Skip to content

AI coding

Most developers reach for an AI coding agent when they pick up a new API. SweatStack is built to make that path short. Three things help your agent ship working code instead of guessing.

1. Install the skills

SweatStack ships installable skills for AI coding agents. Your agent loads them on demand and writes code with the correct imports, real method signatures, and current authentication patterns. No more pasting docs into the chat window.

Source and install instructions on GitHub

The skills cover:

  • The Python SDK (Client construction, authentication, querying activities, longitudinal queries, dailies, tests).
  • OAuth2 and OpenID Connect flows for server-side apps.
  • SweatStack Connect integration.
  • Common patterns: building a coaching dashboard, computing training load, fanning workouts to a connected platform.

Supported agents. Anything that reads the Agent Skills format. That covers Claude Code, Claude Desktop, OpenAI Codex, Cursor and a growing list of agent frameworks.

2. Point your agent at the docs

If your agent supports URL fetching (most do), the next-best move after the skills is pointing it at the docs directly.

Resource URL
These docs https://docs.sweatstack.no/
Interactive API reference (OpenAPI UI) https://app.sweatstack.no/docs
Raw OpenAPI schema https://app.sweatstack.no/openapi.json

Useful one-liner to drop into your system prompt:

Before writing any SweatStack code, fetch https://docs.sweatstack.no/getting-started/ and the OpenAPI schema at https://app.sweatstack.no/openapi.json.

3. Prompt for the right surface

A few patterns that produce working code on the first try:

  • Default to the Python SDK. It's the most documented surface and your agent will produce a runnable script faster than wiring raw HTTP.
  • Ask for a FastAPI snippet when you need OAuth. The sweatstack.fastapi helper handles routes, sessions, and callbacks. The agent should reach for it instead of building OAuth from scratch.
  • Pin the SDK version if you care about reproducibility. Old training data may invent method names from earlier releases.
  • Use the getting started quickstart as a reference example. Telling your agent "follow the quickstart shape" gets you a clean starting point.

Roadmap

llms.txt and an MCP server are on the list. Until they ship, the skills plus the OpenAPI schema cover the same ground.