Sentaurus Tcad
End-to-end Sentaurus TCAD simulation workflow skill. Use this whenever the user asks to create, repair, calibrate, run, diagnose, visualize, or document Sentaurus/SWB/SDE/SDevice/SVisual simulations; mentions TCAD, Sentaurus, SWB, swbpy2, gsub, SDE geometry, mesh, SDevice physics, Id-Vg/Id-Vd/BV/HeavyIon/SEB/TID/ESD, GaN HEMT, p-GaN HEMT, radiation effects, parameter sweeps, convergence failures, or asks for a literature-backed device simulation workflow. It enforces research-before-simulation, SWB-visible execution, gsub submission, result visualization, persistent reporting, and closed-loop
Install
npx skills add starlight-w/claude-sentaurus-skill --skill sentaurus-tcadgit clone --depth 1 https://github.com/starlight-w/claude-sentaurus-skill.git /tmp/claude-sentaurus-skill
mkdir -p ~/.claude/skills
cp -r /tmp/claude-sentaurus-skill/. ~/.claude/skills/sentaurus-tcadPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Sentaurus TCAD 全流程技能 本技能把 Sentaurus 仿真当作一个**科研工程闭环**,而不是“写 cmd 然后跑一下”。每次进入任务时,按下面顺序工作: ``` 问题定义 → 资料检索 → 本地文档/例子验证 → 建立/修改 SWB 项目 → SDE/SDevice/SVisual 实现 → gsub 提交 → 监控 → log/plt/tdr 分层诊断 → 可视化与报告 → 经验沉淀 → 下一轮迭代 ``` ## 0. 先确认环境与项目边界 1. 询问或自动识别:Sentaurus 版本、`STROOT/STRELEASE/STDB`、项目路径、目标器件、仿真类型、期望输出。 2. 在常见 Sentaurus 环境中,优先确认这些变量和路径: - TCAD root: `$STROOT` - TCAD Python: `$STROOT/tcad/$STRELEASE/linux64/bin/python3.11` - STDB: `$STDB/` - PDF manuals: `$STROOT/tcad/$STRELEASE/manuals/olh_sentaurus/pdf/` - Applications Library: `$STROOT/tcad/$STRELEASE/Applications_Library/` 3. 对外分享或在新机器上运行时,不要硬编码上述路径;先让用户提供 Sentaurus 安装目录和 STDB,或用 shell 检查 `swb/gsub/sdevice/svisual` 是否在 PATH 中。 4. **新设备首次运行必须先做 preflight**:确认 PATH、`STROOT/STRELEASE/STDB`、STDB 可写、license 可用、TCAD Python/`swbpy2`、`gsub` 队列、SVisual/display、manuals/examples。preflight 未通过时,不要写 deck、不要提交仿真、不要把环境错误当成物理模型问题修。详见 `references/new-device-preflight.md`。 5. 大任务必须先建立持久化计划文件:`task_plan.md`、`findings.md`、`progress.md`。复杂仿真没有计划文件就不要开始;不要覆盖已有无关计划文件。 ## 1. 不可违反的仿真执行规则 ### SWB 可见性是最高优先级 - 必须通过 SWB 项目树管理仿真:新项目用 `swbpy2` 创建,已有项目用 `swbpy2` 添加参数/实验路径。 - 默认使用 **traditional organization**:`Deck(project_path, False)`。Hierarchical 只有在确有必要时使用,因为跨节点引用更复杂。 - 必须用以下形式提交仿真: ```bash gsub -q local:default -e <纯数字节点号> <项目路径> ``` - `gsub` 会自动预处理,不需要先跑 `spp`。 - 禁止直接运行 `sdevice pp*_des.cmd` 来替代 gsub;那会绕过 `.sta/.job/gexec.cmd` 状态管理,SWB GUI 看不到结果。 - 禁止在树外创建孤立 `pp_*.cmd` 直接跑。需要新实验时,先把实验加入 SWB 树,再用 gsub 提交。 ### 并发与监控
Details
- Skill name
sentaurus-tcad- Repository
- starlight-w/claude-sentaurus-skill
- License
- MIT
- Repo updated
- 13 September 2026
FAQ
What does the Sentaurus Tcad skill do?
End-to-end Sentaurus TCAD simulation workflow skill. Use this whenever the user asks to create, repair, calibrate, run, diagnose, visualize, or document Sentaurus/SWB/SDE/SDevice/SVisual simulations; mentions TCAD, Sentaurus, SWB, swbpy2, gsub, SDE geometry, mesh, SDevice physics, Id-Vg/Id-Vd/BV/HeavyIon/SEB/TID/ESD, GaN HEMT, p-GaN HEMT, radiation effects, parameter sweeps, convergence failures, or asks for a literature-backed device simulation workflow. It enforces research-before-simulation, SWB-visible execution, gsub submission, result visualization, persistent reporting, and closed-loop
How do I install the Sentaurus Tcad skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add starlight-w/claude-sentaurus-skill --skill sentaurus-tcad. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Sentaurus Tcad popular?
It lives in starlight-w/claude-sentaurus-skill, which has 43 GitHub stars and 4 forks.
Related skills
Tufte Viz
66aparente/claude-skills
Ideate and critique data visualizations using Edward Tufte's principles from "The Visual Display of Quantitative Information." Use this skill when: (1) Designing new data visualizations or charts (2) Critiquing or improving existing visualizations (3) Reviewing dashboards or reports for graphical integrity (4) Deciding between visualization approaches (5) Reducing chartjunk or improving data-ink ratio (6) Planning small multiples or high-density displays Applies principles: data-ink ratio, chartjunk elimination, graphical integrity, lie factor, small multiples, and data density.
Cloudwatch Dashboards
43aws-samples/sample-kiro-cli-multiagent-development
AWS CloudWatch dashboard observability patterns including dashboard hierarchy, widget selection, CDK implementation, metric math, alarms, and cross-account monitoring. Use when creating dashboards, setting up observability, or instrumenting workloads with CloudWatch.
Ielts Dashboard
63liqianiiii/Awesome-ielts-claude-skills
启动本地 IELTS Dashboard。React + Vite,浏览器查看备考数据可视化。 触发方式:/ielts-dashboard、「打开仪表盘」「看看进度」「dashboard」
Greenlight Vibe
43wpsoul/greenlight-vibe
Generate or edit design for WordPress Gutenberg blocks using Greenshift/GreenLight plugin. Convert any data to wordpress blocks or convert greenshift blocks back to html + css + js. Use when user asks to create design with Greenshift or Greenlight blocks for wordpress site, convert anything to wordpress blocks or build charts in content. Triggers on keywords: wordpress, gutenberg, greenshift, greenlight, convert to wordpress, convert greenshift blocks to vanilla html, build chart.
Decision Toolkit
70alexdcd/Mafia-Claude-Skills
Generate structured decision-making tools — step-by-step guides, bias checkers, scenario explorers, and interactive dashboards. Use when facing significant choices requiring systematic analysis. Supports multiple cognitive styles and output formats.
Gtm Pipeline:contact Filter
77keinsaasforever/gtm-pipeline-skills
Classify and filter contacts from people-search output BEFORE enrichment. Rejects non-ICP contacts and ranks the rest using job tier, industry tier, location tier, company size, and ICP keyword scoring. Saves enrichment credits by only passing qualified contacts downstream. Input: contacts_found.csv. Output: contacts_filtered.csv. Also triggers on "filter contacts", "ICP filter", "rank contacts".
Browse the most popular Claude skills, all data & analytics skills, or write your own with the skills generator.