Skills Plugins MCP Prompt Model 博客 我的中心

ltspice

Progressive-disclosure workflow for LTSpice / PyLTSpice circuit simulation. Use whenever the user wants to create a netlist, run a SPICE transient or AC simulation, inspect traces, or debug LTSpice convergence through PowerMCP — even when they just say "simulate this circuit", "why won't this converge", or "plot the output". Exposes session creation and batch simulation before plotting or GUI steps. Reach for this instead of answering LTSpice questions unaided.

DeepseekModel Curated skill Quality Excellent · 78 v1.0.0

Get

https://deepseekmodel.com/api/download.php?id=power-agent-powerskills-powerskills-tool-skills-ltspice-skill-md&format=skill
Download .skill Standard format with system_prompt and model_config, ready for any agent framework
The actual content of the system_prompt field in the .skill file.
name ltspice description Progressive-disclosure workflow for LTSpice / PyLTSpice circuit simulation. Use whenever the user wants to create a netlist, run a SPICE transient or AC simulation, inspect traces, or debug LTSpice convergence through PowerMCP — even when they just say "simulate this circuit", "why won't this converge", or "plot the output". Exposes session creation and batch simulation before plotting or GUI steps. Reach for this instead of answering LTSpice questions unaided. LTSpice workflow Start with a runnable netlist and a clean batch simulation. Use plotting and GUI steps only after the run succeeds. Default tool ladder create_rc_transient_netlist(...) for a minimal example, or create_simulation_session(netlist_text) for a real case. run_simulation(netlist_path, session_dir) to generate the raw and log files. read_simulation_log(log_file_path) if the run fails or looks suspicious. list_available_traces(raw_file_path) before requesting plots. plot_specific_traces(raw_file_path, session_dir, trace_names) for focused waveform review. view_netlist_in_ltspice(netlist_path) only when the GUI is actually needed. Working rules Do not ask for broad plotting until the log is clean and the available traces are known. Simplify the netlist and shorten the run before tuning tolerances. Use a minimal reproducible circuit to debug startup or convergence issues. Deliver The netlist used and whether the batch run succeeded. The traces inspected. The likely root cause if the simulation misbehaved.
Keywords that activate this skill. Click one to copy it.

This skill does not provide trigger words.

The downloaded .skill package contains the following fields.
Field Description
formatFormat tag (skill/v1)
skill_idUnique skill ID
nameSkill name
versionVersion
descriptionDescription
categoryCategories (array)
trigger_wordsTrigger words
tagsTags
sourceSource
source_urlSource URL (this page)
exported_atExported at (set per download)
system_promptSystem prompt body
model_configModel config: provider / model / temperature / max_tokens / top_p
examplesExamples
install_guideImport guide for Coze / Dify / Claude / custom frameworks
The same skill can be exported in different platform formats.
.skill Standard format with system_prompt and model_config, ready for any agent framework Download
.skillpro Enhanced format with scripts, tools, dependencies and hooks Download
.json Plain JSON export with system_prompt and model parameters only Download
Coze Markdown with frontmatter, for Coze platform import Download
Dify Dify DSL, import directly after creating an app Download

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。