MiniMax Multimodal Toolkit

by poco-ai

MiniMax Multimodal Toolkit is an AI Engineering skill for Claude Code, published by poco-ai in poco-claw.

1.4K stars127 forkson poco-ai/poco-clawAdded 2026/08/19Repository updated 2026/08/06

View source on GitHub Download repo ZIP

agentaichatbotclaude-codeclawdbotmanusopenclaw

Install in seconds

Install MiniMax Multimodal Toolkit

Copy MiniMax Multimodal Toolkit into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/poco-ai/poco-claw/tree/main/backend/assets/skills/minimax-multimodal-toolkit ~/.claude/skills/minimax-multimodal-toolkit

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/poco-ai/poco-claw.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: backend/assets/skills/minimax-multimodal-toolkit/SKILL.md in poco-ai/poco-claw
Installs to: ~/.claude/skills/minimax-multimodal-toolkit
Collection: One of 7 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What MiniMax Multimodal Toolkit does

MiniMax Multimodal Toolkit generates voice, music, video, and image content using MiniMax APIs. Use it when the user wants to create audio, visuals, or video with MiniMax, including voice cloning, character reference, and FFmpeg media processing.

MiniMax Multimodal Toolkit is cataloged under AI Engineering on DirSkills. MiniMax Multimodal Toolkit comes from a repository tagged agent, ai, chatbot, claude-code and clawdbot.

Documentation

README

Excerpt

Generate voice, music, video, and image content via MiniMax APIs — the unified entry for MiniMax multimodal use cases (audio + music + video + image). Includes voice cloning & voice design for custom voices, image generation with character reference, and FFmpeg-based media tools for audio/video format conversion, concatenation, trimming, and extraction.

Output Directory

All generated files MUST be saved to minimax-output/ under the AGENT'S current working directory (NOT the skill directory). Every script call MUST include an explicit --output / -o argument pointing to this location. Never omit the output argument or rely on script defaults.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about MiniMax Multimodal Toolkit

What else does poco-ai publish alongside MiniMax Multimodal Toolkit?
MiniMax Multimodal Toolkit is one of 7 skills that DirSkills catalogs from poco-ai/poco-claw, the repository it ships in. Its siblings there include GIF Sticker Maker, MiniMax DOCX and Minimax PDF. Each one is a separate skill with its own page in this directory, installs the same way MiniMax Multimodal Toolkit does, and is maintained by poco-ai in that same repository. The rest of the collection is listed on the poco-ai/poco-claw page.
How does MiniMax Multimodal Toolkit compare to other AI Engineering skills?
MiniMax Multimodal Toolkit ranks #1084 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of MiniMax Multimodal Toolkit against them. Open each page to compare what they document and how they install.