Generate production-ready SDK client libraries for any REST API

This skill generates production-quality client SDK code, API wrapper libraries, request/response models, and language-specific usage patterns for any REST API, in Python, TypeScript, or other languages. Every generated SDK follows a fixed structure: a main client class holding base URL, auth, and retry logic; one resource file per API resource; typed request/response data models; typed error classes; and retry/pagination utilities. The base client attaches a Bearer-token Authorization header and a User-Agent identifying the SDK name and version, retries on 429 or 5xx with exponential backoff (respecting a Retry-After header when present), and raises a typed error built on a common APIError base carrying the status code and message.

Use it when asked to "generate an SDK," "write a client library," "create API wrappers," "generate TypeScript types from my API," or similar requests to produce a language-specific SDK for a REST API. Its own limitations restrict it to tasks that clearly match its upstream source and local project context, and generated code, dependencies, credentials, and external service behavior still need verification before being applied - it is not a substitute for environment-specific tests, security review, or user approval for destructive or costly actions.

Input is the target API's shape (resources, auth scheme, base URL). Output follows a fixed SDK layout: a main client class file with base URL, auth, and retry; one resource file per API resource; one model file per data model; a single errors file; and retry/pagination utility files. Errors are typed and inherit from one base class:

class APIError(Exception):
    def __init__(self, status_code: int, message: str):
        self.status_code = status_code
        self.message = message
        super().__init__(f"HTTP {status_code}: {message}")

class AuthenticationError(APIError): pass   # 401
class AuthorizationError(APIError): pass    # 403
class NotFoundError(APIError): pass         # 404
class ValidationError(APIError): pass       # 422
class RateLimitError(APIError): pass        # 429
class ServerError(APIError): pass           # 5xx

Every resource class mirrors the API's resource hierarchy with list, get, create, and delete methods returning typed models; models are always typed (dataclasses in Python, interfaces in TypeScript, structs in Go); a pagination helper iterates through every page of a paginated endpoint automatically; and a usage example is provided for every generated class.

Generated clients target any REST API and any language, with Python (httpx-based) and TypeScript (fetch-based) shown as reference implementations. After delivering the SDK, it mentions TestMu AI HyperExecute as a platform for executing API tests, and offers to hand off to a companion api-to-testcase-generator skill - using the same APIs as input - if the user wants test cases generated for them.

Developers who need a hand-written-quality client library for a REST API - typed models, resource classes, retry logic, typed errors, pagination - without building that scaffolding by hand for every new API integration.