DSH Marketplace

superdesign-skill

superdesigndev/superdesign-skill

Design skill for UI and marketing graphics on the Superdesign canvas: reads the repo for context, extracts its design system, then generates and iterates branchable design drafts, flow pages, and reusable components through the Superdesign CLI.

89466JavaScriptMITSource

Install

Add superdesign-skill to DeepSeek Harness

Install into

via GitHub · GitHub source

Installing from GitHub runs the project's build script, which pnpm blocks until you allowlist it — run the command once and pnpm prints the exact key to add under `allowBuilds` in ~/.dsh/profiles/web/pnpm-workspace.yaml.

What happened when we ran it

Installed cleanly when we ran it

Every command here is run in a throwaway container against a clean profile, and the result is whatever the harness recorded — not a guess from the source. Last run 11d agoon DeepSeek Harness 0.2.2-rc.1.

Show it in your README

install verified — dshmarketplace

For maintainers: the badge serves this listing's latest sandbox verdict, so a re-run updates it on its own — and it links readers to the full result here.

Due diligence

Before you install superdesign-skill

Security

What installing superdesign-skill runs

Build scripts

No build script was blocked in our run.

Source: our sandbox install on DeepSeek Harness 0.2.2-rc.1, 11d ago.

Install hooks

package.json declares no preinstall, install or postinstall script.

Source: package.json on GitHub, read at our last sync. prepare is not recorded; it runs only on a GitHub install, and shows up under build scripts when pnpm blocks it.

README mentions

shell commands (bash, exec, spawn …)

Source: a keyword match on the README — a hint about what the plugin touches, not an analysis of its code.

Not an audit. These are the record of one install and two text scans; nobody has read this plugin's code on your behalf. Plugins run with your agent's permissions.

The AI take

What it is — Points the agent at a Superdesign canvas: extract a design system from the repo, then generate and branch UI, flow, and marketing-graphic drafts through the CLI.

Who it is for — You're using a DeepSeek model in DeepSeek Harness to redo a settings page or dashboard that works but looks like stock components, and you need repo-aware design-system extraction plus branchable canvas drafts. If design already happens in the superdesign.dev web app and the agent only implements approved screens, skip this plugin—the site and the skill are two doors into the same product.

Watch out — It installed on a clean profile and DeepSeek Harness registered it. Canvas work still needs a local Superdesign CLI and a logged-in account, and the skill issues shell commands. It is not the archived Superdesign VS Code extension.

The verdict — Worth adding only as a review surface between today's UI and the next one, knowing that surface is an HTML snapshot plus canvas branches—not as a faster way to edit components in the repo.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.

What superdesign-skill does

Repository tiles flow through a prism into branching design sheets and modular blocks.

superdesign-skill is a DeepSeek Harness plugin that lets an agent design UI and marketing graphics on the Superdesign canvas, rather than generating interface code without a visual drafting stage. It reads the repository to understand the existing UI and design system, stores the system guide at .superdesign/design-system.md, and can create, iterate, branch and fetch design drafts through the superdesign CLI. For existing pages, it can also create replica templates under .superdesign/replica_html_template/<name>.html, which provide the current UI as a baseline for canvas work.

The plugin is intended for developers, product designers and indie hackers working from a coding agent who want to explore page designs, flows and reusable components before implementation. Its terminal surface reaches the repository files it needs to inspect or write and invokes the separately installed superdesign CLI; the CLI must be authenticated with superdesign login. Later sessions can resume project and draft context when the relevant codebase state has not changed.

superdesign-skill is a poor fit when a project only needs direct UI implementation, or when the Superdesign CLI and its canvas workflow are not available. The canvas does not access the codebase directly, so design work on an existing page depends on first producing an accurate replica HTML template. It is also separate from the archived Superdesign VS Code extension.

superdesign-skill documentation

How it behaves

superdesign-skill is invoked through the agent and follows a design workflow rather than a single fixed command. For an existing application, it investigates the relevant UI, creates or updates .superdesign/design-system.md, gathers requirements, and asks whether to design in Superdesign or implement directly. If canvas design is selected, it creates a current-state replica at .superdesign/replica_html_template/<name>.html, then uses that replica and the design-system guide as project context. The replica should describe the current UI only; it is not the place to add the new design.

