Borrowing it
Nothing to install: this file belongs to BeWaterMyFriend7/SKILL-PROJECT. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/BeWaterMyFriend7/SKILL-PROJECT/main/.opencode/skills/svg-generator/SKILL.mdgit clone --depth 1 https://github.com/BeWaterMyFriend7/SKILL-PROJECTWrote 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/bewatermyfriend7/skill-project/svg-generator)<a href="https://agentmods.dev/skills/bewatermyfriend7/skill-project/svg-generator"><img src="https://agentmods.dev/badge/skills/bewatermyfriend7/skill-project/svg-generator/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/bewatermyfriend7/skill-project/svg-generator"><img src="https://agentmods.dev/badge/skills/bewatermyfriend7/skill-project/svg-generator.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 | $0.00120 | $0.01405 |
| Opus 5 | $0.00060 | $0.00702 |
| Sonnet 5 | $0.00024 | $0.00281 |
| Haiku 4.5 | $0.00012 | $0.00140 |
Grade A, and why
svg-generator 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SVG 图形生成器
生成自包含 UTF-8 SVG。用户未指定目录时保存到项目根目录 output/svg/；需要拖拽编辑时改用 xml-diagram。
必读资源
- 分析需求和编写图形描述前读取
references/svg-dsl.md。 - 规划布局、颜色、连线和检查项时读取
references/quality-rules.md。 - 读取与图形类型同名的
templates/*.svg，再参考同类型examples/*.svg；禁止只替换标题后交付。
强制流程
分析需求 → 详细自然语言 DSL → 匹配模板 → 计算布局 → 生成 SVG
→ 严格源文件校验 → 浏览器渲染检查 → 修正并交付
1. 分析需求
确定图形目的、受众、图形类型、浅色或深色主题、阅读方向、内容层级、核心关系和输出路径。区分用户明确内容、合理补充和不可擅自推断的业务事实。
图形类型从以下目录选择：
- 架构：业务、应用/系统、技术、部署、数据；
- 流程与行为：线性流程、分支流程、生命周期、状态、时序；
- 关系：ER、依赖关系、知识关系；
- 信息表达：对比、决策矩阵、SWOT、时间线、路线图、总结图。
不生成系统上下文图；中心系统与外部角色关系优先改为应用架构或依赖关系图。
2. 生成详细自然语言 DSL
按 references/svg-dsl.md 写清画布、层级、分区、节点、布局、尺寸、连线、主题和检查要求。DSL 不强制落盘，不使用 JSON、JSON Schema 或 DiagramPlan 作为中间格式。
3. 匹配模板
- 业务架构读取
templates/architecture-business.svg。 - 应用或系统架构读取
templates/architecture.svg。 - 技术架构读取
templates/architecture-technical.svg。 - 部署架构读取
templates/architecture-deployment.svg。 - 数据架构读取
templates/architecture-data.svg。 - 其他类型读取同名模板。
用户内容与模板不同，可以增减层和卡片，但必须保留模板的层级、间距和设计语言，不机械保留空层。
4. 计算布局
先计算区域、标题、卡片、文字和必要连线所需空间，再确定画布。
- 架构图默认整体纵向分层、层内横向排列；一级标题可在容器顶部居中，二级标题与三级卡片分离。
- 三级卡片默认高
28-34px，同组等宽、等高、等距；内容过多时规则换行或扩展画布。 - 架构图默认不画箭头，通过层级、容器、分组和空间顺序表达关系。只有调用、流量或主数据流不可缺少时才保留少量正交连线。
- 同层内容铺满可用区域，不得集中在左侧；左右、上下留白与内容量匹配。
- 时序图必须包含完整参与者、生命线、横向消息、返回消息和起止语义。
- 流程图必须包含起点、终点和完整判断出口；关系图必须预留连线通道。
5. 生成 SVG
width、height与viewBox一致。- 根节点使用
role="img"和aria-labelledby，包含<title>、<desc>。 - 使用唯一 id；引用的 marker、filter、gradient、clipPath 必须存在。
- 使用字体 fallback，不嵌入外部字体、位图、CSS 或远程资源。
- 多行文字使用
<tspan>，不使用foreignObject。 - 为主要节点、连线和辅助文字分别添加
data-role="node"、data-role="edge"、data-text-role="auxiliary"。 - 只使用统一默认视觉风格。浅色和深色只切换颜色变量，几何结构、文字和关系保持一致。
- 按
background → regions → edges → nodes → labels → legend分层，保证文字和节点位于连线之上。
6. 严格校验和渲染
交付前运行：
python -X utf8 scripts/validate.py output/svg/文件名.svg --strict --render
修改 skill 内模板或示例时运行：
python -X utf8 scripts/validate.py . --strict
python -m unittest discover -s tests -v
What ships with it
44 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/architecture-application-light-ecommerce.svg 3.2 KB
- examples/architecture-business-light-ecommerce.svg 3.7 KB
- examples/architecture-data-light-data-platform.svg 7.1 KB
- examples/architecture-deployment-light-ecommerce.svg 3.8 KB
- examples/architecture-technical-light-ecommerce.svg 3.8 KB
- examples/comparison-light-solutions.svg 2.8 KB
- examples/decision-matrix-light-technology.svg 2.2 KB
- examples/flow-branching-light-order-processing.svg 3.4 KB
- examples/flow-linear-light-order-payment.svg 3.0 KB
- examples/lifecycle-light-development.svg 3.6 KB
- examples/relationship-dependency-light-services.svg 2.5 KB
- examples/relationship-er-dark-user-order.svg 3.6 KB
- examples/relationship-er-light-user-order.svg 3.6 KB
- examples/relationship-knowledge-light-order.svg 2.3 KB
- examples/roadmap-light-product.svg 3.1 KB
- examples/sequence-light-login.svg 3.6 KB
- examples/state-light-order-processing.svg 3.2 KB
- examples/summary-dark-article.svg 2.6 KB
- examples/summary-light-article.svg 2.6 KB
- examples/swot-light-product.svg 2.0 KB
- examples/timeline-light-project.svg 2.1 KB
- references/quality-rules.md 5.7 KB
- references/svg-dsl.md 4.3 KB
- scripts/validate.py 22 KB runs code
- templates/architecture-business.svg 3.7 KB
- templates/architecture-data.svg 7.1 KB
- templates/architecture-deployment.svg 3.8 KB
- templates/architecture-technical.svg 3.8 KB
- templates/architecture.svg 3.1 KB
- templates/comparison.svg 2.8 KB
- templates/decision-matrix.svg 2.2 KB
- templates/flow-branching.svg 3.4 KB
- templates/flow-linear.svg 3.0 KB
- templates/lifecycle.svg 3.6 KB
- templates/relationship-dependency.svg 2.5 KB
- templates/relationship-er.svg 3.6 KB
- templates/relationship-knowledge.svg 2.3 KB
- templates/roadmap.svg 3.1 KB
- templates/sequence.svg 3.6 KB
- templates/state.svg 3.2 KB
- templates/summary.svg 2.6 KB
- templates/swot.svg 2.0 KB
- templates/timeline.svg 2.1 KB
- tests/test_validate.py 4.5 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 · 97 lines · 120 tokens per session scan A 8ac4d85836b9
svg-generator is a skill published in the GitHub repository BeWaterMyFriend7/SKILL-PROJECT (51 stars, last pushed 4d ago), licensed Apache-2.0. It adds 120 tokens to every session and 1,405 once invoked, about $0.0006 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.