Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/znlgis/opengis-skillsnpx agentmods add skills/znlgis/opengis-skills/design-drawing-svg-mdWrote 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/znlgis/opengis-skills/design-drawing-svg-md)<a href="https://agentmods.dev/skills/znlgis/opengis-skills/design-drawing-svg-md"><img src="https://agentmods.dev/badge/skills/znlgis/opengis-skills/design-drawing-svg-md/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/znlgis/opengis-skills/design-drawing-svg-md"><img src="https://agentmods.dev/badge/skills/znlgis/opengis-skills/design-drawing-svg-md.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 | $0.00109 | $0.08047 |
| Opus 5.5 | $0.00044 | $0.03219 |
| Sonnet 5.5 | $0.00022 | $0.01609 |
| Haiku 4.5 | $0.00011 | $0.00805 |
Grade A, and why
design-drawing-svg-md 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
技能定位： 设计图 SVG+MD 双载体记录方法论——把"会画不懂"的矢量 PDF 工程图，转化为大模型能准确理解、指认与复刻的交付物。
项目地址： 无上游项目仓库——本技能为内部方法论，正文与配套脚本、参考文档均位于本仓库
cad/design-drawing-svg-md/。许可证： MIT——本技能为仓库自有方法技能，随仓库以 MIT 分发（见 LICENSE）。
方法来源： 一套钢结构施工图数字化执行方案的固化与泛化；文中数字为示例值或多图实测值，执行时以实际图纸实测为准。
适用输入： 矢量线画 + 无文字层的 PDF 工程图（彩色分层或单色均可）。
包管理器：
pip install pymupdf numpy scipy pillow（PyMuPDF 2.0、2026-10-19；脚本已按新包名import pymupdf，不再使用旧的import fitz别名，截至 2026-10）依赖版本： Python 3.10+（脚本使用
str | None等 3.10 语法）＋ PyMuPDF ＋ NumPy ＋ SciPy ＋ Pillow；实际运行版本由07_validate.py在测量当时写入validate.json，报告读回而非另行探测，保证与交付物同源。脚本资产： 本仓库
scripts/目录附带可直接复跑的泛化脚本——共用库 scripts/common.py、入口配置 scripts/config.example.json、十一阶段脚本01_extract.py…09_verify_deliverables.py（执行顺序与门禁见 reference/pipeline.md）。
概述
MD 是"大模型阅读主线"，SVG 是"高精度几何档案 + 按需切片源"，两者用统一 ID 体系互联，用校验闭环保证一致。
何时使用
- 需要让大模型/Agent 理解一份工程图纸（几何、尺寸、语义、工艺、管理信息）
- 源图为 PDF，且是矢量线画、无文字层（尺寸数字只是 glyph 轮廓路径，直接渲染"会画不会读"）
- 需要对图纸做问答、复刻重绘、改图、核量、生成 BOM 等下游任务
- 图纸会换版（R00→R01），需要可 diff、可追溯的数字化档案
何时不使用
- 源图已有文字层且无需精确几何 → 直接 PDF 文本提取即可
- 只需一张渲染图给人看，无下游智能任务 → 不必建双载体
- 栅格扫描件 → 本技能不覆盖矢量化（OCR/矢量化另案处理）
适用对象
A0 钢结构施工图（无文字层的矢量线画）为典型用例；任何"矢量线画 + 无文字层"的 PDF 工程图均可套用。
环境准备
# Python 3.10+
pip install pymupdf numpy scipy pillow
# 配置：从样例复制后按本机改路径与图层口径
cd scripts
cp config.example.json config.json # 或运行时 --config /path/to/config.json
common.py 的配置解析顺序：命令行 --config <path> / --config=<path> 优先，否则回退脚本同目录的 config.json；两者都找不到时报错退出并提示。config.json 覆盖模块级常量（PDF 目录、页面尺寸与旋转、图号前缀、颜色→层映射、OCG 名单、字形阈值、字体路径），因此同一套脚本可换图复用而无需改代码。
需要按本机改的关键项：
| 配置项 | 说明 |
|---|---|
paths.pdf_dir / paths.out |
源 PDF 目录与输出根目录 |
sheets |
图号列表（含版本后缀，如 … R00），也是命令行传的图号 |
page.w_pt/h_pt/rotation |
页面尺寸与回正方向，A0 竖放为 ccw90、pt_per_mm=2.83465 |
drawing_no_prefixes |
图号前缀，用于从标题栏文本中识别本图 |
layering.color_layer / ocg_* |
颜色兜底映射与 OCG 语义名单，换企业模板时必改 |
fonts.cjk |
中文字体绝对路径，示例值为 C:/Windows/Fonts/simhei.ttf，Linux/macOS 须换成本机字体 |
What ships with it
17 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.
- reference/md-spec.md 8.1 KB
- reference/pipeline.md 19 KB
- reference/svg-spec.md 9.4 KB
- scripts/01_extract.py 8.2 KB runs code
- scripts/02_cluster_views.py 17 KB runs code
- scripts/03_render_regions.py 21 KB runs code
- scripts/03b_text_recover.py 23 KB runs code
- scripts/03c_glyph_solve.py 35 KB runs code
- scripts/03d_vision_read.py 34 KB runs code
- scripts/04_build_md.py 30 KB runs code
- scripts/05_crosswalk.py 28 KB runs code
- scripts/06_enhance_svg.py 16 KB runs code
- scripts/07_validate.py 14 KB runs code
- scripts/08_qa.py 18 KB runs code
- scripts/09_verify_deliverables.py 91 KB runs code
- scripts/common.py 41 KB runs code
- scripts/config.example.json 1.6 KB
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.
- today Changed · +48 tokens per session 45c6f03f7403
- 12d ago Changed · +13 lines 4e1c94b54c9a
- 13d ago Changed · +78 lines ce257f3abff4
- 1mo ago Changed · +35 lines 7cdc967be5d6
- 1mo ago First seen · 225 lines · 61 tokens per session scan A df7805d80d5b
design-drawing-svg-md is a skill published in the GitHub repository znlgis/opengis-skills (75 stars, last pushed today), licensed MIT. It adds 109 tokens to every session and 8,047 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 2026-09-03.
Other skills, from other repositories
pdf-explore
Use this skill when the user has attached a PDF, paper, report, or other document and the answer needs content from more than one place in it: summarize the methods or any other section, compare sections, find where a topic is discussed, read a value or label off a figure or chart, or find/list/extract every instance…
smart-data-collection
A workflow for extracting structured information from images and documents such as PDFs, Word files, and spreadsheets, then storing it in a database.
summarize
Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube).
solidworks-engineering-drawing
A SolidWorks skill for creating and reviewing engineering drawings, which are manufacturing documents showing views, measurements, holes, parts lists, and title-block information.
knowledge-base
A knowledge-base skill for uploading files, webpages, articles, and notes, then browsing and searching them in IMA.
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…