After project setup, the agent creates a design draft and iterates or branches it using the returned designDraft ID. Flow work is split into planning flow pages and executing flow pages. Existing project, draft, extracted component and source-context information can be retained across sessions.

Commands

The README documents these superdesign CLI operations:

Command Purpose
superdesign search-prompts --query "<keyword>" Search the prompt library by query
superdesign search-prompts --tags "style" Search by tags, optionally with --query
superdesign get-prompts --slugs "<slug1,slug2,...>" Read the compact index for selected prompts
superdesign get-prompts --slugs "<slug>" --full Fetch full prompt bodies
superdesign extract-website --url https://example.com --design-md Extract a site's design DNA into a design guide
superdesign login Authenticate the CLI

The canvas tooling also covers project creation, optional HTML-template seeding, draft creation, draft iteration or replacement, branching, flow-page planning and execution, and fetching a specific draft. CLI output is intended to be read directly; use --json for a full machine-readable payload and --full to expand truncated fields.

Requirements

The README lists support for Claude Code, Cursor, Codex and more than 70 coding agents. It requires the separately installed @superdesign/cli, followed by superdesign login. The README does not specify environment variables, operating-system constraints or CLI authentication defaults.

Written from the project's own documentation and kept in sync with it. Where the two disagree, the source is authoritative — read the README on GitHub

Same category

Alternatives to superdesign-skill

dsh-skill-explorer

zhu1090093659

10k

Skill center for the dsh web GUI: browse all loaded skills grouped by source, enable or disable model invocation, create new skills, and delete into a recoverable trash.

Installed cleanly when we ran it

npm packageTypeScript2d ago

AI review

dsh-skill-explorer

What it is — A DSH Web GUI page that lists loaded skills by origin, with invocation toggles, creation, and a trash you can restore from.

Who it is for — You run agents in the DSH Web GUI with skills piled in from several origins, and the model keeps hitting ones you wanted left idle. Anyone who only edits skill files in a terminal and never opens the Web GUI has no use for this panel.

Watch out — On a fresh profile it installed and the harness registered it. No sharp edges showed up in that run.

The verdict — A single setup pass on invocation flags does not earn a plugin slot from me; I add it only when I keep turning skills on and off.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Details

Answers a question with a one-page visual HTML explainer: the model writes a short Markdown draft and the bundled `am` CLI builds the page, with flow, sequence, tree, timeline and ER diagrams, tables and callouts.

Installed cleanly when we ran it

GitHub sourceJavaScriptyesterday

AI review

answer-me-with-html

What it is — Questions come back as one HTML page: the model stops at a short Markdown draft, and the bundled am CLI draws layout plus flow, sequence, tree, timeline and ER diagrams, tables and callouts.

Who it is for — You are in DeepSeek Harness unpacking a handshake, a repo module map, or Redis versus Memcached, and a terminal transcript cannot show the structure. Skip it if the agent only patches code and runs tests, or if answers already land in a docs repo you maintain—the extra file has no place in that path.

Watch out — In a fresh profile it installed and the harness registered it. Node.js 20 or newer is required, and the bundled am CLI is invoked through the shell. Their Claude Sonnet 5.5 numbers on a plain Claude Code setup: model-written tokens about 4,893 versus 612, 31 s versus 12 s, bill down only about 15% because each turn still reads the system prompt, the question and the thread.

The verdict — I would enable it on a profile reserved for explainers I will send or reopen, and leave it off sessions that die in the terminal.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Details

skillhub

iflytek

5.3k

Browse and search a SkillHub registry and manage local skill installation, updates, and removal inside DeepSeek Harness. Targets DSH 0.2.0-rc.2 and 0.2.1-rc.2; not yet compatible with 0.2.1-rc.3.

