Run multi-provider terminal coding sessions with Snow CLI
Use Snow CLI as a terminal coding agent that can route repository work through OpenAI, Gemini, Claude, DeepSeek, or compatible providers without switching tools.
npx skills add agentskillexchange/skills --skill run-multi-provider-terminal-coding-sessions-with-snow-cli
Use Snow CLI when an operator wants one terminal-native coding-agent workflow across multiple model providers. The agent can inspect a repository, edit files, run commands, and keep the coding loop inside the shell while the operator chooses the backing model route.
What this skill actually does
Invoke this instead of using a provider-specific assistant directly when the workflow needs provider portability, relay/API routing, and a repeatable terminal coding loop. The scope boundary is terminal coding-agent execution in a local repository. It is not a generic model SDK, relay marketplace, or broad AI platform listing.
Inputs and prerequisites: Node.js or npm-compatible runtime, Git repository, API credentials or relay route for the selected model provider.
Setup notes: Install the snow-ai package from npm, then run the Snow CLI from a target repository and configure the desired provider credentials or relay endpoint.
Source and verification boundary: use https://github.com/MayDay-wpf/snow-cli as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.