| 壁挂式 | 柜体通过挂件/螺栓固定于墙面 | 吊柜、浴室柜、壁龛 | 墙体承载力验算 | 全部荷载由墙面承担 | S2：需结构验算 |
| 嵌入式 | 柜体嵌入墙体凹龛或结构空间 | 壁龛柜、嵌入式衣柜 | 预留洞口尺寸精确 | 底部+侧面支撑 | S2：设计文件 |
| 模块化组合 | 标准模块自由组合拼接 | 开放式收纳、办公储物 | 模块间连接可靠 | 按组合方式定 | S3：经验数据 |
2.2 关键性能指标表
| 性能指标 | 要求 | 检验方法 | 适用部品 | 数据来源 |
|---|---|---|---|---|
| 甲醛释放量 | E1级≤0.124mg/m³；ENF级≤0.025mg/m³（1m³气候箱法） | 1m³气候箱法 | 所有人造板部品 | S1：GB 18580-2025 |
| 柜体承载力（层板） | 搁板弯曲挠度变化值≤0.5%（≤0.5% 即 ≤L/200）；均布荷载下与 L 为跨度两支属试验方法侧读法——该版不设跨度定义（跨度 全份计数 0），6.6.5 柜类强度和耐久性整体委托 GB/T 10357.5—2023，故挠度与跨度的换算属该试验方法标准侧（该试验方法标准未取件），本行凭据面仅支撑限值本体 |
均布荷载试验（该版 6.6.5 委托 GB/T 10357.5—2023，试验方法本体未取件） | 层板、搁板 | S1：GB/T 3324-2024 5.6 表6 搁板弯曲挠度变化值行（一般项目，条文级核验 2026-10-01，全份已逐字核验 2026-10-02）；原「卸载后无永久变形」一支该版未载，撤为无依据表述 |
| 壁挂柜体承载力 | 以结构验算结论为准：按荷载组合与锚栓/基体设计抗力验算确定；不得以通用倍数或单点经验值替代验算 | 拉拔试验+荷载试验（按验算条件） | 吊柜、浴室柜 | S2：需结构验算、结构工程师确认 |
| 尺寸偏差（柜体） | 邻边垂直度：对角线＜1000mm 时长度差≤2mm、≥1000mm 时≤3mm；长/宽/高偏差≤1mm | 钢尺/卷尺 | 所有柜体 | S1：GB/T 3324-2024 5.2 表2 邻边垂直度行（分档形制，条文级核验 2026-10-01）；≤1mm 一支严于该版表1「所有尺寸偏差应在 ±5 以内」通用档，属 S2：企业／合同约定值 |
| 门板平整度 | ≤2mm/m | 靠尺+塞尺 | 柜门 | S3：本合集施工验收口径（GB/T 3324-2024 表2 无每米斜率形制，全份已逐字核验 2026-10-02、不载此指标；其平整度项系绝对值 ≤0.20mm，不承载该断言） |
| 防潮性能（卫浴） | 板材吸水厚度膨胀率≤8%（24h浸水） | 浸水试验 | 卫浴柜 | S2：行业通用做法（GB/T 3324-2024 5.3.3 将人造板指标交由合同约定的标准承载，全份已逐字核验 2026-10-02、不载此具体值；承载标准待核验，见台账 PL-116） |
| 五金耐久性 | 铰链≥5万次开合；滑轨≥5万次推拉 | 疲劳试验 | 柜门、抽屉 | S2：行业通用做法（GB/T 3324-2024 表6 全份已逐字核验 2026-10-02、无任何开合／推拉循环次数指标，仅定性「五金连接件应无松动」；承载标准待核验，见台账 PL-116） |
| 表面耐磨 | ≥50转（漆膜）/≥100转（三聚氰胺） | 耐磨试验 | 柜体表面 | S2：企业／产品口径（GB/T 3324-2024 表4 全份已逐字核验 2026-10-02、漆膜耐磨性为「应不低于 3 级」、覆面耐磨性为聚氯乙烯薄膜饰面≥150 转／其他不低于 3 级，无 50／100 转档） |
What ships with it
4 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.
- 29d ago Changed 3669f84cead2
- 1mo ago Changed · +4 lines 5ae71802f724
- 1mo ago Changed 08bd2db79c44
- 2mo ago First seen · 393 lines · 136 tokens per session scan A f6ce1ea9fd12
prefab-storage-system is a skill published in the GitHub repository eiway112/prefab-interior-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 136 tokens to every session and 9,201 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.