No one-line install — this plugin lives inside a larger repository and publishes no npm package.

GitHub sourceJava25d ago

AI review

skillhub

What it is — A DeepSeek Harness plugin that queries a SkillHub registry and installs, updates, or removes skills on the local machine.

Who it is for — You do agent work inside DeepSeek Harness while the skills your team actually reuses already live in a SkillHub you can reach, and you are still jumping out to fetch packages. If skills move as git repos or shared folders and your day is not spent in DSH, skip this plugin.

Watch out — It is not published as a one-command package; you have to wire it from a repository subdirectory. It runs shell commands and expects an API key or token. It targets DSH 0.2.0-rc.2 and 0.2.1-rc.2 and is not compatible with 0.2.1-rc.3.

The verdict — This is not a reason to introduce SkillHub; I would only attach it after a registry is already how skills get distributed.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
2Source

dashi-taskboard

chuspeeism

3.4k

现代化可灵活嵌入的任务面板,支持 Codex、DeepSeek Harness

Installed cleanly when we ran it

GitHub sourceJavaScript19d ago

AI review

dashi-taskboard

What it is — A local-first issue board whose HTTP API feeds both a browser UI and taskctl, with a CDP path into Codex.

Who it is for — You are cutting slices in the Codex desktop app and need the agent to inspect issues and move their status on a machine-local board. If DeepSeek Harness is your only surface and you expect a matching in-harness panel after install, skip it—the writeup never describes that UI, only Codex injection and desktop apps.

Watch out — On a clean profile it installed and the harness registered it. It runs shell commands and wants an API key or token; the service needs Node.js 22.5 or newer. The Codex launcher or injector has to stay running while the panel is used, and desktop builds add Rust 1.88 plus Xcode or Visual Studio Build Tools.

The verdict — I would keep it for the Skill’s last gate—done only after I accept—not because it registered.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
2Source

vox-director

Alisa0808

2.5k

Turn one topic into a finished Vox-style paper-collage explainer/ad video — automated end to end on Atlas Cloud + ffmpeg. An agent skill.

Installed cleanly when we ran it

GitHub sourcePython1mo ago

AI review

vox-director

What it is — An agent skill that takes one topic through beat maps, collage posters, motion, voice-over, music and burned-in captions and writes a Vox paper-collage mp4 .

Who it is for — You are cutting explainer or ad shorts inside Claude Code or Codex from a topic line, a talking-head, or a product still, and you lack a skill that owns that collage path. Skip it if you only need to swap narration or BGM on an edit that already exists; this is not a detachable TTS plugin and it re-enters through beats.json .

Watch out — It calls Atlas Cloud for image, i2v , TTS and music, then shells out to local ffmpeg.You approve the beat map and pick a look by eye before the rest runs. Sandbox: it installed on a fresh profile and the harness registered it.

The verdict — I leave it registered and judge from the first posters; thin paper texture and I pull it rather than debug the video stage.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Source
1.9k

Daily radar for new AI terms: names of new models, products and repos, caught on X, Hugging Face, GitHub and sitemaps before keyword tools list them.

Installed cleanly when we ran it

GitHub sourcePython21d ago

AI review

new-term-radar

What it is — Collects new AI model, product and repo names from X, Hugging Face, GitHub and sitemaps, ahead of keyword tools.

Who it is for — You are writing pages for an AI-tool site or picking the day's newsletter lead, and you need names that just surfaced. If your DeepSeek Harness work is code and agent wiring, this list has no downstream.

Watch out — It installed on a fresh profile and DeepSeek Harness registered it. X and new-site signals need an AIsa key and bill per run; Hugging Face, GitHub and sitemaps do not. It executes shell commands.

The verdict — I would keep it only as a daily report habit; a one-off name check is not worth a plugin slot.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Source