REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Agent skill that draws architecture, flowchart, sequence, data-flow and lifecycle diagrams as hand-placed SVG, to one linted house style.
Si lo creaste tú, pega este código en tu README. La insignia enlaza a esta página.
[](https://mcp.popnx.com/en/skills/bybit-exchange-svg-diagram)Servidores MCP que conectan la IA a servicios para el mismo trabajo
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
Mismo tipo de trabajo, ordenadas como la lista de Skills
| Este svg-diagram | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| Autor | bybit-exchange | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skills | 1 | 1 | 1 | 1 | 1 |
| Estrellas de GitHub | 673 | 468.733 | 234.332 | 150.287 | 144.566 |
| Último cambio de código | 3 sept 2026 | 19 nov 2026 | 20 abr 2026 | 18 nov 2026 | 18 nov 2026 |
| Licencia | MIT | MIT | – | Apache-2.0 | MIT |
1 skills (conjuntos de instrucciones) de bybit-exchange que la IA lee y sigue · no es un MCP server
MCP = las manos
Conecta la IA a un servicio o dato externo, como leer Notion o crear una factura. Necesita un programa o servidor en marcha.
Skill = el manual
Un archivo de texto que enseña a la IA cómo hacer una tarea. No se conecta a nada.
A veces se parecen: algunas Skills ejecutan scripts que llaman herramientas y algunos MCP solo envían conocimiento. Empieza por la tarea que quieres hacer.
Claude CodeClaude (เว็บ/แอป)CodexCursorGemini CLIGitHub CopilotWindsurfOpenCodeKiro
Según el README del autor y las carpetas del repo
GitHub account bybit-exchange (organization), 8 years old
★ 673 stars · code last changed 3 sept 2026
46 scripts that can run on a computer: tools/svg-lint/bin/svg-lint.mjs, tools/svg-lint/lib/checks/arrow-marker.mjs, tools/svg-lint/lib/checks/baseline-offset.mjs, tools/svg-lint/lib/checks/block-spacing.mjs and 42 more
Could not check every script (some are too large); read them first
No hooks or writes to machine settings found
Checked automatically from the repo files at commit c30c9e3 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
Primero: ¿qué IA usas?
Elige tu app y esta página mostrará solo cómo instalarlo en ella
Uploading to claude.ai would fail: the description is over 200 characters (356). Use "Let the AI install it" instead
Copia esta frase y pégala en un chat de Claude Code
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Vuelve a abrir Claude Code y escribe /svg-diagram, o pide una tarea relacionada y Claude lo usará
Checked against official docs 12 nov 2026 · Source: code.claude.com
Un Skill son instrucciones que la IA seguirá. Lee los archivos antes de instalar e instala solo de autores de confianza.
¿Ya está instalado? Compruébalo primero · Abre la Terminal, escribe este comando y pulsa Enter
node -vMac: pulsa ⌘ + Espacio, escribe Terminal y pulsa Enter
Windows: abre Inicio, escribe Windows PowerShell y elige Abrir
Si no está instalado: Abre la página oficial de descargas, elige la versión LTS y el instalador de clics: .pkg en Mac · .msi en Windows. Haz doble clic y sigue hasta el final. No necesitas ningún comando curl
Abrir la página de descarga de Node.js ↗
Al terminar, cierra la Terminal, ábrela de nuevo y ejecuta el mismo comando. Debe aparecer un número de versión: node -v
Se instala una vez y sirve para todo lo que usa Node.js
Revisando los comandos · los botones de copiar aparecen cuando pasan la revisión
Copiado del README del autor; descarga y ejecuta su código
Mac: pulsa Command+Espacio y escribe Terminal · Windows: el comando no funciona en PowerShell; usa «Que la IA lo instale» arriba
Descarga el repo a una carpeta temporal y copia solo las carpetas con SKILL.md
Revisando los comandos · los botones de copiar aparecen cuando pasan la revisión
La app de escritorio de ChatGPT incluye Codex, y Codex lee las skills de la carpeta ~/.agents/skills
Abre Codex en la app de escritorio de ChatGPT y pega esta frase en el chat
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Coloca la carpeta svg-diagram en ~/.agents/skills/svg-diagram
~ es tu carpeta de inicio ($HOME)
Un Skill son instrucciones que la IA seguirá. Lee los archivos antes de instalar e instala solo de autores de confianza.
Mac: pulsa Command+Espacio y escribe Terminal · Windows: el comando no funciona en PowerShell; usa «Que la IA lo instale» arriba
Descarga el repo a una carpeta temporal y copia solo las carpetas con SKILL.md
Revisando los comandos · los botones de copiar aparecen cuando pasan la revisión
Checked against official docs 15 nov 2026 · Source: learn.chatgpt.com
Las skills que instalas tú no funcionan aquí; solo las que vienen con un plugin del directorio
Para usar esta skill con ChatGPT, usa la app de escritorio de ChatGPT como se indica arriba
Checked against official docs 15 nov 2026 · Source: learn.chatgpt.com
Copia esta frase y pégala en un chat de Codex · Sirve en Codex dentro de la app de escritorio de ChatGPT, en Codex CLI y en la extensión del IDE
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex detecta solo las skills recién instaladas; si una no aparece, reinicia Codex · Para usarla: en ChatGPT escribe @ y elige la skill · en Codex CLI o la extensión del IDE ejecuta /skills o escribe $ y el nombre de la skill
Checked against official docs 15 nov 2026 · Source: learn.chatgpt.com
Un Skill son instrucciones que la IA seguirá. Lee los archivos antes de instalar e instala solo de autores de confianza.
