What it does
A layout engine for AI diagrams: the model says what to draw, Sketchy figures out where. Hand-drawn, interactive, in Claude, Cursor and VS Code.
- Connects Instruction files the AI reads
- Account or key Not confirmed yet (README not read yet)
- Category Coding
For makers: add a badge to your README
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/ddkbs-sketchy)Use together with
MCP servers that connect the AI to services for the same work
Fallow
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
Desktop Commander
MCP server for terminal commands, file operations, and process management
Similar Skills
Same kind of work, ordered like the Skills list
| This one sketchy | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| Maker | ddkbs | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skills | 1 | 1 | 1 | 1 | 1 |
| GitHub stars | 449 | 465,460 | 233,910 | 149,364 | 144,149 |
| Last code change | Nov 13, 2026 | Nov 17, 2026 | Apr 20, 2026 | Nov 17, 2026 | Nov 17, 2026 |
| License | MIT | MIT | – | Apache-2.0 | MIT |
1 skills (instruction sets) by ddkbs that an AI reads and follows · not an MCP server
How a Skill differs from MCP
MCP = the hands
Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.
Skill = the manual
A text file that teaches the AI how to do a task. It connects to nothing.
Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.
Works with
Claude CodeClaude (เว็บ/แอป)CodexCursorWindsurfOpenCode
From the maker’s README and the folders in the repo
Install
Is it safe?
- Who made it
GitHub account ddkbs (person), 1 years old
- Use and upkeep
★ 449 stars, few users so far · code last changed Nov 13, 2026
- Any scripts?
1 scripts that can run on a computer: render.ts
- Uses the internet?
No internet calls found in the scripts
- Changes machine-wide settings?
No hooks or writes to machine settings found
Checked automatically from the repo files at commit c246cd4 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
First: which AI do you use?
Pick your app and this page shows only how to install it there
Option 1Upload to claude.ai (web and app)
Uploading to claude.ai would fail: the description is over 200 characters (448). Use "Let the AI install it" instead
Option 1Let Claude Code install it
Copy this sentence and paste it into a Claude Code 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
Restart Claude Code, then type /skill or ask for a matching task and Claude picks it up
Checked against official docs Nov 12, 2026 · Source: code.claude.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.claude/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
Restart Claude Code, then type /skill or ask for a matching task and Claude picks it up
ChatGPT desktop app
The ChatGPT desktop app has Codex built in, and Codex reads skills from ~/.agents/skills
Option 1Let ChatGPT install it
Open Codex in the ChatGPT desktop app and paste this sentence into the 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
Option 2Put the folder there yourself
Put the sketchy folder at ~/.agents/skills/sketchy
~ is your home folder ($HOME)
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.agents/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
After installing
- ChatGPT desktop app: open Skills in the sidebar to see that the skill is there
- To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
- Codex picks up newly installed skills by itself; if one does not show up, restart Codex
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
ChatGPT on the web and mobile
Skills you install yourself do not work here; only skills that come with a plugin from the directory
To use this skill with ChatGPT, use the ChatGPT desktop app as above
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
Option 1Let Codex install it
Copy this sentence and paste it into a Codex chat · Works in Codex inside the ChatGPT desktop app, Codex CLI and the IDE extension
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 picks up newly installed skills by itself; if one does not show up, restart Codex · To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.agents/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
Restart Codex, then ask for a matching task; Codex lists the skill
Option 1Let Cursor install it
Copy this sentence and paste it into a Cursor 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
In Cursor’s Agent chat, type / and pick skill
Checked against official docs Nov 12, 2026 · Source: cursor.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.cursor/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
In Cursor’s Agent chat, type / and pick skill
Option 1Let the AI install it
For other apps that read skills. The sentence gives the paths for Claude Code, Codex and Cursor so the AI picks the one for your 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 Nov 12, 2026 · Source: code.claude.com, learn.chatgpt.com, cursor.com
For Terminal users
Other apps that support Agent Skills (such as Gemini CLI or GitHub Copilot) use different folders. Check that app’s guide, then copy the folder with the SKILL.md there.
Skill folders checked against the official Claude Code, Codex and Cursor guides on Nov 11, 2026
View the original SKILL.md
The text below comes from the maker’s repo, not from PopNx MCP
Showing the first 8,000 characters · Open the full file on GitHub
---
name: sketchy
description: Draws hand-sketched, interactive diagrams (architecture, flows with step-by-step walkthroughs, comparisons, metaphors, Arduino circuits) right in the chat. Use whenever a concept, system, process or comparison is easier to understand as a drawing, or when the user asks for a sketch, diagram or visual explanation. In the regular Claude chat, use this skill even if Sketchy MCP tools are connected, because the chat does not display their drawings.
---
# Sketchy
In the regular Claude chat, always use this skill instead of the Sketchy MCP tools: the chat runs those tools but does not show their drawings.
You describe **what** to draw in a few short lines; Sketchy computes every position and renders it in a hand-drawn style with hover details and step navigation. Never pass coordinates.
## Workflow
Draw inline with your visualization tool (the one that renders HTML widgets in the conversation). Pass this HTML as the widget code, with the scene between the backticks:
```html
<h2 class="sr-only">One-sentence summary of the drawing</h2>
<div id="sketchy" style="min-height: 320px"></div>
<script src="{{CDN}}/sketchy.js" {{SRI}}></script>
<script>
Sketchy.draw(
"#sketchy",
`
title How a web request works
dir right
group net The internet
browser Browser @globe ~ Shown on hover
server Server @server in net !accent
db Database (cylinder) in net
browser -> server HTTPS
server --> db query
step Request: The browser asks the server | browser server browser->server
`,
);
</script>
```
Keep the widget code exactly like this: no other markup, styles or text. Then explain the drawing in 2–4 sentences in your reply instead of describing it again. If the widget shows "Sketchy could not draw this", fix the line the message names and draw again.
To change an earlier drawing, draw the whole scene again with the same ids.
Without a visualization tool, write the scene to a file and render a standalone page with the script in this skill's folder (Node.js, no network needed), then share the file:
```bash
node <skill-folder>/scripts/render.mjs /tmp/scene.txt /mnt/user-data/outputs/<short-name>.html
```
## Scene syntax
One element per line:
```
title <text> subtitle <text> dir right|down
group <id> <label> [in <parent group>]
<id> <label> [@icon] [(shape)] [in <group>] [!accent|!muted] [~ hover text]
<a> -> <b> [label] [!accent|!muted] (--> dashed, <-> arrowheads on both ends)
label <id>[.<pin>] <text>
step <title>: <text> | <ids to highlight; edges as a->b>
part <id> <type> [key=value] [caption]
wire <part.pin> -> <part.pin> [red|black|blue|green|yellow|orange|purple|gray|white]
draw <id> [WxH] [in <group>] [: title] (free drawing, its shape lines follow)
```
A free drawing has its own canvas (default `100x100`, y pointing down) and sits in the scene like a node, so arrows can connect to it. Later lines paint on top:
```
circle [name] x,y r ellipse [name] x,y rx ry rect [name] x,y w h (x,y = top left)
line|arrow|curve [name] x,y x,y … curve is smooth
shape|blob [name] x,y x,y x,y … closed; blob is smooth
arc [name] x,y r from to degrees, 0 = right, counter-clockwise
text [name] x,y words [size=14]
object <type> [name] x,y [size] [rotate=45] [flip] a ready-made thing
icon [name] x,y <lucide name> [size]
repeat i=0..7: <shape line> i in coordinates, {i+1} in names and labels
slider a 0..1 [= 0] [hidden] before the shapes using it
let w = 84-12*a names a sub-expression for the lines below
angle [name] x,y cx,cy x,y [r] arc at the middle point; 90° gets the square
measure [name] x,y x,y [offset] dimension line with arrows
brace [name] x,y x,y [depth] curly brace, bulging to the right of the way
axes [name] x,y w h [ticks=10] [~ x name | y name] x,y is the origin
grid [name] x,y w h [step] x,y is the top left
```
Object types: person, tree, cloud, house, car, bike, gear, sun, bulb, battery, laptop, phone, server, book, heart, drop, flame, mountain, flask, rocket, lock, key.
