SolidWorks Automation Skill is a Python toolkit that connects coding-agent tools to the SolidWorks API for automating CAD work. Engineers use it with SolidWorks and, for some workflows, AutoCAD through a skill package, MCP server, or desktop application. The catalogue add-ons provide workflows that operate this toolkit.
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 wzyn20051216/solidworks-automation-skill --skill solidworks-vibecadgit clone --depth 1 https://github.com/wzyn20051216/solidworks-automation-skillWrote 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/wzyn20051216/solidworks-automation-skill/solidworks-vibecad)<a href="https://agentmods.dev/skills/wzyn20051216/solidworks-automation-skill/solidworks-vibecad"><img src="https://agentmods.dev/badge/skills/wzyn20051216/solidworks-automation-skill/solidworks-vibecad/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/wzyn20051216/solidworks-automation-skill/solidworks-vibecad"><img src="https://agentmods.dev/badge/skills/wzyn20051216/solidworks-automation-skill/solidworks-vibecad.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 58 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 64 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00096 | $0.01018 |
| Opus 5.5 | $0.00038 | $0.00407 |
| Sonnet 5.5 | $0.00019 | $0.00204 |
| Haiku 4.5 | $0.00010 | $0.00102 |
Grade A, and why
solidworks-vibecad 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 1mo 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.
What it actually says
SolidWorks VibeCAD
核心定位
本子技能把“自然语言想法”转成可执行、可审查的 SolidWorks 参数化设计计划。它不是临时生成 VBA 宏,而是把重复机械设计固化成:
行业知识库 + 参数 schema + 提示词模板 + 稳定 API 封装 + 自动审查
LLM 负责理解意图和补齐参数;SolidWorks API 负责确定性执行;知识库负责工程正确性;审查链路负责防止“看起来成功但几何错误”。
适用任务
- 用户用自然语言描述零件,希望生成参数化建模计划。
- 需要把高频机械件模板化,如 CNC 安装座、连接块、L 型支架、底板、孔阵列。
- 需要沉淀行业知识库,如攻丝底孔、通孔、沉孔、倒角、圆角、最小壁厚。
- 需要给 SolidWorks 自动化执行器提供 JSON 计划和风险门禁。
- 需要把成功案例变成可复用模板,而不是每次重新写宏。
工作流
- 读取用户需求,确认零件族、工艺、材料、输出格式和约束。
- 参考
knowledge/manufacturing_rules.yaml补齐保守默认值。 - 用
prompts/solidworks_parametric_planner.md约束 LLM 输出结构化计划。 - 用
schemas/design_plan.schema.json校验计划字段。 - 运行
scripts/plan_from_brief.py生成本地规则计划,或把 LLM 输出保存为同 schema JSON。 - 运行
scripts/sw_execution_outline.py生成 SolidWorks 执行摘要。 - 后续执行时交给父技能
scripts/sw_session.py、scripts/sw_part.py、scripts/sw_review.py和相关专项子技能。
快速命令
py subskills\solidworks-vibecad\scripts\plan_from_brief.py `
--brief-file subskills\solidworks-vibecad\examples\motor_mount_brief.txt `
--out subskills\solidworks-vibecad\examples\motor_mount_plan.json
py subskills\solidworks-vibecad\scripts\sw_execution_outline.py `
--plan subskills\solidworks-vibecad\examples\motor_mount_plan.json `
--out subskills\solidworks-vibecad\examples\motor_mount_execution.md
与父技能的关系
solidworks-automation:连接 SolidWorks、建模、导出、审查的主技能。solidworks-vibecad:自然语言 -> 参数化设计计划。solidworks-fillet-chamfer-cnc:复杂 CNC 圆角/倒角执行经验。solidworks-threaded-holes:螺纹孔、攻丝底孔和螺纹表达执行经验。
当计划中出现圆角/倒角密集的 CNC 件,继续读取:
subskills/solidworks-fillet-chamfer-cnc/SKILL.md
当计划中出现 M3/M4/M5/M6/M8 螺纹孔,继续读取:
subskills/solidworks-threaded-holes/SKILL.md
少走弯路
- 不要让 LLM 直接输出 SolidWorks 长参数 COM 调用。
- 不要把计划 JSON 当作几何成功;必须经过真实 SolidWorks 执行和
sw_review审查。 - 不确定参数可以用保守默认值,但必须写入
assumptions。 - 螺丝固定孔要区分通孔、沉孔、攻丝孔;不能把
M5 螺丝固定孔默认误建成 M5 攻丝孔。 - 输出计划必须包含
review_plan,否则不能进入自动建模。
当前状态
当前阶段已实现需求文本到设计计划和执行摘要的最小闭环。真实 SolidWorks 执行器应作为下一阶段接入父技能稳定 API。
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/motor_mount_brief.txt 283 B
- examples/motor_mount_execution.md 1.6 KB
- examples/motor_mount_plan.json 5.1 KB
- knowledge/manufacturing_rules.yaml 1.7 KB
- manifest.yaml 668 B
- prompts/solidworks_parametric_planner.md 1.7 KB
- README.md 2.7 KB
- references/vibecad-roadmap.md 2.3 KB
- schemas/design_plan.schema.json 2.3 KB
- scripts/plan_from_brief.py 9.7 KB runs code
- scripts/sw_execution_outline.py 4.2 KB runs code
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.
- 1mo ago First seen · 78 lines · 96 tokens per session scan A c6c8df937f7b
solidworks-vibecad is a skill published in the GitHub repository wzyn20051216/solidworks-automation-skill (1,541 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 1,018 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
ifoxcad
Use when writing AutoCAD / ZWCAD / GstarCAD plugins in C# with IFoxCAD (NuGet IFox.CAD.ACAD 0.9.12) — DBTrans transaction wrapper, CurrentSpace.AddEntity, LayerTable.AddOrChange, block attributes, SSGet, EditorEx prompts, multi-CAD GlobalUsings aliases. Also for "eNotInDatabase" on an entity Id, entities vanishing…
solvespace
Use when doing lightweight parametric 2D/3D CAD in SolveSpace 3.3 — constraint sketching, linkage/mechanism checks, section and 2D views, STL for printing, or driving the solver from solvespace-cli / the PyPI slvs package in CI; also when sketch lines turn red (over-constrained) or blue (under-constrained), a…
qcad
Use when editing or batch-converting DXF/DWG drawings with QCAD 3.33 — RAddObjectsOperation scripting, dwginfo/dwg2pdf/dwg2svg console tools, or version conversion through qcad -no-gui -autostart SaveAs.js -filter; also when dwg2pdf/dwg2svg are missing because they ship only with QCAD Professional, when a PDF export…
autocad-mcp-premium
Use for any AutoCAD MCP Pro work whose result someone will rely on - a part drawn from a dimensioned source, an edit to an existing drawing, a P&ID, a foreign DWG/DXF to read, a plan, a takeoff, or a delivery. Teaches the measured workflow (requirements -> geometry -> verified on the CAD -> saved -> reopened ->…
fluidcad-assembly
Building multi-part models in FluidCAD: assemblies, part files, inserting and mating parts, connectors, exposed geometry, part parameters, sub-assemblies, replicated instances, STEP parts, project units, and assembly export. Use this skill whenever the user wants an assembly, a mechanism, a hinge, a slider, several…
fy_layout
Use when writing C# plugins for the FeiYang LightCAD/LightBIM platform (construction site layout) — ILcPlugin registration, ElementType with fixed GUID, [CommandClass]/[CommandMethod] commands, TabItem ribbon menus, 2D Action plus Shape/Solid Provider pairs for fence, lawn, foundation pit, road, prefab house. Also for…