ai_api_configs

Consolidate multi-vendor AI provider configuration for API keys, base URLs, and model IDs.

11|4|Updated Feb 2, 2025
One-click install
npx skills add https://github.com/konglr/Lottery --skill ai-api-configs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ai_api_configs
Source: https://github.com/konglr/Lottery/tree/main/skills/ai_api_configs
Command: npx skills add https://github.com/konglr/Lottery --skill ai-api-configs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill solves the confusion and errors that happen when teams wire multiple AI providers with inconsistent keys, base URLs, and model identifiers, leading to broken integrations or hard-to-debug failures.

Core Features & Use Cases

  • Centralized provider configuration: Documents required environment variables and base URLs for multiple AI vendors (DashScope, Gemini, NVIDIA NIM, and a Claude-code/tengu guidance section).
  • Verified model catalogs: Lists supported/validated model IDs so developers can choose models that match the project’s runtime expectations.
  • Environment loading norms: Establishes how to read secrets via a recommended .Renviron / os.getenv workflow to reduce key leakage and misconfiguration during development.

Quick Start

Use the ai_api_configs skill to look up the correct environment variable name and base URL for the provider you are integrating, then align your selected model ID to the verified list before running your app.

Frequently Asked Questions about ai_api_configs

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I configure environment variables for multiple AI providers like DashScope and Gemini?

Consolidating multi-vendor AI provider configuration requires strict environment-variable naming for API keys and base URLs. Using a centralized reference prevents misconfiguration and key leakage when integrating DashScope, Gemini, and NVIDIA NIM.

What are the correct model IDs to use when integrating NVIDIA NIM and DashScope APIs?

Validated model IDs are specific to each provider and must match runtime expectations. Using a verified model catalog ensures the selected model ID aligns with NVIDIA NIM and DashScope endpoint constraints to prevent runtime failures.

Does the Gemini API support OpenAI-compatible endpoint configurations?

Gemini integrations must adhere to OpenAI-compatible endpoint constraints when applicable. Verifying that your base URL and environment variables follow these compatibility rules ensures consistent setup and prevents broken integrations.

Why does my AI API integration fail with a runtime error after setting the base URL?

Runtime failures occur when teams wire multiple AI providers with inconsistent keys, base URLs, and model identifiers. Applying a validated model-selection workflow and verified environment loading norms fixes these broken integrations.

What is the best way to manage AI API keys during local development?

Managing AI API keys locally requires a recommended environment loading workflow using `.Renviron` or `os.getenv`. This approach reduces key leakage and ensures secrets are read safely during application development.