Make Content Editable logo

Make Content Editable

Organization
nuxt-content
make-content-editable

Converts hardcoded Vue components in a Nuxt Content markdown file into slot-based, Studio-editable MDC components. Use when a user wants their Nuxt Content page to be visually editable in Nuxt Studio's TipTap editor.

Overview

Publishernuxt-content
Repositorynuxt-studio
Skill namemake-content-editable
Stars
724
Forks
146
Bundled files
6
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.

  • 6 bundled files

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

  • Open source

    Published by nuxt-content on GitHub. Read the source before you install it.

Installation

Install the Make Content Editable 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/nuxt-content/nuxt-studio.git /tmp/nuxt-studio
mkdir -p .claude/skills
cp -r /tmp/nuxt-studio/skills/make-content-editable .claude/skills/make-content-editable
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Make Content Editable 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 Make Content Editable 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 Make Content Editable 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.

Make Content Editable

Convert hardcoded Vue components found in a markdown file into slot-based, Nuxt Studio-editable MDC components.

References

Consult these files as you work through each step:

FileWhen to consult
references/vue-slots.mdSlot naming conventions, props vs slots, mdc-unwrap, interactive components
references/mdc-syntax.mdColon depth, indentation, slot ordering, parse errors
references/nuxt-studio.mdWhy slots = editable regions, v-show rule
references/nuxt-components.mdNuxt component auto-discovery, props, default/named slots
references/nuxt-ui-components.mdUPageHero/UCard slot API, :ui overrides, text-center quirk
references/tailwind-purging.mdStatic lookup maps for color props

Goal

Produce a 1:1 visual match of every original rendered component, with all content moved into MDC slots and props so it is editable in Nuxt Studio's TipTap editor.


Step 0 — Select file and components

0a — Pick the file: Glob content/**/*.md (also .mdoc, .markdown). Present the list via AskUserQuestion (single-select).

0b — Pick the components: Read the chosen file. Extract every component reference (block ::name and inline :name), deduplicate, find and read each Vue file. Present the list via AskUserQuestion (multiSelect: true), showing for each: name + one-line summary of whether it has hardcoded content or is already slot/prop-driven.

0c — Confirm: Single-select confirmation before any conversion begins. If the user goes back, repeat 0b.

Process each confirmed component through Steps 1–5.


Step 1 — Read and analyse the component

Read the component file in full. If it uses Nuxt UI components, call mcp__nuxt-ui__get-component (sections: ["theme"]) and mcp__nuxt-ui__get-component-metadata to look up their slot API first.

Classify each element (see references/vue-slots.md — Slot Naming Conventions):

ElementBecomes
Hardcoded text (headings, labels, paragraphs)Named slot
Repeated items (cards, tabs)Child component with its own slots
Icon name, URL, booleanProp
Color/variant differing between siblingscolor prop + static lookup map
Interactive logic (tab switching, accordions)Hardcoded inside component — not a slot

Identify visual render order top-to-bottom — this is the required slot order in MDC.

Check if the project uses Nuxt UI and whether a layout component (UPageHero, UPageSection, UPageCard) already matches the visual pattern — prefer wrapping over reimplementing.


Step 2 — Design the component tree

Name components generically (reusable across pages, not tied to a specific page):

  • One parent section (HomeHero, LandingFeatures)
  • One collection wrapper for repeated items (FeatureList)
  • One item component per repeated element (FeatureCard)
  • One component per interactive sub-section (CodePlayground)

Align slot names with the naming table in references/vue-slots.md. If wrapping Nuxt UI, match its slot API 1:1 so slots can be forwarded without renaming.


Step 3 — Create the Vue components

Slots: <slot name="..." mdc-unwrap="p" /> for editable text. Add mdc-unwrap="p" for slots inside headings or <p> tags. See references/vue-slots.md.

Props: defineProps for icon names, URLs, booleans, colors. Never use props for content editors need to type.

Colors: When siblings differ visually, add a color prop with a static lookup map — never build Tailwind classes dynamically. See references/tailwind-purging.md.

Nuxt UI wrapping: Forward slots via <template #slotName><slot name="slotName" /></template>. Use v-if="$slots.slotName" for optional decorative slots. Override :ui instead of adding wrapper divs to reset styles. See references/nuxt-ui-components.md.

Interactive components: Keep state inside the component. Use v-show (not v-if) so all slot content stays mounted.

Script tag: Only add <script setup> when there are props, refs, or computed values.


Step 4 — Update the MDC in the markdown file

Replace each component usage. See references/mdc-syntax.md for colon depth, indentation, and parse error reference.

Key rules:

  • Slots appear in visual DOM order (top to bottom)
  • Plain-text slots (#headline, #title, #description) before slots containing nested components (#body, #footer)
  • Short config → inline props {key="value"}; multiple/complex → YAML frontmatter
  • #default works for simple single-slot components; use named slots when nested children share slot names (#title, #description) to avoid parse errors

Step 5 — Verify visual parity

Compare every element against the original:

  • Same section padding and container width
  • Same heading text, size, weight
  • Same description text and size
  • Same badge/headline label and icon
  • Same interactive controls with same labels and icons
  • Same code snippets verbatim
  • Same number of cards/items in same order
  • Same icon and color per card/item (check ALL siblings — colors often differ)
  • Content sections not text-centered if the original wasn't

Fix any discrepancy before moving to the next component.


Step 6 — Update memory

After all components are converted, save any new patterns or edge cases to the project memory file.

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 Make Content Editable AI skill do?

Converts hardcoded Vue components in a Nuxt Content markdown file into slot-based, Studio-editable MDC components. Use when a user wants their Nuxt Content page to be visually editable in Nuxt Studio's TipTap editor.

Why use Make Content Editable on TypingMind?

Because you install it once and use it with any model. Make Content Editable 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 Make Content Editable in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/nuxt-content/nuxt-studio/tree/main/skills/make-content-editable. 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 Make Content Editable?

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 Make Content Editable?

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

Is the Make Content Editable AI skill free?

Yes. It is published on GitHub by nuxt-content 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 👇