Skills Plugins MCP Prompt Model 博客 我的中心
开发编程 #automation #api #ai

lumerical-fdtd

Use when connecting Codex to Ansys Lumerical FDTD, probing lumapi or fdtd-solutions.exe, normalizing FDTD solver environments, running LSF CLI sentinels, scripting FDTD object creation, reading monitor or Qanalysis results, handling sampled materials, or repairing FDTD automation failures.

DeepseekModel 官方收录技能 质量 良好 · 64 v1.0.0

获取

https://deepseekmodel.com/api/download.php?id=wfy-op-codex-for-comsol-lumerical-lumerical-fdtd-skill-md&format=skill
下载 .skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用
.skill 文件中 system_prompt 字段的实际内容。
name lumerical-fdtd description Use when connecting Codex to Ansys Lumerical FDTD, probing lumapi or fdtd-solutions.exe, normalizing FDTD solver environments, running LSF CLI sentinels, scripting FDTD object creation, reading monitor or Qanalysis results, handling sampled materials, or repairing FDTD automation failures. Lumerical FDTD Overview Use this skill to operate Ansys Lumerical FDTD through local Python API sessions or the fdtd-solutions.exe LSF command-line fallback. Keep the scope to solver connection, environment setup, object creation, monitor/source/analysis scripting, result extraction, material data handling, and failure repair. Workflow Detect the operating system first: On Windows PowerShell, run the Python probe directly with py -3 or a chosen Python. On Git Bash for Windows, use scripts/probe_lumerical.sh ; it detects MINGW/MSYS/CYGWIN and chooses py -3 when available. On Linux, use scripts/probe_lumerical.sh ; it chooses python3 and searches Linux FDTD install roots. Decide whether to use Python API or CLI LSF: Prefer Python API when lumapi imports and an FDTD session starts. Use CLI LSF when Python API startup is blocked but fdtd-solutions.exe can run scripts. Load only the needed reference: FDTD Python API, LSF, object creation, monitors, Qanalysis, data extraction, far-field projection, or materials: references/lumerical-fdtd-automation.md . Example profile structure: references/solver-profiles.json . Probe before real work unless the same profile already passed in the current session. Normalize the local solver environment before launching binaries. Run the smallest viable operation first: import check, executable check, session start, or CLI sentinel. Store raw stdout/stderr, generated scripts, result files, and probe JSON near the caller's job artifacts, not inside this skill. If a solver call fails, classify the signature, propose the smallest patch, retry once when safe, then report the exact command and artifacts. Quick Commands $skill = "C:\path\to\lumerical-fdtd" $out = ".\solver_probe_out\lumerical" py -3 "$skill\scripts\probe_lumerical.py" --dry-run --out-dir "$out" py -3 "$skill\scripts\probe_lumerical.py" --deep --out-dir "$out" py -3 "$skill\scripts\probe_lumerical.py" --cli --deep --out-dir "$out-cli" If py -3 is not the right interpreter, use a user-selected Python environment: conda run -n <env> python "$skill\scripts\probe_lumerical.py" --dry-run --out-dir "$out" Git Bash or Linux: skill= "/path/to/lumerical-fdtd" out= "./solver_probe_out/lumerical" bash " $skill /scripts/probe_lumerical.sh" --dry-run --out-dir " $out " bash " $skill /scripts/probe_lumerical.sh" --deep --out-dir " $out " bash " $skill /scripts/probe_lumerical.sh" --cli --deep --out-dir " $out -cli" Defaults Prefer lumapi.FDTD() after adding the local api/python directory to sys.path . Set ANSYSLMD_LICENSE_FILE when session startup fails with license/session errors. Prepend the FDTD bin and licensingclient/winx64 directories to PATH . Keep fdtd-solutions.exe -run <script.lsf> as a CLI fallback. Use .txt as the safe LSF sentinel/export extension, then convert to JSON in Python if needed. Common Mistakes Do not edit files inside the solver installation directory. Do not assume a normal python command exists on Windows; prefer the discovered or user-specified Python. Do not trust old solver syntax without a local probe. Do not treat a solver exit code as enough; verify the expected sentinel, monitor data, or exported file exists. Do not add unrelated solver-family guidance to this FDTD-only skill.
Agent 识别该技能的关键词,点击任意一个即可复制。

该技能未提供触发词。

下载的 .skill 包内含以下字段。
字段 说明
format格式标识(skill/v1)
skill_id技能唯一 ID
name技能名称
version版本号
description技能描述
category所属分类(数组)
trigger_words触发词列表
tags标签列表
source来源标识
source_url来源链接(本页地址)
exported_at导出时间(每次下载生成)
system_prompt系统提示词正文
model_config模型参数:provider / model / temperature / max_tokens / top_p
examples示例
install_guide各平台导入说明(Coze / Dify / Claude / 自定义框架)
同一份技能可按不同平台格式导出。
.skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用 下载
.skillpro 增强格式,额外含脚本 / 工具 / 依赖 / 钩子占位 下载
.json 纯 JSON 导出,只含 system_prompt 与模型参数 下载
Coze 带 frontmatter 的 Markdown,Coze 平台导入用 下载
Dify Dify DSL,创建应用后直接导入 下载

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。