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/eiway112/prefab-interior-skillsnpx agentmods add skills/eiway112/prefab-interior-skills/prefab-floor-systemWrote 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-floor-system)<a href="https://agentmods.dev/skills/eiway112/prefab-interior-skills/prefab-floor-system"><img src="https://agentmods.dev/badge/skills/eiway112/prefab-interior-skills/prefab-floor-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-floor-system"><img src="https://agentmods.dev/badge/skills/eiway112/prefab-interior-skills/prefab-floor-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 | $0.00114 | $0.08616 |
| Opus 5 | $0.00057 | $0.04308 |
| Sonnet 5 | $0.00023 | $0.01723 |
| Haiku 4.5 | $0.00011 | $0.00862 |
Grade A, and why
prefab-floor-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 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 — 474 lines — stays where its author put it; the contents beside it link to each section on GitHub.
装配式楼地面系统 — 决策与验证引擎
§1 角色定位
| 项目 | 定义 |
|---|---|
| 技能标识 | FL |
| 技能名称 | prefab-floor-system |
| 定位 | 装配式楼地面系统的决策方法论与验证引擎 |
| 核心原则 | 所有输出结论基于物理原理和标准规范，不基于产品营销话术 |
v2 认知模型升级：从 v1 的"地面方案推荐"升级为"决策方法论 + 验证引擎"。旧模型："我有这些地面方案 → 你的需求匹配哪个 → 推荐给你"；新模型："你有任何方案 → 我帮你系统验证 → 你做出决策"。技能知识分三层处理：原则红线层（A 层，不可逾越的硬约束）、方法论层（B 层，核心能力输出）、演示示例层（方法论运作载体）。
核心能力矩阵：
| 能力 | 说明 | 支撑体系 |
|---|---|---|
| 选型决策 | 四技术路线×多场景的决策树 | B1 选型决策树 |
| 撞击声隔声估算 | 通过 ACE IC-08 调用 M5 模型 | B2 验证协议 Step 3 |
| 验证协议 | 六步骤全流程验证 | B2 验证协议 |
| 施工指导 | 关键控制点与验收标准 | B4 施工控制原则 |
与隔墙技能（PW）的协作边界：
| 维度 | FL 管辖 | PW 管辖 |
|---|---|---|
| 声学 | 撞击声：Ln,w / L'nT,w / ΔL | 空气声：Rw+C / Rw+Ctr / DnT,w+C |
| 构件 | 楼地面构造层（弹性垫层、浮筑层、架空体系等） | 隔墙构造（龙骨、板材、空腔等） |
| 红线 | FL-R-P0-1（不混淆评价量） | PW 对应红线 |
§2 认知基础
技能对"什么是装配式楼地面"的定义（三要素：基层、功能层、面层）、四分类体系（浮筑/架空/干法/快装）及分类→验证方式映射，详见 reference.md §一。该定义以 ../shared/glossary.md（合集级共享术语库）为统一基准。
核心价值声明：FL 的所有输出结论基于物理原理和标准规范，不基于产品营销话术。
认知基线指针：
| 内容 | 指针 |
|---|---|
| 定义与分类框架 | → reference.md §一 |
| 标准层次与引用规则 | → reference.md §二 |
| 原理红线层（A 层） | → reference.md §三 |
§3 方法论层摘要
B1-B5 核心能力概述
| 编号 | 能力 | 核心内容 | 指针 |
|---|---|---|---|
| B1 | 选型决策树 | 场景识别→隔声/功能路径→约束校验 | → reference.md §四 B1 |
| B2 | 验证协议 | 六步骤全流程（SRE→解析→审查→计算→核验→组装） | → reference.md §四 B2 |
| B3 | 成本分析框架 | 成本构成+典型区间+敏感性分析 | → reference.md §四 B3 |
| B4 | 施工控制原则 | 浮筑/架空/地暖兼容施工控制点 | → reference.md §四 B4 |
| B5 | 功能适应性 | 地暖兼容、管线分离、防水、荷载限制 | → reference.md §四 B5 |
B2 验证执行清单（六步骤）
所有输出结论必须经过 B2 验证协议，未经 B2 的结论不得输出（对应红线 FL-R-P0-5）。
□ Step 0: 标准推理 — 调用 IC-10（SRE）确定适用标准集和评价量
□ Step 1: 输入解析 — 建筑类型、空间类型、楼板基层、构造方案、标高约束
□ Step 2: 三原则审查 — 评价量匹配、标准时效性、适用范围
□ Step 3: 计算验证 — 调用 IC-08（ACE M5 模型）估算 ΔLw / Ln,w
□ Step 4: N 维度核验 — D1~D10 按需选择（隔声/标高/承载/声桥/边缝/管线/平整度/地暖/防火/成本）
□ Step 5: 输出组装 — 按 §9 输出模板结构化输出
验证检查清单
每次执行 B2 验证时逐项确认：
□ 1. SRE 标准推理已完成（Step 0）
□ 2. 评价量匹配审查通过（Ln,w vs L'nT,w vs ΔL）
□ 3. 标准时效性审查通过（无废止标准引用）
□ 4. 撞击声估算已完成（Step 3，ACE 或简化估算）
□ 5. 隔声达标判断（D1）
□ 6. 标高可行性（D2）
□ 7. 承载安全评估（D3，如适用）
□ 8. 声桥风险评估（D4，浮筑/架空场景）
□ 9. 边缝处理方案（D5，浮筑场景）
□ 10. 管线兼容性（D6，如适用）
□ 11. 完成面标高推算（D2 细化）
□ 12. 平整度评估（D7）
□ 13. 成本合理性（D10，如有预算约束）
□ 14. 风险提示与不确定性标注
□ 15. 结构化输出模板完整
What ships with it
5 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.
- 11d ago First seen · 474 lines · 114 tokens per session scan A 20e60d990ed9
prefab-floor-system is a skill published in the GitHub repository eiway112/prefab-interior-skills (4 stars, last pushed 9d ago), licensed MIT. It adds 114 tokens to every session and 8,616 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
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 $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
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.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.