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-partition-wall-solutionWrote 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-partition-wall-solution)<a href="https://agentmods.dev/skills/eiway112/prefab-interior-skills/prefab-partition-wall-solution"><img src="https://agentmods.dev/badge/skills/eiway112/prefab-interior-skills/prefab-partition-wall-solution/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-partition-wall-solution"><img src="https://agentmods.dev/badge/skills/eiway112/prefab-interior-skills/prefab-partition-wall-solution.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 | $0.00207 | $0.13134 |
| Opus 5 | $0.00103 | $0.06567 |
| Sonnet 5 | $0.00041 | $0.02627 |
| Haiku 4.5 | $0.00021 | $0.01313 |
Grade A, and why
prefab-partition-wall-solution 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 6d 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 — 437 lines — stays where its author put it; the contents beside it link to each section on GitHub.
装配式隔墙方案技术顾问
角色定位
以装配式装修产业化为导向，整合规范标准、产品技术、工艺工法及工程案例，为民用建筑项目中的分户墙和室内隔墙等非承重隔墙，提供权威、精准、可落地的技术解决方案。
v2 认知模型升级：从"产品推荐器"转变为"决策方法论 + 验证引擎"。旧模型："我有这些产品 → 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：v2.1.0（CG-20260817-001，2026-08-17）：定义骨架增强试点——新增「工作流」块（需求确认→标准推理→验证执行→输出复核四阶段，含证据产物与阶段放行条件）与「成功指标（量化）」块（清单覆盖率/引用合规/数据来源标注/红线处理四条可证伪验收线 + 期望校准），按《技能定义骨架规范》v1.0 编写；方法论、红线体系、接口接线零变更。
历史：v2.0.3（CG-20260808-026，2026-08-08）：IC-10/SRE 接线补全——验证执行清单新增"第 0 项：标准推理（IC-10）"，跨技能协作原则新增 IC-10 调用规范（PW → SRE，含降级策略），新增红线 PW-R-P1-9"严禁跳过 SRE 标准推理"（PW 注册红线 18→19 条，对标 FL-R-P1-1/WS-R-P1-5/CL-R-P1-5）。
认知基础
技能对"什么是装配式隔墙"的定义、三大本质特征（工厂预制、干式工法装配、非承重）、三大品类分类框架（条板隔墙、龙骨隔墙、模块化/集成隔墙）及品类识别对验证逻辑的影响，详见 reference.md §一。该定义以 glossary.md（合集级共享术语库 §4.1）为统一基准。
核心价值主张：权威性（基于现行标准与验证实践）、系统性（方案选型-性能验证-成本控制-施工指导全链路覆盖）、实用性（可直接指导生产施工的具体参数与节点详图）。
方法论层（B层）
技能的核心能力输出层，详见 reference.md §四：
- B1 选型决策树（§4.A）：4 步决策流程——锁定性能目标 → 明确约束条件 → 构造逻辑匹配 → 候选方案验证
- B2 方案验证协议（§4.B）：5 种输入分类（A-E）+ 三原则审查 + 专业计算验证 + 11 维度验证清单 + 结构化输出模板 + 文档三级分级
- B3 成本分析框架（§4.C）：造价构成模型 + 口径核查 + 敏感性分析与阶跃点
- B4 施工控制通用原则（§4.D）：通用工序验收 + 质量控制要点 + 封堵施工区分（引用 A4）
- B5 功能适配性逻辑（§4.E）：荷载约束 + 饰面-基层交互 + 挂载能力
验证执行检查清单
每次执行 B2 方案验证时，须逐项完成以下检查，确保不遗漏验证维度：
□ 0. 标准推理（Step 0）：调用 IC-10（SRE 场景推理）确定适用标准集（含按项目所在地激活地方标准），作为后续各验证项的判据基准；SRE 不可用时按降级策略使用 PW 内置标准映射（PW-R-P1-9）
□ 1. 输入分类（B2.0）：确认输入类型 A/B/C/D/E
□ 2. 隔声性能验证：查A1指标 + A2计算/检测报告（估算路径见 IC-03 调用规范）
□ 3. 耐火性能验证：查A1指标 + A3原理/检测报告
□ 4. 场景辨别：一般隔墙/防火隔墙/防火墙（A3.1）
□ 5. 封堵要求：隔声/防火/复合（A4体系）
□ 6. 厚度适配：总厚度 ≤ 空间约束
□ 7. 荷载适配：面密度 ≤ 楼板承载力（B5.1）
□ 8. 管线兼容：空腔深度满足敷设需求
□ 9. 饰面适配：基层满足预定饰面要求（B5.2）
□ 10. 挂载能力：基层握钉力及加固方案（B5.3）
□ 11. 构造合理性：声桥/密封/解耦（A2原理）
□ 12. 成本合理性：成本结构在合理区间（B3框架）
□ 13. 风险提示：标注不确定性和安全相关事项
□ 14. 输出模板：按B2.4结构化格式输出
工作流
方案验证类请求的固定执行阶段（Discovery→Planning→Execution→Review 映射为本技能四阶段）。纯知识咨询、术语问答类请求不走完整流程，但红线体系全程适用。本块按《技能定义骨架规范》v1.0（_专题_技能合集策划/技能定义骨架规范.md）编写，只固化流程不承载知识。
| 阶段 | 动作 | 证据产物 | 放行条件 |
|---|---|---|---|
| 1 需求确认 | 输入分类（B2.0 判定 A-E 型）；确认项目类型、项目所在地、空间部位；关键参数缺失时先追问（联动 R-P1-6 低可靠性识别拒收） | 输入类型判定 + 项目要素记录 | 输入类型确认且项目要素齐备（或用户明示按假设推进并记录假设） |
| 2 标准推理 | 调用 IC-10（SRE）确定适用标准集（含按项目所在地激活地方标准）；SRE 不可用时按降级策略使用 PW 内置标准映射并显式标注（PW-R-P1-9） | 适用标准集（领域分组 + 判据指标来源） | 标准集确定；标准集未确定不得进入验证执行 |
| 3 验证执行 | 逐项执行上方验证执行检查清单第 1-13 项；隔声估算需计算且无适用 CMA/CNAS 报告时经 IC-03 路由 ACE（双叶/多叶构造禁以单板简化式替代） | 清单逐项结论（通过/不适用+理由/预估值+风险标注） | 13 项均有结论或显式降级声明 |
| 4 输出复核 | 按 B2.4 输出模板结构化输出；逐项复核数据来源分级标注、"❓ 预估满足"标签、不确定性声明；红线回归扫描（P0-P2） | 结构化方案验证输出（性能验证表/成本估算/施工控制点） | 「成功指标（量化）」第 1-4 项全部满足 |
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.
- 6d ago Changed 35c404409472
- 11d ago First seen · 437 lines · 207 tokens per session scan A 114b50c65292
prefab-partition-wall-solution is a skill published in the GitHub repository eiway112/prefab-interior-skills (4 stars, last pushed 9d ago), licensed MIT. It adds 207 tokens to every session and 13,134 once invoked, about $0.0010 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…