Skip to content

Novita AI command-line client

Lets an agent chat with DeepSeek, GLM and other models through the Novita AI API via a CLI.

Stars
58,084
Licence
Apache-2.0
Files
1 file

What it does

This skill teaches an AI agent how to use a command-line tool that talks to Novita AI, a service that hosts many open AI models such as DeepSeek and GLM. Once installed, the agent can send prompts, stream answers, list available models, and check that the API key works, all by running commands instead of writing its own API code. It is designed so the agent can request machine-readable JSON output.

Great for

  • Developers who want an agent to query Novita-hosted models from the terminal
  • People comparing DeepSeek, GLM or MiniMax answers side by side
  • Engineers building scripts that call Novita models and need JSON output

Skip it if

  • Users without a Novita account or API key, since nothing works without one
  • Anyone expecting the skill to run a local model; requests go to Novita's servers, so prompts and data leave your machine
  • Sensitive or confidential data pasted into prompts, since it is sent to a third-party AI provider

Try asking

  • “Ask DeepSeek to explain quantum computing using the Novita CLI”
  • “List the models available on Novita and tell me which one suits long documents”
  • “Stream a Python factorial function from the Novita model and save the output”
  • “Test that my Novita API key and connection are working”
Step-by-step guide: how to use Novita AI command-line clientInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.

    skills.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip skills.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip skills.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Store the API key with the config set command or an environment variable rather than pasting it into chats
  • Run the test command first to confirm connectivity before relying on the skill
  • Ask the agent to use the --json flag so its output is structured and easier to parse

What's inside

  • SKILL.md

Redistributed unmodified from HKUDS/CLI-Anything under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.