Vitepress Skilld logo

Vitepress Skilld

Organization
skilld-dev
vitepress-skilld

Vite & Vue powered static site generator. ALWAYS use when writing code importing "vitepress". Consult for debugging, best practices, or modifying vitepress.

Overview

Publisherskilld-dev
Repositoryvue-ecosystem-skills
Skill namevitepress-skilld
Stars
180
Forks
8
Bundled files
337
LicenseMIT
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.

  • 337 bundled files

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

  • Open source

    Published by skilld-dev on GitHub. Read the source before you install it.

Installation

Install the Vitepress Skilld 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.
  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/skilld-dev/vue-ecosystem-skills.git /tmp/vue-ecosystem-skills
mkdir -p .claude/skills
cp -r /tmp/vue-ecosystem-skills/skills/vitepress-skilld .claude/skills/vitepress-skilld
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Vitepress Skilld 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 Vitepress Skilld 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 Vitepress Skilld 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.

vuejs/vitepress vitepress@1.6.4

Tags: latest: 1.6.4, next: 2.0.0-alpha.17

References: Docs

API Changes

This section documents version-specific API changes — prioritize recent major/minor releases.

  • BREAKING: pathname:// — protocol dropped in v1.0.0-rc.9, use target="_self" or target="_blank" instead source

  • BREAKING: shikiSetup — renamed from shikijiSetup in v1.0.0-rc.41 following the migration from shikiji back to shiki source

  • BREAKING: sidebar items — children key was renamed to items in v1.0.0, and top-level items no longer support link source

  • BREAKING: collapsed — replaced collapsible sidebar option in v1.0.0-alpha.44; collapsed: true implies collapsible source

  • BREAKING: markdown.headers — disabled by default since v1.0.0-alpha.57; PageData no longer includes headers unless explicitly enabled source

  • NEW: onAfterPageLoad — router hook added in v1.4.0, triggered after the page is loaded and before it is rendered source

  • NEW: onBeforePageLoad — router hook added in v1.0.0-beta.4, allows executing logic before a page load starts source

  • NEW: useData().hash — new property in v1.1.0 that provides a reactive reference to the current URL hash source

  • NEW: useSidebar() — exposed in v1.0.0-beta.4, provides access to sidebar state and logic in custom themes source

  • NEW: defineClientComponent() — helper added in v1.0.0-alpha.59 for creating components that only render on the client source

  • NEW: onContentUpdated — hook now triggers on frontmatter-only changes as of v1.4.0 source

  • NEW: createContentLoader() — helper added in v1.0.0-alpha.53 to load content from markdown files with glob support source

  • NEW: mergeConfig() — utility exported in v1.0.0-rc.25 to assist in merging VitePress configurations source

  • NEW: appearance: 'force-auto' — new option added in v1.3.0 to force color scheme based on user system preference source

Also changed: PageData.filePath new alpha.75 · Theme.extends new alpha.50 · Theme.setup deprecated alpha.50 · Theme.NotFound deprecated alpha.50 · on-demand social icons experimental v1.5.0 · externalLinkIcon option new beta.4 · cleanUrls stable alpha.41 · metaChunk experimental beta.6 · rewrites experimental alpha.41 · sitemap experimental beta.7

Best Practices

  • Use createContentLoader for archives and indexes over manual data loading — automatically handles caching and minimizes client-side JSON weight source
ts
import { createContentLoader } from 'vitepress'
export default createContentLoader('posts/*.md', { excerpt: true })
  • Wrap browser-only components with defineClientComponent — prevents SSR/SSG build failures when libraries access window or document on import source
vue
<script setup>
import { defineClientComponent } from 'vitepress'
const ClientOnlyComp = defineClientComponent(() => import('./BrowserComponent.vue'))
</script>
  • Prefer relative URLs for images and assets in Markdown — enables Vite's hashing pipeline and automatic base64 inlining for small files source

  • Use the withBase() helper for dynamic paths in theme components — ensures assets resolve correctly regardless of the site's deployment base URL source

  • Enable cleanUrls: true only when server-side support is confirmed — prevents broken direct links on platforms that do not automatically map /foo to /foo.html source

  • Target rewritten paths for relative links when using rewrites — links must resolve against the final URL structure, not the source directory structure source

  • Pass large Markdown or HTML blocks via the content property in dynamic route loaders — prevents bloating the client-side JavaScript payload with serialized params source

js
// [pkg].paths.js
export default {
  async paths() {
    return [{ params: { id: '1' }, content: '## Large Content' }]
  }
}
  • Use <script client> for minimal interactivity in MPA mode — standard <script setup> in MPA mode is used for server-side templating only and lacks reactivity source

  • Programmatically exclude pages from search via the _render hook — allows complex filtering logic based on file path or frontmatter during the indexing phase source

ts
// .vitepress/config.ts
themeConfig: {
  search: {
    provider: 'local',
    options: {
      _render(src, env, md) {
        if (env.frontmatter?.search === false) return ''
        return md.render(src, env)
      }
    }
  }
}
  • Employ defineConfigWithTheme<DefaultTheme.Config> for site configuration — provides full TypeScript inference and validation for both core and default theme settings source

Bundled files

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

and 140 more files.

Frequently asked questions

What does the Vitepress Skilld AI skill do?

Vite & Vue powered static site generator. ALWAYS use when writing code importing "vitepress". Consult for debugging, best practices, or modifying vitepress.

Why use Vitepress Skilld on TypingMind?

Because you install it once and use it with any model. Vitepress Skilld 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 Vitepress Skilld in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/skilld-dev/vue-ecosystem-skills/tree/main/skills/vitepress-skilld. 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 Vitepress Skilld?

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 Vitepress Skilld?

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

Is the Vitepress Skilld AI skill free?

Yes. It is published on GitHub by skilld-dev under the MIT license. 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 👇