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-engineering-drawinggit 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-engineering-drawing)<a href="https://agentmods.dev/skills/wzyn20051216/solidworks-automation-skill/solidworks-engineering-drawing"><img src="https://agentmods.dev/badge/skills/wzyn20051216/solidworks-automation-skill/solidworks-engineering-drawing/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-engineering-drawing"><img src="https://agentmods.dev/badge/skills/wzyn20051216/solidworks-automation-skill/solidworks-engineering-drawing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.01141 |
| Opus 5 | $0.00029 | $0.00571 |
| Sonnet 5 | $0.00012 | $0.00228 |
| Haiku 4.5 | $0.00006 | $0.00114 |
Grade A, and why
solidworks-engineering-drawing 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 12d 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 工程图生成与审视
本子技能专注二维工程图。它依赖根技能 solidworks-automation 提供 SolidWorks COM
会话、模型、导出和通用几何证据；自身负责 DrawingSpec v1、工程图工作流和制造交付审视。
何时调用
- 生成零件工程图或装配工程图。
- 需要 GB/T 图框、第一角投影、尺寸链、孔表、BOM 或标题栏。
- 检查工程图视图重叠、尺寸文字、PDF 文字、标题栏侵入或交付证据。
- 钣金任务需要审视展开图证据时。
默认规则
standard=GB_T默认使用projection=first_angle。- GB/T + 第三角投影会被
DrawingSpec前置检查阻断。 - 所有孔、槽和接口必须有规格、数量和定位信息。
- 工程图交付必须导出 PDF，并将每个 COM 尺寸位置与最终 PDF 的矢量文字框一一关联；PDF 缺失、解析器缺失、关联不完整或文字碰撞都会阻断或要求复核。
- 本子技能不实现强化学习，也不暴露任意 Python/VBA 执行入口。
工作流
- 读取并校验
schemas/drawing_spec.schema.json。 - 运行根技能的 SolidWorks preflight 和能力探测。
- 选择图框，创建图纸页，回读图幅和投影法。
- 按执行器能力创建视图、尺寸、孔表和 BOM，并回读真实实体；不得静默忽略 DrawingSpec 字段。
- 保存
.slddrw，导出 PDF 和 BMP/PNG。 - 运行
drawing_review.py，生成机器证据和人工复核门禁。
能力边界
- 零件和装配工程图为 pilot：跨版本真机回归仍在持续；但在 PDF 尺寸文字框、视图边界、尺寸链、孔表和 BOM 证据全部通过时，工具会返回
pass，不会因 COM 缺少原生文字框而无条件降级。 - 通用 MCP 生成器当前只可靠执行空配置的
front/top/right三视图、显式且可容纳的比例、模型尺寸导入、注释和模板化 BOM。轴测、剖视、局部视图、指定 ID 尺寸、孔标注/孔表、标题栏业务字段和钣金专用选项必须在修改文档前返回DRAWING_SPEC_CAPABILITY_UNSUPPORTED，由专项脚本执行。 - 审查器按尺寸 ID/视图/种类/数值、孔规格/数量/位置、真实 BOM 类型/数据行/配置及标题栏字段回读做结构化核验；模板候选、任意表格或模糊子串不能作为通过证据。
professionalAnnotations可声明中心标记、中心线、孔标注、基准、GD&T、表面粗糙度和焊接符号。审查器只接受 SolidWorks 专用实体回读；普通 Note 文字不能替代。- 通用生成器已支持
centerMarks自动写入：每项必须声明id、标准视图、期望总数和targets（holes/fillets/slots），并通过GetFirstCenterMark2/GetNext实体回读。SW2026 真机确认新建工程图需首次保存后再插入；未保存状态下 API 可能返回True但实体暂不可回读，封装会保持失败。其余专业标注仍保持能力阻断。 - 跨版本真机矩阵使用
python tests/solidworks_drawing_version_matrix.py --years 2024 2025 2026。脚本只启动已注册的精确版本 ProgID，并核对实际回读年份；未安装版本记为unavailable，不得用默认 ProgID 的结果顶替。 - 钣金工程图只有在本机存在可靠展开图证据时继续；缺证据返回
blocked，不宣称无人值守完成。 - 完整 GD&T 语义求解不在本版本范围内，只检查要求是否存在并可追溯。
依赖根技能
优先复用：scripts/sw_connect.py、scripts/sw_session.py、scripts/sw_export.py、
scripts/sw_review.py、scripts/sw_document_data.py 和 scripts/sw_capability_probe.py。
What ships with it
10 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.
- manifest.yaml 617 B
- README.md 2.3 KB
- references/api-lookup.md 471 B
- references/drawing.md 848 B
- references/review.md 1.7 KB
- schemas/drawing_spec.schema.json 5.5 KB
- scripts/__init__.py 48 B runs code
- scripts/drawing_review.py 42 KB runs code
- scripts/drawing_spec.py 8.3 KB runs code
- scripts/drawing_workflow.py 87 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.
- 12d ago First seen · 51 lines · 58 tokens per session scan A 32c01cecc2f1
solidworks-engineering-drawing is a skill published in the GitHub repository wzyn20051216/solidworks-automation-skill (879 stars, last pushed 4d ago), licensed MIT. It adds 58 tokens to every session and 1,141 once invoked, about $0.0003 per session on Opus 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
design-drawing-svg-md
Use when converting vector PDF engineering drawings (steel-structure shop drawings, A0 drawings, linework-only PDFs without a text layer) into LLM-consumable dual-carrier records — semantic Markdown reading thread plus layered SVG geometry archive linked by shared IDs and crosswalk.
pencil-export
Export a Pencil (.pen) deck to PNG + PDF + PPTX + a self-contained HTML on WSL. PNG and PDF come from Pencil natively through the execute tool. PPTX defaults to an EDITABLE twin (identical look, native editable text, brand fonts embedded); the image-per-slide locked-look PPTX is opt-in via pptx-flat. The PPTX and…
xpager
Produce a 31C OnePager (xPager) using the locked corporate template. Three-page branded document - dark full-bleed cover with ODUN.ONE wordmark, capability page, and proof/contact page. Renders to PDF + HTML. Trigger when the user says "xPager", "x-pager", "onepager", "one-pager", "1-pager", "product one-pager"…
visual-inspector
A workflow for turning a PDF into one image per page so people or other tools can inspect its visual layout. It also produces a JSON report and can render selected pages or cropped regions for closer review.
aspicio-inspect-dxf
Use when the user shares, references, or asks questions about a DXF or PDF drawing (.dxf, .pdf) — what it contains, its layers, dimensions, size, units, or what it looks like. Requires the aspicio MCP server (describedxf / renderdxf, describepdf / renderpdf, describedoc / renderdoc). Covers choosing between structural…
minimax-pdf
Use this skill when visual quality and design identity matter for a PDF. CREATE (generate from scratch): "make a PDF", "generate a report", "write a proposal", "create a resume", "beautiful PDF", "professional document", "cover page", "polished PDF", "client-ready document". FILL (complete form fields): "fill in the…