Skip to content
Get packs

MiniMax AI Command-Line Tool

Lets an agent chat with MiniMax models and turn text into speech via the MiniMax API.

Source Download skill
Repository
HKUDS/CLI-Anything
Stars
58,084
Licence
Apache-2.0
Files
1 file

What it does

This skill teaches an AI agent to use a command-line program called cli-anything-minimax, which connects to the MiniMax AI service. Once installed, the agent can send chat prompts to MiniMax models, stream responses, list available voices, and generate MP3 (or other format) speech audio from text, saving the result to a file. It requires your own MiniMax API key to work.

Great for

  • Developers who already use MiniMax AI and want their agent to call it from the terminal
  • Creators who want to generate narration or speech audio from text using MiniMax voices
  • Anyone building scripts or agent workflows that need JSON-formatted MiniMax responses

Skip it if

  • People without a MiniMax account or API key, since the tool cannot function without one
  • Tasks needing offline or private processing, because prompts and text are sent to the MiniMax online service
  • Users who expect a general-purpose agent skill; it only covers MiniMax chat and TTS

Try asking

  • “Use the MiniMax CLI to explain quantum computing and save the answer”
  • “Generate an MP3 narration of this paragraph with a MiniMax voice”
  • “List the available MiniMax TTS voices and pick a warm English one”
  • “Stream a Python quicksort explanation from MiniMax-M3”
Step-by-step guide: how to use MiniMax AI Command-Line ToolInstall, 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 your API key with an environment variable or config set rather than pasting it into prompts or shared files
  • Use the --json flag when an agent needs to parse results, and use absolute paths for audio output files
  • Check the model list with models or models --tts, since model IDs may change over time

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.