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-searchgit 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-search)<a href="https://agentmods.dev/skills/k-13robot/hfss_mcp/hfss-search"><img src="https://agentmods.dev/badge/skills/k-13robot/hfss_mcp/hfss-search/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-search"><img src="https://agentmods.dev/badge/skills/k-13robot/hfss_mcp/hfss-search.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 | $0.00125 | $0.03374 |
| Opus 5.5 | $0.00050 | $0.01350 |
| Sonnet 5.5 | $0.00025 | $0.00675 |
| Haiku 4.5 | $0.00013 | $0.00337 |
Grade A, and why
hfss-search 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 2d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
天线文献检索与提炼
补的是 hfss-design 的 flow/design-loop.md 第 1 步那个死胡同:卡片库没有匹配拓扑时怎么办。
本 skill 的交付物是**「结构理解表 + 起手尺寸」交用户确认**,不是卡片 —— 卡片是整条流程走完、
仿真达标、用户点头之后才录的(见 §5)。
0. 先查本地库 —— 硬门槛,不许跳
任何情况下先调 search_designs(传 frequency_ghz / polarization / topology / min_gain_dbi),
命中就用 read_design_card 取正文,直接走 hfss-design 的 flow/design-loop.md 第 2 步缩放建模,不要联网。
只有确认库里没有可用拓扑,才进本 skill 后续步骤。
理由:库里的卡是自己验证过的,可信度和可用性都高于任何论文;联网检索慢且贵。
1. 指标 → 拓扑候选 → 检索式
先把用户指标翻成拓扑候选,再翻成英文检索词。中文检索天线文献基本无效,检索式一律用英文。
指标 → 拓扑的常用映射(候选,不是唯一解):
| 指标特征 | 优先考虑的拓扑 | 检索关键词 |
|---|---|---|
| 窄带、低剖面、低成本 | 矩形/圆形微带贴片 | microstrip patch antenna |
| 圆极化(单馈) | 切角/开槽贴片 | single-fed circularly polarized patch, truncated corner |
| 圆极化(宽轴比带宽) | 双馈+90°电桥、序列旋转 | dual-fed CP antenna, sequential rotation |
| 宽带(>30%) | 磁电偶极子、E 型/U 型开槽贴片、堆叠贴片 | magneto-electric dipole, E-shaped patch, stacked patch |
| 高增益(单元) | 缝隙耦合叠层、SIW、介质谐振 | aperture-coupled stacked, SIW antenna, dielectric resonator antenna |
| 高增益(阵列) | 微带阵 + 馈电网络 | microstrip array, series-fed, corporate feed |
| 宽波束/半球覆盖 | 单极子、PIFA、缝隙 | monopole, PIFA, slot antenna |
| 毫米波 | SIW、贴片阵、透镜 | mmWave antenna, substrate integrated waveguide |
| 双频/多频 | 开槽、寄生单元、分形 | dual-band patch, parasitic element |
检索式模板(按需组合,别一次堆太多词,先宽后窄):
<拓扑关键词> AND (<频段词>) AND (<性能约束>)
如: "magneto-electric dipole" AND "5G" AND "wideband"
"circularly polarized patch" AND "axial ratio bandwidth" AND "single feed"
频段词用应用名往往比数字好使(sub-6 GHz / 5G n78 / WLAN 2.4 GHz / Ka-band),
因为论文标题里写应用名的比写具体频率的多。
2. 检索源与分工
我能自主做的(有联网工具时):
WebSearch找综述和公开可读的论文,快速摸清这类天线有哪些主流做法- IEEE Xplore 的检索结果页通常可读(标题/摘要/DOI),据此出候选清单
- arXiv(eess.SP 有部分天线文章)、MDPI 系期刊、开放获取论文可直接读全文
必须用户做的:下载 IEEE / 付费期刊的 PDF。我的网页抓取不带用户的登录态和学校 IP, 拿回来只会是登录页。所以流程是:我给候选清单和链接 → 用户下载 → 把 PDF 路径告诉我。
别做批量下载。 出版商对高频抓取有风控,触发会封整个机构的 IP 段,代价由全校承担。 每轮候选控制在 3
5 篇,选定 12 篇精读即可。
没有联网工具时(换了 MCP 客户端 / 无网):直接请用户提供论文 PDF 或粘贴关键段落, 跳到 §3 精读。本 skill 的提炼纪律不依赖联网。
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.
- 2d ago Changed f78f7db83cdd
- 1mo ago First seen · 155 lines · 125 tokens per session scan A 4cd1ad2d100d
hfss-search is a skill published in the GitHub repository K-13ROBOT/HFSS_MCP (8 stars, last pushed 2d ago), licensed MIT. It adds 125 tokens to every session and 3,374 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 2026-09-09.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Builds and analyzes phylogenetic trees using MAFFT multiple sequence alignment, IQ-TREE maximum likelihood with ModelFinder and branch support, and FastTree approximate inference. Uses ETE3 for tree summaries and visualization. Applies to homologous nucleotide or protein sequences, microbial gene trees, protein…
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
presenting-conference-talks
Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.