By 2p1c
General-purpose COMSOL Multiphysics automation via the mph Python library and COMSOL Java API. Covers model creation, physics setup, meshing, studies, and result extraction for COMSOL 6.0–6.3
COMSOL Multiphysics automation skills — programmatic simulation via Python.
Version: 1.2.0
# Register this marketplace (one time)
/plugin marketplace add 2p1c/comsol_ai
# Install the COMSOL skill
/plugin install comsol@comsol-skills
| Skill | Description |
|---|---|
comsol | COMSOL model creation, physics setup, meshing, parametric/time-domain studies, and result extraction via mph + COMSOL Java API. Verified against COMSOL 6.2. |
mph, numpy, pandasskills/comsol/ # The skill
├── SKILL.md # Skill instructions
├── scripts/ # Simulation scripts
├── references/ # API reference, debugging log, examples
.claude-plugin/
└── marketplace.json # Plugin registry manifest
comsolbatch 求解模式:实时文本进度输出(替代无 GUI 的 mph solve)--build-only CLI 参数:构建后停止,方便在 COMSOL GUI 中检查--config CLI 参数:通过外部 JSON 文件覆盖默认配置study.set("plot", "on") 和 probesel="all" 求解进度设置SolverLog 在客户端 API 不可用问题 → 改用 comsolbatch 日志ModelUtil.showProgress(true) 崩溃(JVM 无 Swing toolkit).claude-plugin/marketplace.json)skill/ → skills/comsol/,符合官方规范assets/ 移至 scripts/compatibility、metadata 字段)Box/Ball 替代 BoxSelection/BallSelection)entitydim 必须传字符串类型("2" 而非 2)condition 含义(是实体包含类型,非坐标过滤)"r"(非 "radius").named() 替代 .set())Free BC 的 selection 不可编辑(默认自动管理)DomainPointProbe 不可用,改用 CutPoint3Ddensity、youngsmodulus 等,含短名 rho、E)debugging-log.md 自改进)Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub 2p1c/comsol-skills --plugin comsolCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,561 supported skills.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer