by JimLiu
Run Claude Design locally as an Agent Skill — Cursor, Codex, DeepSeek Harness & more. Produce polished UI mockups, prototypes, decks & wireframes as self-contained HTML, without claude.ai/design. Best with Opus or Claude.
From $49 · 30 days · terms & refunds
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Automated security scan — not a certification.
# Add to your Claude Code skills
git clone https://github.com/JimLiu/open-artifactsGuides for using ai agents skills like open-artifacts.
Last scanned: 11/14/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-11-14T11:13:37.602Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how open-artifacts compares with popular alternatives.
https://github.com/user-attachments/assets/d5b4f39b-a701-49de-87b8-64f3c6ef9c61
https://github.com/user-attachments/assets/84ddf462-5ac6-44c6-a175-05a7ccaa019e
https://github.com/user-attachments/assets/db6c5d93-dc28-4170-8356-4dbe5725a57c
Run Claude Design on your own local agent — Cursor, Claude Code, Claude Desktop, or any file‑capable coding agent.
This repo brings claude.ai's Artifact types to local agents: editable slide decks, design canvases, design systems, data dashboards, motion films and whiteboards, each opened in its own editor that runs on your machine. motion-director directs those films, from the point of the film to the finished cut. dataviz is the chart guide the agent reads before it draws any chart, in these skills or anywhere else. The six editors also ship as DeepSeek Harness plugins, installed from npm by name.
This project was called baoyu-design until November 2026, and its old address on GitHub leads here. The original baoyu-design skill (self‑contained HTML mockups and prototypes) has been archived to archive/baoyu-design/.
No website, no separate subscription, no upload step. The agent already on your machine does the work, and every artifact stays in your repo.
| Skill | Makes | You edit it in |
|---|---|---|
claude-slides |
Slide decks: project/deck.json plus one HTML file per slide |
The slides editor: present, retype, drag; export PDF, HTML or PowerPoint |
claude-design |
A canvas of artboards: project/canvas.json plus .dc.html Design Components |
The canvas editor: artboards side by side, play prototypes, retype copy, adjust tweaks; export HTML, PDF, PNG or HTML for Figma |
claude-design-system |
Design systems: tokens, a README brand book, component previews, fonts, asset groups | The design system editor: browse and edit colors, type, components and assets |
claude-data |
Data‑backed dashboards: datasets (CSV, TSV, JSON) and a page of charts, numbers and tables over them | The dashboard page: live charts, filters, and a Sources panel that traces every number to its rows |
claude-motion |
Motion films: animated videos, 10–30 s unless you ask for more and 15 minutes at most, written as code scene by scene into the film's own store under <root>/db/ |
The Motion player: watch it fill in, retype lines, drag scene lengths, adjust style and tweaks; export MP4 or GIF |
motion-director |
A finished film with something to say: it finds the point, writes the narration for the ear, has it voiced, times every scene to the words, and checks the frames as a viewer would. Needs claude-motion beside it |
The same Motion player, open from the first minute |
claude-whiteboard |
Whiteboards: diagrams, flows, maps of ideas, plans and comparisons, written as elements (blocks, sections, arrows, tables, sticky notes, drawings, working embeds) into the board's own store under <root>/db/ |
The board editor: move, resize, type, draw with the pen, add sections, sticky notes, shapes and stickers, drop in videos; export PNG |
dataviz |
Better charts in any medium (HTML, SVG, d3, matplotlib, plotly…): picking the form, colors that stay readable in light and dark and for color‑blind readers, marks, legends and tooltips, with a palette validator script | Nothing to open: the agent reads it before writing chart code; swap palette.md for your brand's colors |
These six skills write the Artifact type's own file format into a folder and open it in that type's editor page, served from your machine. The agent writes the files and the editor shows each write at once; your edits in the editor are saved back into the same files, so you and the agent can take turns.
In the slides, canvas and design-system editors and on the dashboard page, choose Comment (or press C) to comment on an element or area; in the Motion player, its Comment button comments on a moment of the film; on a whiteboard, the comments button comments on an item, a spot or an area. Comments stay in the project's local comments.json; the agent reads and replies through artifact.mjs. While it listens with comments <root> --wait, the editor offers Send to Agent to send your comment for it to act on, and the page's own buttons that ask the agent for something (Ask the agent to fix on a slide or canvas that can't be shown, the design system's setup buttons, the dashboard's Ask the agent) send it their request the same way.
To work together, share <root> (or open <root> --lan) opens the deck, canvas, design system, dashboard, film or board to your local network, the same Wi‑Fi or LAN, and prints a link per role: editor edits and comments, commenter comments without editing, viewer only looks. Whoever opens a link types a name and is in; what they change shows on everyone's page, and their comments land in the same comments.json. The person at this computer is the owner: the Share button lists who joined and who is online, changes someone's role or removes them, and turns each link off, back on or resets it. Guests get a Share button too, with the links they may pass on: their own role's and those below it. There is no account and nothing leaves your network; it is plain http, so anyone there with a link gets in.
Every change is kept as a version, with who made it: a guest by the name they typed, the owner, or Agent for a change made to the files on this computer. The History button (the clock beside Share) lists the versions by day; open one to see which slides, artboards or documents it changed, line by line, preview the whole thing as it was, or restore it (or just one part) as a new version, so nothing is lost. When two people save the same slide at once, the later save no longer wipes out the earlier one unnoticed: the version records whose change it replaced, and both people get a notice with Compare and Bring back, which puts back only what was replaced and leaves the other person's other changes. In the slides, design and design-system editors, someone else's save updates your page in place instead of reloading it, and if they saved the slide, artboard or file you have unsaved edits on, a bar asks whether to use theirs, keep yours, or keep both (yours becomes a new slide after it, an artboard beside it, or a copy of the file). The two are first merged: on a canvas element by element, in slides and design-system files line by line (a token file token by token). When you changed different elements or lines, both changes stay and nothing asks; the bar comes up only when the merge cannot sort it out, such as both changing the same line. The history lives in the project's history/ folder.
While others have the page open, their avatars sit beside History. In the slides and canvas editors each one's card says which slide or artboard they are on and whether they are editing, and their cursors and selections show where they work; when someone starts editing what you are looking at, you get a short note, and nothing is ever locked. While Claude changes the files, it shows up there too.
To back a project up, move it to another computer or hand it to someone, the owner's Whole folder (.zip) item, last in the Share panel's Export tab (the owner's: guests can pass a link on but not export), downloads the whole folder as one zip, its history and comments included; artifact.mjs archive <root> does the same from the command line. Unzip it anywhere and open it with the same skill to carry on. This computer's server state and the share links are left out, so a copy you send is not shared until its new owner shares it.
claude-slides: slide decksA deck is project/deck.json plus one HTML file per slide. In the editor you can present full screen, retype any text, drag elements, add text, images, tables and shapes, and export to PDF, HTML or PowerPoint. A video added by link plays in its provider's player, and the agent can upload a clip for a slide. Above: a five‑slide health class deck about sleep, built on a sample design system.
claude-design: a canvas of artboardsA canvas holds artboards side by side: project/canvas.json plus one .dc.html Design Component per artboard. Play an artboard as a working prototype, on the canvas or full screen; retype copy, adjust tweaks and leave notes; export the whole design as a standalone HTML page, a PDF or PNG images (1× or 2×, several artboards in a .zip); HTML for Figma saves the artboards as a page without frames, for Figma's Chrome extension to capture. Full window, an artboard lays out at a screen width you pick (phone, tablet or desktop sizes), and its Export saves the whole page at that width as a PNG. *Above: the landing hero of a coffee subscription, with its mobile si
open-artifacts is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by JimLiu. Run Claude Design locally as an Agent Skill — Cursor, Codex, DeepSeek Harness & more. Produce polished UI mockups, prototypes, decks & wireframes as self-contained HTML, without claude.ai/design. Best with Opus or Claude. It has 6,426 GitHub stars.
Yes. open-artifacts passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/JimLiu/open-artifacts" and add it to your Claude Code skills directory (see the Installation section above).
open-artifacts is primarily written in JavaScript. It is open-source under JimLiu on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh open-artifacts against similar tools.
No comments yet. Be the first to share your thoughts!