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 K-13ROBOT/HFSS_MCP --skill hfss-stackupgit clone --depth 1 https://github.com/K-13ROBOT/HFSS_MCPWrote 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/k-13robot/hfss_mcp/hfss-stackup)<a href="https://agentmods.dev/skills/k-13robot/hfss_mcp/hfss-stackup"><img src="https://agentmods.dev/badge/skills/k-13robot/hfss_mcp/hfss-stackup/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/k-13robot/hfss_mcp/hfss-stackup"><img src="https://agentmods.dev/badge/skills/k-13robot/hfss_mcp/hfss-stackup.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 | $0.00161 | $0.03995 |
| Opus 5.5 | $0.00064 | $0.01598 |
| Sonnet 5.5 | $0.00032 | $0.00799 |
| Haiku 4.5 | $0.00016 | $0.00400 |
Grade A, and why
hfss-stackup 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 yesterday.
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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PCB 叠层表 → HFSS 多层板(板级/工艺,跨天线类型)
何时读:用户丢来一份板厂叠层表(StackUp Report,xlsx/csv),要求在 HFSS 里建出这块板—— 不管上面最后放的是天线、走线还是什么都不放。建天线时用户指定了真实生产叠层,也读这篇。
核心难点不在 HFSS 操作,在读懂叠层表:同一份报告里藏着好几条不成文的行业约定, 读错一条整块板厚度就错,而且错得很隐蔽(层数、层序看着都对)。
流程:dump 表格 → 按规则解析 → 厚度自校验 → 出层表让用户确认 → 建模 → bbox 自检 → setup。
与 hfss-design 的 SKILL.md §3.5 的关系:那边是文献复现时自己编层叠的约定(层少、自己定厚度);
本篇是厂商给定叠层的还原(层多、厚度不可改、必须和总厚对上)。z 约定一致(底面 z=0,+z 向上)。
1. Dump 原始表格(别用 Read 直接看 xlsx)
xlsx 是二进制,Read 读不出来。一次性把整张表打成文本再自己判读:
python -c "
import openpyxl
wb=openpyxl.load_workbook(r'<路径>',data_only=True)
ws=wb[wb.sheetnames[0]]
for r in ws.iter_rows(max_row=ws.max_row,max_col=ws.max_column):
print(r[0].row,'|'.join('' if c.value is None else str(c.value) for c in r))
"
data_only=True必须加,否则公式单元格返回公式字符串而不是值。- 顺手 dump 一次
ws.merged_cells.ranges:是不是合并单元格,决定了空白格怎么解释(见 §2.4)。 - 表头行不一定在第 1 行,前面常有 Job Name / Finish Board Thickness 等元信息行。
Finish Board Thickness是最重要的一行——它是你后面自校验的标尺,先抄下来。
不要写解析脚本当交付物。 dump 完你自己按下面规则读、自己算 z,规则和判断留在对话里。 脚本会把"这份表长这样"写死,换一家板厂就废;你的判读能力才是可迁移的。
2. 解析规则(踩过的坑都在这)
典型列:Layer Index | Stackup Buildup | PP Name And RC | Dielectric Thickness(mm) | Finish Cu Thk(oz) | Material Family | Copper Rate(%)
2.1 行的两种类型看第一列
- 第一列是
L<n>/D<n>→ 铜层行,厚度在Finish Cu Thk列(oz)。 - 第一列是
Core或空白 → 介质行,厚度在Dielectric Thickness列(mm)。
行序就是层序,表格从上到下 = 板子从顶到底。
2.2 D<n> 是"占号不占铜"的层 —— 必须跳过
D14、D16 这种行,Stackup Buildup 和 Finish Cu Thk 全空。它是保留的层号但整层没有铜
(设计上留了序号,实际全蚀刻掉)。建模时不要为它建实体,厚度按 0 计。
判据:L 开头且 Cu 列非空 = 有铜;D 开头或 Cu 列空 = 无铜。
⚠️ 直接影响层数:一块"L23"的板,真实铜层数 = 23 − D 层数。别照着最大层号建 23 层铜。
2.3 oz → mm,以及 "+ Plating"
1 oz = 35 µm = 0.035 mm,按倍数线性换算(0.5oz=17.5µm、2oz=70µm)。0.5oz + Plating= 基铜 + 电镀铜。电镀增量表里从来不给,典型 ~18–20 µm。 取一个待定值T_PLATE,用 §3 的总厚校验反解它——校验能对上,说明取对了。
2.4 连续多行同名 PP:厚度是"这一组的总厚",不是每片
最容易错的一条。经常看到:
|PP|PP(1035)RC76|0.108||SJ7036N|
|PP|PP(1035)RC76|||SJ7036N| <- 厚度空白
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.
- yesterday Changed 17700407d765
- 2d ago Changed 7e5ddec29167
- 1mo ago First seen · 223 lines · 161 tokens per session scan A 0d4bf32b0eff
hfss-stackup is a skill published in the GitHub repository K-13ROBOT/HFSS_MCP (8 stars, last pushed 2d ago), licensed MIT. It adds 161 tokens to every session and 3,995 once invoked, about $0.0006 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 2026-09-09.
Other skills, from other repositories
neuroskill-bci
Use live BCI cognitive and mood state from NeuroSkill.
ruview-applications
Run RuView sensing applications — presence/occupancy, breathing & heart rate, activity & fall detection, 17-keypoint pose estimation (WiFlow), sleep monitoring & apnea screening, environment mapping, Mass Casualty Assessment (MAT), and the 3D point-cloud fusion demo. Use when someone wants to actually do something…
lab-hardware-cad
Designs custom laboratory hardware as parametric build123d models and exports fabrication artifacts as STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a…
pylabrobot
Develops and reviews PyLabRobot lab-automation resources, liquid-handling plans, offline simulations, and supported-device integrations. Supports PyLabRobot protocols and API questions; keep physical execution behind an explicit operator safety gate.
pybamm
Simulates lithium-ion battery charge, discharge and rest experiments with PyBaMM, records parameter-set provenance, checks mesh and solver sensitivity, and compares predicted voltage curves with measured cycling data. Use for SPM or DFN electrochemical battery modeling, C-rate protocols, voltage cutoffs, parameter…
calibrate-room
Run the ADR-151 per-room calibration pipeline — baseline → enroll → extract → train → a bank of small specialists (presence/posture/breathing/heartbeat/restlessness/anomaly).