Zaidan logo

Zaidan

Organization
nightly-labs
zaidan

Install and configure the Zaidan component registry in an existing SolidJS codebase, and recommend Zaidan components for a product or interaction need. Use when setting up Zaidan, adding Zaidan components, fixing consumer-side registry configuration, or deciding which Zaidan components to compose for a SolidJS interface.

Overview

Publishernightly-labs
Repositoryopenbot
Skill namezaidan
Stars
521
Forks
81
Bundled files
3
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by nightly-labs on GitHub. Read the source before you install it.

Installation

Install the Zaidan AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/nightly-labs/openbot/tree/main/.agents/skills/zaidan
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/nightly-labs/openbot.git /tmp/openbot
mkdir -p .claude/skills
cp -r /tmp/openbot/.agents/skills/zaidan .claude/skills/zaidan
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Zaidan in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Zaidan on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Zaidan is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Zaidan

Use this skill for consumer-side work in a SolidJS application. Treat Zaidan as a source-code registry: configure the project, select suitable components, add them with the registry CLI, and verify the resulting SolidJS code.

Use shadcn-to-zaidan instead when the task is to import, sync, transform, or maintain a shadcn-style React component inside the Zaidan registry.

Load References

  • Read references/installation.md before installing, configuring, adding, or troubleshooting Zaidan in a project.
  • Read references/component-selection.md when recommending components or deciding how to compose a requested interface.

What the Registry Holds

One @zaidan registry serves several kinds of item. Knowing which kind a name is tells you what the CLI will write.

KindNamesWhat lands in the project
Componentsbutton, dialog, sidebar, …Source files under the ui alias
Blockssortable, image-crop, message-scroller, questionnaire, and the chart examples (chart-bar-default, chart-line-interactive, …)Larger compositions plus the components they use
Hookuse-mobileSource file under the hooks alias
Shared componentcolor-modeSource file under the components alias
Stylesstyle-vega, style-nova, style-maia, style-lyra, style-mira, style-luma, style-sera, style-rheastyles/base.css and styles/utilities.css, plus their imports
Base colors and themesneutral, stone, zinc, gray, mauve, olive, mist, taupe; blue, green, …Light and dark CSS variables
Chart paletteschart-blue, chart-neutral, …chart-1 … chart-5 only
Radiusradius-none, radius-small, radius-medium, radius-large--radius
Fontsfont-inter, font-geist-mono, …The face, wired to --font-sans, --font-serif, or --font-mono
Typesettypesetstyles/typeset.css and its import

Two items are generated from a code rather than listed in the registry:

  • @zaidan/preset-<code> — a whole design system (style, base color, theme, chart palette, fonts, radius, menu accent) from a code produced by https://zaidan.carere.dev/create.
  • @zaidan/typeset-<code> — the typeset stylesheet, the fonts a design uses, and its .typeset-<item> preset class, from a code produced by https://zaidan.carere.dev/typeset.

Both resolve over the CLI even though no listing entry exists for them. Prefer a preset over a hand-assembled list of style, color, radius, and font items when the user wants a full design system.

Workflow

  1. Inspect package.json, the lockfile, framework configuration, TypeScript aliases, global CSS, and components.json when present. Identify the SolidJS framework, package manager, Tailwind version, existing aliases, and current Zaidan style before editing.
  2. Translate the user's request into interaction needs. Recommend the smallest useful component set and explain the role of each component. Distinguish alternatives such as select versus combobox, dialog versus alert-dialog, and sheet versus drawer.
  3. Verify recommended item names against the current registry before presenting an install command. In this repository, inspect src/registry/kobalte/registry.json; elsewhere, resolve the corresponding https://zaidan.carere.dev/r/kobalte/<name>.json item. @zaidan/preset-<code> and @zaidan/typeset-<code> are the exception: they are generated on demand from the code, so they resolve without appearing in the registry listing.
  4. Configure only missing prerequisites. Preserve the project's package manager, framework conventions, aliases, CSS entry point, theme choices, and existing components.json values.
  5. Add the selected components through the configured @zaidan registry. Let registry metadata install transitive Zaidan items and npm dependencies.
  6. Inspect the generated files and imports. Adapt the user's application only when requested; installing components alone does not imply building a feature with them.
  7. Run the smallest relevant formatting, typecheck, or build command available in the target project. Report the configuration changed, components added, commands run, and any remaining integration work.

Recommendation Standard

Base recommendations on behavior, not visual resemblance alone. Account for:

  • the information or action the interface must expose;
  • whether content is persistent, contextual, modal, or transient;
  • keyboard, focus, dismissal, and validation behavior;
  • data size, search needs, touch use, and responsive layout;
  • existing components already installed in the project.

Lead with one recommended composition. Mention an alternative only when a real product decision changes the choice. State when Zaidan supplies primitives but the requested product pattern still needs application-owned state, data loading, validation, or layout.

Boundaries

  • Keep generated components as editable application source; do not add a runtime zaidan package.
  • Use SolidJS imports and syntax in consumer examples.
  • Prefer the registry CLI over copying source files by hand.
  • Keep registry-authoring, React-to-Solid transformation, release syncing, Zaidan documentation, and registry manifest maintenance in shadcn-to-zaidan.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Zaidan AI skill do?

Install and configure the Zaidan component registry in an existing SolidJS codebase, and recommend Zaidan components for a product or interaction need. Use when setting up Zaidan, adding Zaidan components, fixing consumer-side registry configuration, or deciding which Zaidan components to compose for a SolidJS interface.

Why use Zaidan on TypingMind?

Because you install it once and use it with any model. Zaidan is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Zaidan in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/nightly-labs/openbot/tree/main/.agents/skills/zaidan. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Zaidan?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Zaidan?

As many as you like. As long as a model supports skills, you can use Zaidan with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Zaidan AI skill free?

It is published on GitHub by nightly-labs. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