Extension Development logo

Extension Development

OrganizationPopular
nimbalyst
extension-development

Build, install, and hot-reload Nimbalyst extensions using MCP tools. Use when developing, testing, or iterating on Nimbalyst extensions.

Overview

Publishernimbalyst
Repositorynimbalyst
Skill nameextension-development
Stars
1.9K
Forks
300
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 nimbalyst on GitHub. Read the source before you install it.

Installation

Install the Extension Development 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/nimbalyst/nimbalyst/tree/main/packages/extensions/extension-dev-kit/claude-plugin/skills/extension-development
  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/nimbalyst/nimbalyst.git /tmp/nimbalyst
mkdir -p .claude/skills
cp -r /tmp/nimbalyst/packages/extensions/extension-dev-kit/claude-plugin/skills/extension-development .claude/skills/extension-development
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Extension Development 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 Extension Development 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 Extension Development 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.

Extension Development in Nimbalyst

Nimbalyst provides MCP tools for building, installing, and hot-reloading extensions directly from within the running app. This enables rapid iteration on extension development without manually running build commands.

The recommended in-app scaffold flow uses File > New Extension Project, Developer > New Extension Project, or the Extension Developer Kit's /new-extension command. Enable Extension Dev Tools in Settings > Advanced before using the build/install workflow.

Available MCP Tools

Build Extension

mcp__nimbalyst-extension-dev__extension_build

Runs the project's build script (usually vite build) with pnpm if the project uses pnpm, npm otherwise.

Parameters:

  • path: Absolute path to the extension project root (directory containing package.json and manifest.json)

Returns: Build output including any errors or warnings.

Install Extension

mcp__nimbalyst-extension-dev__extension_install

Installs a built extension into the running Nimbalyst instance. The extension must be built first.

Parameters:

  • path: Absolute path to the extension project root

Returns: Installation status and any validation warnings.

Hot Reload Extension

mcp__nimbalyst-extension-dev__extension_reload

Rebuilds and reinstalls an extension in one step. This is the most common tool for iterating on extension development.

Parameters:

  • extensionId: The extension ID from manifest.json (e.g., "com.nimbalyst.my-extension")
  • path: Absolute path to the extension project root

Returns: Build and reload status.

Uninstall Extension

mcp__nimbalyst-extension-dev__extension_uninstall

Removes an installed extension from the running Nimbalyst instance.

Parameters:

  • extensionId: The extension ID to uninstall

Get Extension Status

mcp__nimbalyst-extension-dev__extension_get_status

Gets the current status of an installed extension, including whether it loaded successfully and what it contributes.

Parameters:

  • extensionId: The extension ID to query

Restart Nimbalyst

mcp__nimbalyst-extension-dev__restart_nimbalyst

Restarts the entire Nimbalyst application. Only use when explicitly requested by the user.

Testing Tools

Run Playwright Tests

mcp__nimbalyst-extension-dev__extension_test_run

Execute Playwright scripts against the running Nimbalyst instance via CDP. Supports inline scripts or .spec.ts file paths.

Parameters:

  • script: Inline Playwright code (runs inside an async test with page connected to Nimbalyst)
  • testFile: Absolute path to a .spec.ts file
  • timeout: Max execution time in ms (default: 30000)

Provide either script or testFile, not both.

Open File for Testing

mcp__nimbalyst-extension-dev__extension_test_open_file

Opens a file in Nimbalyst and waits for the editor to mount. Use before running tests that need a specific file open.

Parameters:

  • filePath: Absolute path to the file to open
  • waitForExtension: Extension ID to wait for (waits until the extension's editor container renders)
  • timeout: Max wait time in ms (default: 5000)

Test AI Tool Handler

mcp__nimbalyst-extension-dev__extension_test_ai_tool

Execute an extension's AI tool handler directly and return the result. Bypasses full MCP routing.

Parameters:

  • extensionId: The extension ID
  • toolName: Tool name without extension prefix (e.g., "get_elements")
  • args: Arguments object to pass to the handler
  • filePath: For editor-scoped tools: file path for context

Development Workflow

Initial Setup

  1. Create extension project with /new-extension <path> <name> [file-patterns]
  2. Implement the extension code
  3. Build with extension_build
  4. Install with extension_install
  5. Test in Nimbalyst

Iteration Loop with Testing

  1. Make code changes
  2. Run extension_reload to rebuild and reinstall
  3. Run extension_get_status to verify it loaded
  4. Run extension_test_open_file to open a sample file
  5. Run extension_test_run with Playwright scripts to verify behavior
  6. Use capture_editor_screenshot for visual verification
  7. Check get_renderer_debug_logs for runtime errors
  8. Fix issues and repeat from step 1

Inline test example:

extension_test_run({
  script: `
    const editor = page.locator('[data-extension-id="com.nimbalyst.my-ext"]');
    await expect(editor).toBeVisible();
    await editor.locator('.save-btn').click();
    await expect(editor.locator('.status')).toHaveText('Saved');
  `
})

Test file example:

extension_test_run({ testFile: "/path/to/extension/tests/basics.spec.ts" })

Debugging

  1. Check extension status with extension_get_status
  2. Read logs with mcp__nimbalyst-extension-dev__get_main_process_logs (filter by component: "EXTENSION")
  3. Check renderer logs with mcp__nimbalyst-extension-dev__get_renderer_debug_logs

Important Notes

  • Always build before install - extension_install requires a pre-built extension
  • Use extension_reload for iteration - It combines build + reinstall in one step
  • Check manifest validation - Build and install tools validate manifest.json and report warnings
  • Extensions load on app start - For full reload, user may need to restart Nimbalyst
  • Never restart without permission - Only use restart_nimbalyst when the user explicitly asks

Common Issues

"Extension not found" after install

  • Check that the extension ID in manifest.json matches what you're querying
  • Verify the build output exists in dist/index.js

Build fails

  • Check that dependencies were installed in the extension directory (pnpm install or npm install, matching its lockfile)
  • Verify vite.config.ts is properly configured
  • Check for TypeScript errors in the output

Extension doesn't appear

  • Use extension_get_status to check if it's loaded
  • Check the release channel - some extensions require "alpha" channel
  • Verify the extension is enabled in Settings > Extensions

Frequently asked questions

What does the Extension Development AI skill do?

Build, install, and hot-reload Nimbalyst extensions using MCP tools. Use when developing, testing, or iterating on Nimbalyst extensions.

Why use Extension Development on TypingMind?

Because you install it once and use it with any model. Extension Development 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 Extension Development in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/nimbalyst/nimbalyst/tree/main/packages/extensions/extension-dev-kit/claude-plugin/skills/extension-development. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Extension Development?

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 Extension Development?

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

Is the Extension Development AI skill free?

Yes. It is published on GitHub by nimbalyst 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 👇