Mac: pulsa Command+Espacio y escribe Terminal · Windows: el comando no funciona en PowerShell; usa «Que la IA lo instale» arriba
Descarga el repo a una carpeta temporal y copia solo las carpetas con SKILL.md
Revisando los comandos · los botones de copiar aparecen cuando pasan la revisión
Copia esta frase y pégala en un chat de Cursor
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
En el chat Agent de Cursor escribe / y elige svg-diagram
Checked against official docs 12 nov 2026 · Source: cursor.com
Un Skill son instrucciones que la IA seguirá. Lee los archivos antes de instalar e instala solo de autores de confianza.
Mac: pulsa Command+Espacio y escribe Terminal · Windows: el comando no funciona en PowerShell; usa «Que la IA lo instale» arriba
Descarga el repo a una carpeta temporal y copia solo las carpetas con SKILL.md
Revisando los comandos · los botones de copiar aparecen cuando pasan la revisión
Para otras apps que leen skills. La frase incluye las rutas de Claude Code, Codex y Cursor para que la IA elija la de tu app · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 12 nov 2026 · Source: code.claude.com, learn.chatgpt.com, cursor.com
Otras apps con Agent Skills (como Gemini CLI o GitHub Copilot) usan otras carpetas. Mira la guía de esa app y copia allí la carpeta con el SKILL.md.
Carpetas de skills comprobadas con las guías oficiales de Claude Code, Codex y Cursor el 11 nov 2026
El texto siguiente viene del repo del autor, no de PopNx MCP
Se muestran los primeros 8000 caracteres · Abrir el archivo completo en GitHub
---
name: svg-diagram
description: SVG diagramming conventions blending a technical look with CJK-friendly typography. Use when creating flowcharts, architecture diagrams, and similar SVG figures. For one-shot generation, prefer invoking it from a subagent so the main context does not have to carry this skill plus the SVG XML; for multi-round tweaking, use it directly in the main context.
---
# SVG Diagramming Conventions
## Output location and referencing
> Diagrams go in SVG, never ASCII art. That rule decides *whether* to draw; this skill covers *how*, starting with where the file lands.
- Put the file in an `assets/` directory next to the document (e.g. `docs/foo.md` → `docs/assets/foo-arch.svg`)
- Reference it from markdown with a relative path, ``. Do not inline SVG XML.
- When data in the document changes, the corresponding SVG must be updated too. A figure that contradicts the prose beside it is worse than no figure
## Core principles
### Get it right on the first pass
The first SVG you generate must already satisfy every item in the verification checklist at the end of this document. Do not rely on user feedback to fix basic layout problems (spacing, padding, alignment, viewBox clipping). After generating, walk the checklist yourself and fix anything you find before showing the result.
### No overlapping elements
- Text must not sit on top of boxes or lines
- Lines must not cut through boxes (unless the line is an arrow terminating at that box)
- Keep 10–20px between text and lines
- **For spacing between sibling/adjacent boxes see the "Block spacing" section below** (single standard: ≥25px, 25–30px recommended)
- Put color-key legends outside the diagram body (bottom or side), never overlapping the content area
```xml
<!-- ✅ Correct: label sits beside the line -->
<path d="M35,200 C 35,120 ..." .../>
<text x="55" y="200">Label text</text> <!-- 20px clearance -->
<!-- ❌ Wrong: label sits on the line -->
<text x="35" y="200">Label text</text>
```
### Visual balance
The left and right halves should carry similar visual weight; add or remove annotation boxes to even them out.
## Layout rules
### Centering
```
content width = right edge of rightmost element - left edge of leftmost element
left margin = (viewBox width - content width) / 2
```
**Center the title on the *content* center, not the viewBox center** (they differ whenever the content is asymmetric):
```xml
<!-- content center = (content left edge + content right edge) / 2 -->
<text x="[content center x]" y="[top_padding + font_ascent]" text-anchor="middle">Title</text>
```
Only when the content is left-right symmetric does `content center x = viewBox width / 2`. When it is asymmetric, center the whole group with `<g transform="translate(...)">` and update the title's `x` to the new content center as well.
### Shifting everything after the fact
If you only notice asymmetric left/right (or top/bottom) padding after the SVG is finished, you do not need to touch every coordinate. Wrap the content in one `<g transform="translate(dx, dy)">`:
```xml
<svg viewBox="0 0 800 460" ...>
<defs>...</defs>
<g transform="translate(22, 0)">
<!-- all content here, coordinates unchanged -->
</g>
</svg>
```
**Computing the offset**: `dx = (right padding - left padding) / 2`, where padding is the distance from the viewBox edge to the nearest content element.