- Options: `fill=<color>`, `hatch=<color>`, `color=<color>`, `width=2`, `--dashed`, `arrow`, `both`, `!accent`, `!muted`, `stage=2`, `along=<shape name>@<0..1>`, `move=<dx>,<dy>`, `~ label`.
- Colors: black, gray, white, accent, yellow, blue, red, green, purple, orange.
- Prefer `~ label` over `text`: Sketchy places labels clear of the drawing. Coordinates may be math, such as `50+30*cos(1),50`.
- In steps, `| pic[name]` circles a named shape and `pic=2` shows only shapes up to stage 2, so a picture can build up. Start with `pic=1`. `a=0.5` glides a slider there, which is how things move. Draw a moving shape at its start and shift it with `move=40*a,0`; a shape with `along=wire@a` rides on the shape named `wire`. Every step should end in a clear picture: move things all the way, one idea per step, never stop a motion halfway.
Ready-made explanation shapes take only their contents, one entry per line, ended by a blank line. End an entry with `!accent`, `!muted` or `~ small print`:
```
timeline t: History <when> | <what>
cycle c: Water cycle <entry>
pyramid p: Needs <entry>, top first
funnel f: Sales <entry>, top first
mindmap m: Topic <centre>, then - <branch>, -- <sub-branch>
venn v: Pets set a Cats, set b Dogs, then a | purrs, a,b | pets (2 or 3 sets)
matrix x: Plans cols Option | Price, then Cheap | 1 €
```
In steps, `| t[2]` circles the 2nd entry and `t=2` shows only the first two.
Molecules and maps:
```
molecule m CC(=O)O [full] : Acetic acid SMILES; full writes out every C and H; steps circle atoms as m[3]
map m europe : Title world, europe, africa, asia, middle-east, north-america,
Germany !accent ~ Start south-america, americas, oceania, a country, or w,s,e,n
France fill=blue countries by English name: fill=, hatch=, !accent, ~ label
place berlin 52.52,13.40 Berlin a dot with a label, at latitude,longitude
route r: berlin -> 48.86,2.35 --dashed ~ 8 h
```
In steps, `| m[Germany]` (spaces as dashes: `m[United-Kingdom]`) circles a country, `m[berlin]` a place or route.
- Labels are 1–4 words; put details after `~`.
- Icons: `@globe`, `@server`, `@database` (Lucide) or `@simple-icons:react`.
- Shapes: `(cylinder)` storage, `(person)` actor, `(note)`, `(circle)`, `(rounded)`, `(text)`.
- Ids are letters, digits, `_` or `-`, unique across the scene; arrows, labels and steps may only use ids defined in it.
## Explanation patterns
Pick one per drawing:
- **structure** ("what is it made of?"): components as nodes, groups for areas, labels for the important bits; `dir down` for hierarchies.
- **flow** ("how does it work?"): a left-to-right chain of nodes and arrows plus one step per stage.
- **comparison** ("X vs Y"): one group per option with parallel nodes in the same order; `!muted` for what is equal, `!accent` for the key difference.
- **metaphor** ("explain it simply"): one group for the real thing, one for an everyday counterpart, dashed arrows between matching elements.
- **picture** ("what does it look like?"): a `draw` block of the thing itself when boxes and arrows would hide the idea, such as atoms, forces, cells, orbits, geometry or machines.
Quality rules: 3–12 nodes; `!accent` on at most one or two elements; icons sparingly; 3–7 steps of one or two sentences each.
## Circuits
Find part types and pin names first (needs code execution):
```bash
node <skill-folder>/scripts/render.mjs --parts "distance sensor"
node <skill-folder>/scripts/render.mjs --parts arduino-uno
``Discussion
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
From GitHub
- GitHub stars
- 449
- Maker
- ddkbs
- License
- MIT
- Last code change
- Nov 13, 2026
- SKILL.md files in the repo (including translated copies and templates)
- 1
- Topics
- claude, claude-code, claude-skill, claude-skills, cursor, diagrams, elkjs, layout-engine, mcp, mcp-apps, model-context-protocol, npm
- Repo
- ddkbs/sketchy