Create Rolldown Plugin logo

Create Rolldown Plugin

OrganizationPopular
videojs
create-rolldown-plugin

Create Rolldown plugins. Use for hooks.

Overview

Publishervideojs
Repositoryv10
Skill namecreate-rolldown-plugin
Stars
1K
Forks
93
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

    Published by videojs on GitHub. Read the source before you install it.

Installation

Install the Create Rolldown Plugin 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/videojs/v10/tree/main/.agents/skills/create-rolldown-plugin
  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/videojs/v10.git /tmp/v10
mkdir -p .claude/skills
cp -r /tmp/v10/.agents/skills/create-rolldown-plugin .claude/skills/create-rolldown-plugin
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Create Rolldown Plugin 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 Create Rolldown Plugin 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 Create Rolldown Plugin 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.

Rolldown plugin implementation

Inspect the installed Rolldown version, relevant package config and exports, neighboring plugins, and host-level tests before choosing hooks. Prefer a Rolldown plugin when the behavior is about modules or build output rather than Vite configuration, HTML, the dev server, or HMR.

Workflow

  1. Define the host contract first: selected modules, source shape entering and leaving each hook, virtual IDs, graph information required, output ownership, watch inputs, and whether the plugin is safe in ordinary application builds or only a dedicated build. Use transform for source-module semantics and renderChunk only when the edit depends on final generated chunks or output options.
  2. Let Rolldown own resolution, traversal, ordering, caching, watching, and output. Use this.resolve, normal graph entries, this.addWatchFile, and this.emitFile; do not invoke another compiler plugin directly or start a nested build to simulate the host graph.
  3. Use host-native object hook filters for resolveId, load, and transform. Keep a matching handler guard only when compatibility with hosts lacking the filter is intentional and tested. Normalize query-bearing IDs without dropping parameters that distinguish transformed module identities.
  4. Keep virtual modules private unless consumers genuinely import them. Prefix internal IDs with \0, resolve them explicitly, return the correct moduleType, and add every non-imported source dependency as a watch file.
  5. Keep mutable state per plugin instance and reset build-derived state in buildStart. Prefer module meta for JSON-serializable information that must survive later transforms or host caching; namespace it and explicitly merge updates within that namespace because hook results merge meta only one level deep. Read graph-wide information no earlier than buildEnd unless the hook contract guarantees completeness.
  6. Extend existing input rather than replacing it. Use packages/vjsc/src/plugins/input.ts in VJSC. Remember that an options() result does not deep-merge input, while an emitted chunk follows chunk naming unless fileName is forced.
  7. Emit generated output with this.emitFile. Do not write staging source. Never delete unrelated chunks or assets; complete bundle replacement is valid only for an explicitly asset-only build with tests proving the boundary.
  8. When transform or renderChunk consumes host-provided magicString, explicitly enable experimental.nativeMagicString: true in the owning Rolldown input config. In tsdown, configure it under inputOptions.experimental. Return the native object rather than stringifying it so Rolldown can compose maps, enable output sourcemap when consumers need emitted maps, and fail clearly if a repository-owned host violates this contract. Reserve JavaScript fallbacks for intentional compatibility adapters.
  9. Test through real Rolldown builds. Cover existing entries, virtual resolution and module type, filters, query identities, static/dynamic/type-only dependencies, graph timing, watched inputs, rebuild state, output names/content, and path or name collisions.

Read references/api-and-host-contracts.md when the plugin uses virtual entries, graph inspection, editable source capture, inter-plugin communication, declarations, or output replacement.

Use packages/vjsc/src/plugins/vjsc.ts as the transform-pipeline anchor, packages/vjsc/src/plugins/component-schema.ts for virtual package entries and declaration-aware hosts, and packages/vjsc/src/plugins/shadcn.ts for a dedicated asset build.

Validation

Run the narrow plugin tests, the owning package build, host-consumer tests, pnpm typecheck, and pnpm check:workspace. If the plugin claims Vite compatibility, exercise the same contract through both Rolldown and Vite rather than relying on structural types alone.

Example

Input: “Create a build plugin that publishes transformed component metadata as JSON.”

Output: One Rolldown plugin that loads components through the host graph, retains namespaced metadata, assembles complete graph data at the proper hook, watches discovery inputs, emits JSON assets, preserves unrelated output, and has direct Rolldown plus host-compatibility tests.

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 Create Rolldown Plugin AI skill do?

Create Rolldown plugins. Use for hooks.

Why use Create Rolldown Plugin on TypingMind?

Because you install it once and use it with any model. Create Rolldown Plugin 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 Create Rolldown Plugin in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/videojs/v10/tree/main/.agents/skills/create-rolldown-plugin. 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 Create Rolldown Plugin?

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 Create Rolldown Plugin?

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

Is the Create Rolldown Plugin AI skill free?

It is published on GitHub by videojs. 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 👇