- `dx > 0`: shift content right (use when content sits too far left)
- `dx < 0`: shift content left (use when content sits too far right)
When to use it: the content as a whole is off-center and you do not want to edit every `x` coordinate. Downside: the coordinates in the file no longer equal rendered positions, so later edits require mentally subtracting the offset — if a larger layout rework is coming, fold the offset into the individual coordinates and drop the `<g>`.
### viewBox margins
The title is part of the content, so top and bottom margins are measured from the title:
```
title y = margin + font ascent (≈ font-size × 0.75)
viewBox height = bottom y of content + margin
```
**Recommended margin**: 20–25px
```xml
<!-- Example: 16px title, 20px margin -->
<!-- title y = 20 + 16×0.75 ≈ 32 -->
<!-- content bottom 270px, viewBox height = 270 + 25 = 295 -->
<svg viewBox="0 0 680 295" ...>
<text x="340" y="32" font-size="16">Title</text>
...
</svg>
```
### Box layout
- Boxes in the same row differ in size by ≤60px; text is centered (`text-anchor="middle"`)
- Boxes in the same column share a center line
- An outer box fully encloses the inner boxes: `outer size = content size + padding × 2`
### Dashed grouping boxes (containers)
Used to group related boxes together (e.g. "Server", "Client", "Employee instances").
**Style consistency**: within one diagram, every dashed grouping box must share these attributes:
- `stroke-dasharray` (recommended `6,4`)
- `rx` (corner radius, recommended 8–12)
- `fill` (recommended `#f8fafc` or `none`)
- Inner padding (recommended 15–20px)
- Title font size (recommended 11px, to distinguish it from the 12px box body text)
**Title placement**: put the group title inside the top-left corner of the box (`x = box x + 10, y = box y + 14`) using the secondary text color `#64748b`.
**Vertical-centering trap**: compute the group box's vertical position from the combined height of **title + inner content**, not from the box alone. With a title, the top of the box is occupied for roughly 20–25px, and inner boxes start below it:
```xml
<!-- ✅ Group box: title + content laid out as a whole -->
<!-- box top y=100, title takes 20px, inner boxes start at y=125 -->
<rect x="50" y="100" width="200" height="120" rx="10"
stroke="#94a3b8" stroke-dasharray="6,4" fill="#f8fafc"/>
<text x="60" y="114" font-size="11" fill="#64748b">Server</text>
<!-- inner boxes -->
<rect x="65" y="125" width="170" height="36" rx="6" .../>
<rect x="65" y="170" width="170" height="36" rx="6" .../>
```
**Connectors pointing at a group**: when a connector logically targets a set of elements rather than one of them, terminate it on the group box boundary instead of on a single member. Alternatively, wrap the elements in a grouping box and point the arrow at that box.
### Box dimensions
Derive box height from the font size so there is enough inner padding:
| Content | Height formula | Example (12px font) |
|---------|----------------|---------------------|
| One line | font-size × 3 | 36px |
| Two lines | font-size × 3 + line height | 36 + 18 = 54px |
| Multiple lines | font-size × 3 + (lines - 1) × line height | +18px per extra line |
**Where the formula comes from**: `font-size × 3 = top padding (≈font-size) + glyph height (≈font-size) + bottom padding (≈font-size)`. Scale the same ratio for non-standard font sizes.
**Recommended line height**: font-size × 1.5 (e.g. 18px for a 12px font)
### Vertically centering text in a box (baseline positioning)
In SVG, `<text y=...>` is the **baseline**, not the top of the glyph. To center text optically inside a box:
```
text y = box center y + font-size × 0.35
= box y + box height/2 + font-size × 0.35
```
The 0.35 factor is an empirical value for "optical glyph center to baseline" (roughly one third of the font size).
**Keep the two factors apart**:
- `font-size × 0.75` (ascent): for elements **positioned from the top**, such as titles (y = top_padding + ascent)
- `font-size × 0.35` (baseline offset): for **vertical centering inside a box**
```xml
<!-- One line: height = 12 × 3 = 36px -->
<rect x="30" y="50" width="110" height="36" rx="6" .../>
<!-- y = 50 + 36/2 + 12×0.35 = 50 + 18 + 4.2 ≈ 72 -->
<text x="85" y="72" ...>Single line</text>
<!-- Two lines: height = 36 + 18 = 54px -->
<rect x="30" y="50" width="110" height="54" rx="6" .../>
<text x="85" y="70" ...>First line</text>
<text x="85" y="88" ...>Second line</text> <!-- 18px apart -->
```
### Display size
```xml
<svg viewBox="0 0 750 400" width="750" xmlns="http://wwPregunta, comparte un consejo o avisa de que no funciona. Ordenado por lo que la gente marcó como útil.
Aún no hay publicaciones. Sé la primera persona en preguntar o compartir.
Lo publicado aquí lo escriben usuarios, no el equipo de PopNx.