Plugin Creator logo

Plugin Creator

Community
JuliusBrussee
plugin-creator

Scaffold a complete cave plugin bundle — generates .cave-plugin/plugin.json manifest and the standard directory structure (commands/, skills/, agents/, themes/, hooks/). Use when a user wants to create, publish, or package a cave plugin for the marketplace. Triggered by "create a plugin", "scaffold a plugin", "/plugin create", or "new cave plugin".

Overview

PublisherJuliusBrussee
Repositorycaveman-code
Skill nameplugin-creator
Stars
942
Forks
107
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Plugin Creator 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/JuliusBrussee/caveman-code/tree/main/packages/coding-agent/skills/plugin-creator
  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/JuliusBrussee/caveman-code.git /tmp/caveman-code
mkdir -p .claude/skills
cp -r /tmp/caveman-code/packages/coding-agent/skills/plugin-creator .claude/skills/plugin-creator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Plugin Creator 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 Plugin Creator 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 Plugin Creator 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.

Plugin Creator

You scaffold new cave plugins. A cave plugin is a directory published to GitHub (or any zip URL) with a .cave-plugin/plugin.json manifest and optional sub-directories for commands, skills, agents, themes, and hooks.

Manifest Schema

json
{
  "name": "my-plugin",
  "version": "0.1.0",
  "description": "A short, clear description of what this plugin does.",
  "author": "your-github-handle",
  "license": "MIT",
  "homepage": "https://github.com/your-handle/my-plugin",
  "caveVersion": ">=0.65.0",
  "tags": ["productivity", "git"],
  "capabilities": {
    "commands": true,
    "skills": true,
    "agents": false,
    "themes": false,
    "mcp": false,
    "hooks": []
  }
}

Field Rules

  • name: kebab-case, a-z0-9 and hyphens only. Must be unique in the marketplace.
  • version: semver ("major.minor.patch").
  • description: one sentence, plain text.
  • tags: free-form strings for caveman plugin search matching.
  • capabilities.commands: set true if commands/ directory is present.
  • capabilities.skills: set true if skills/ directory is present.
  • capabilities.agents: set true if agents/ directory is present.
  • capabilities.themes: set true if themes/ directory is present.
  • capabilities.mcp: set true if .mcp.json is present.
  • capabilities.hooks: array of hook entries (see below).

Hook Entry Shape

json
{ "event": "PostToolUse", "command": "hooks/post-tool-use.sh", "matcher": "Bash" }

Directory Structure

my-plugin/
├── .cave-plugin/
│   └── plugin.json          ← required
├── commands/
│   └── my-command.md        ← markdown slash commands
├── skills/
│   └── my-skill/
│       └── SKILL.md         ← skill with frontmatter
├── agents/
│   └── my-agent.md          ← agent definition markdown
├── themes/
│   └── my-theme.json        ← theme JSON (cave theme format)
├── hooks/
│   └── post-tool-use.sh     ← hook scripts (chmod +x)
├── .mcp.json                ← optional MCP server definitions
└── README.md

Scaffolding Steps

When the user asks to create a plugin, follow these steps:

  1. Ask for plugin details (name, description, which capabilities are needed).
  2. Create .cave-plugin/plugin.json using the schema above.
  3. Create only the sub-directories that are needed (do not create empty dirs).
  4. Add placeholder files for each enabled capability:
    • commands/example.md with frontmatter ---\ndescription: Example command.\n---\n\n# Example\n\nDescribe what this command does.\n
    • skills/example/SKILL.md with the standard skill frontmatter.
    • agents/example.md with agent frontmatter.
    • hooks/example.sh with #!/bin/bash\n# Hook: <event>\n and chmod +x.
  5. Create a README.md with install instructions and a short description.
  6. Validate the manifest by echoing it back and checking all required fields.

Publishing

After scaffolding, instruct the user to:

  1. Push the plugin to a public GitHub repository.
  2. Submit it to a marketplace by adding an entry to a marketplace.json:
    json
    {
      "plugins": [
        {
          "ref": "your-handle/my-plugin",
          "name": "my-plugin",
          "description": "...",
          "tags": ["..."],
          "version": "0.1.0"
        }
      ]
    }
  3. Users install it with: caveman plugin install your-handle/my-plugin

Example Interaction

User: "Create a plugin that adds a /summarize command and a post-save hook."

You:

  1. Create .cave-plugin/plugin.json with "commands": true, "hooks": [{ "event": "PostToolUse", "command": "hooks/post-save.sh", "matcher": "Write" }].
  2. Create commands/summarize.md with a summarize slash command description.
  3. Create hooks/post-save.sh with a stub hook script.
  4. Create README.md.
  5. Report the file tree created.

Frequently asked questions

What does the Plugin Creator AI skill do?

Scaffold a complete cave plugin bundle — generates .cave-plugin/plugin.json manifest and the standard directory structure (commands/, skills/, agents/, themes/, hooks/). Use when a user wants to create, publish, or package a cave plugin for the marketplace. Triggered by "create a plugin", "scaffold a plugin", "/plugin create", or "new cave plugin".

Why use Plugin Creator on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/JuliusBrussee/caveman-code/tree/main/packages/coding-agent/skills/plugin-creator. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Plugin Creator?

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 Plugin Creator?

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

Is the Plugin Creator AI skill free?

Yes. It is published on GitHub by JuliusBrussee 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 👇