Config logo

Config

OrganizationPopular
kubb-labs
config

How to author a kubb.config.ts and pick the right @kubb/plugin-* packages when generating TypeScript from an OpenAPI/Swagger spec. Use whenever setting up Kubb, adding a generator, or debugging codegen output.

Overview

Publisherkubb-labs
Repositorykubb
Skill nameconfig
Stars
1.8K
Forks
147
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 kubb-labs on GitHub. Read the source before you install it.

Installation

Install the Config 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/kubb-labs/kubb.git /tmp/kubb
mkdir -p .claude/skills
cp -r /tmp/kubb/tools/claude/skills/config .claude/skills/config
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Config 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 Config 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 Config 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.

Config Skill

This skill instructs agents on authoring a kubb.config.ts and picking the right @kubb/plugin-* packages. Generation runs through the kubb CLI (kubb generate), and the same build powers the bundled MCP server.

When to Use

  • Setting up Kubb in a project
  • Adding or swapping a generator plugin
  • Debugging why generated output is missing or wrong

What It Does

  • Shows the shape of a kubb.config.ts
  • Lists the generator plugins and how to combine them
  • Points at each plugin's Options type and kubb.dev docs page for authoritative options
  • Describes the validate, init and generate workflow

Shape of a config

ts
import { defineConfig } from 'kubb'
import { pluginTs } from '@kubb/plugin-ts'
import { pluginAxios } from '@kubb/plugin-axios'

export default defineConfig({
  root: '.',
  input: {
    path: './petstore.yaml', // local file path or a remote URL
  },
  output: {
    path: './src/gen',
    clean: true, // wipe the output dir before each run
    barrel: { type: 'named' }, // generate index.ts barrels with named exports
  },
  plugins: [
    pluginTs({ output: { path: 'models' } }),
    pluginAxios({ output: { path: 'clients' } }),
  ],
})

Rules that matter:

  • Set adapter options only when you need them, through a top-level adapter: adapterOas({ ... }) from @kubb/adapter-oas (for validate, serverIndex, serverVariables, discriminator or contentType).
  • pluginTs is the base. The client plugins (pluginAxios, pluginFetch) need it, the framework plugins (pluginReactQuery, pluginVueQuery, pluginSwr) need pluginTs and a client plugin, and pluginMsw needs pluginTs and pluginFaker. Check the plugin's docs page on kubb.dev (https://kubb.dev/plugins/plugin-<name>) for the full dependency list.
  • Each generator plugin takes its own output.path, resolved relative to the top-level output.path. Keep generated kinds in separate folders (models, clients, hooks, ...).
  • input accepts { path } for a file or URL. Validate untrusted specs with kubb validate before generating.
  • Generation is destructive when output.clean is true. Never point output.path at hand-written source.
  • Set output.format or output.lint to 'auto' to format and lint generated files with whatever tool the project already has (oxfmt, Biome, Prettier, oxlint or ESLint).

Available generator plugins

Pick plugins by what the consumer needs, then install kubb plus each package.

NeedPackageImport
TypeScript types (recommended base)@kubb/plugin-tspluginTs
Axios client@kubb/plugin-axiospluginAxios
Fetch client@kubb/plugin-fetchpluginFetch
TanStack React Query hooks@kubb/plugin-react-querypluginReactQuery
Vue Query hooks@kubb/plugin-vue-querypluginVueQuery
SWR hooks@kubb/plugin-swrpluginSwr
Zod schemas@kubb/plugin-zodpluginZod
Faker.js mock factories@kubb/plugin-fakerpluginFaker
MSW request handlers@kubb/plugin-mswpluginMsw
Cypress fixtures@kubb/plugin-cypresspluginCypress
MCP server from the spec@kubb/plugin-mcppluginMcp
ReDoc documentation@kubb/plugin-redocpluginRedoc

For an installed plugin's exact options, read its Options type from the installed package (node_modules/@kubb/plugin-<name>/src/types.ts or the published type declarations) and the plugin's docs page (https://kubb.dev/plugins/plugin-<name>), which lists every option with defaults, the plugin dependencies, and the default output.path. Use those as the source of truth instead of guessing an option name.

Common combinations:

  • Types only: pluginTs().
  • Typed data fetching: add pluginAxios() or pluginFetch(), or a framework plugin (pluginReactQuery, pluginVueQuery or pluginSwr) which pulls in client generation.
  • Runtime validation: add pluginZod() and point the client at it for typed, validated responses.
  • Testing and mocks: add pluginFaker() and pluginMsw().

Workflow

The commands wrap the kubb CLI, so the same steps work from a terminal.

  1. Validate the spec with kubb validate <spec> before anything else.
  2. Scaffold and install with kubb init. Pass --input, --output and --plugins to skip the prompts, or write kubb.config.ts by hand using the shape above.
  3. Generate with kubb generate. Pass --verbose when diagnosing why a file is missing or malformed, and --watch to regenerate on spec changes.
  4. Typecheck the generated output and wire it into the app.

Related Skills

SkillUse For
../output/SKILL.mdImporting and using the generated code

Frequently asked questions

What does the Config AI skill do?

How to author a kubb.config.ts and pick the right @kubb/plugin-* packages when generating TypeScript from an OpenAPI/Swagger spec. Use whenever setting up Kubb, adding a generator, or debugging codegen output.

Why use Config on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kubb-labs/kubb/tree/main/tools/claude/skills/config. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Config?

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 Config?

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

Is the Config AI skill free?

Yes. It is published on GitHub by kubb-labs 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 👇