Mmx

Multimodal content generation and analysis via MiniMax CLI, including text chat, image/video creation, speech synthesis, music, vision, and web search with A...

Security Scan

The skill appears to be a CLI reference for a MiniMax 'mmx' tool (coherent) but has mismatches and omissions — it expects an API key and references other system tools without declaring them or a source for the CLI, which is unexplained and worth caution.

Purpose & Capability

The SKILL.md describes a CLI-centric multimodal tool (mmx) and the commands in the file line up with that purpose. However the registry metadata provided with the skill claims no required binaries or credentials while the SKILL.md frontmatter and content explicitly expect the 'mmx' executable and an API key. This discrepancy between declared requirements and the instructions is inconsistent.

Instruction Scope

Runtime instructions tell the agent to run many mmx CLI commands and to perform authentication via 'mmx auth login --api-key <your-api-key>'. The docs also demonstrate piping to other system tools (mpv, jq, cat) and use of local files/URLs. Those auxiliary binaries and the need to supply an API key are not declared elsewhere; the instructions therefore reference system state and tools outside the skill's declared surface.

Install Mechanism

This is an instruction-only skill with no install spec and no code files, which minimizes installer risk. Nothing in the package attempts to download or execute external code by itself.

Credentials

The SKILL.md requires an API key for 'mmx auth login' but the skill does not declare any required environment variables or primary credential in the registry metadata. That omission means the skill's credential needs are not made explicit. Additionally, commands reference other local tools (mpv, jq) which might require additional permissions or environment setup; those are not declared either.

Persistence & Privilege

The skill is not marked always:true and is user-invocable; it does not request persistent presence or claim privileges to alter other skills or system-wide settings. No install actions are present that would grant it additional persistence.

What to consider before installing

This skill is a CLI usage guide for a third-party 'mmx' tool. Before installing/using it: 1) Verify the origin and integrity of the mmx CLI (source URL or package repo), because the skill assumes that binary is installed and trustworthy. 2) Expect to provide an mmx API key — confirm how that key is stored/used; the skill did not declare any environment variable for it. 3) Note the examples call other local binaries (mpv, jq, cat); ensure you have or trust those tools before piping data to them. 4) Ask the skill author or publisher for a homepage/source repository and an explicit list of required binaries and credentials; absence of those details is the main inconsistency. 5) If you will run commands from this skill, run them in a controlled environment (sandbox/container) until you've validated the CLI and API endpoints.

MMX — MiniMax Multimodal CLI

Full reference for mmx CLI. For deep research workflows, use mmx-text-researcher skill instead.

Auth Check (First)

mmx auth status
# If not authenticated:
mmx auth login --api-key <your-api-key>
# Check region:
mmx config show

Text Chat

# Basic
mmx text chat --message "What is MiniMax?"

# Streaming
mmx text chat --model MiniMax-M2.7-highspeed --message "Hello" --stream

# With system prompt
mmx text chat --system "You are a coding assistant" --message "Fizzbuzz in Go"

# Multi-turn (conversation history)
mmx text chat --message "user:Hi" --message "assistant:Hey!" --message "How are you?"

# JSON output
mmx text chat --message "Extract key facts as JSON" --output json

# From file
cat messages.json | mmx text chat --messages-file - --output json

Models

• MiniMax-M2.7 — standard
• MiniMax-M2.7-highspeed — faster response
• MiniMax-Text-01 — best for research/synthesis

Image Generation

# Simple
mmx image "A cat in a spacesuit"

# With options
mmx image generate --prompt "A cat" --n 3 --aspect-ratio 16:9

# Output to directory
mmx image generate --prompt "Logo" --out-dir ./out/

# Available aspect ratios: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9

Video Generation

# Async (start and track)
mmx video generate --prompt "Ocean waves at sunset"

# Async with progress tracking
mmx video generate --prompt "A robot painting" --async

# Get task status
mmx video task get --task-id <task-id>

# Download completed video
mmx video download --file-id <file-id> --out video.mp4
mmx video generate --prompt "Ocean waves at sunset" --download sunset.mp4

Speech / TTS

# Basic synthesis
mmx speech synthesize --text "Hello!" --out hello.mp3

# Streaming playback (pipe to mpv)
mmx speech synthesize --text "Stream me" --stream | mpv -

# Voice selection + speed
mmx speech synthesize --text "Hi" --voice English_magnetic_voiced_man --speed 1.2

# List available voices
mmx voices

# From stdin
echo "Breaking news" | mmx speech synthesize --text-file - --out news.mp3

Music Generation

# With lyrics
mmx music generate --prompt "Upbeat pop" --lyrics "[verse] La da dee, sunny day" --out song.mp3

# Auto-generate lyrics from prompt
mmx music generate --prompt "Indie folk, melancholic, rainy night" --lyrics-optimizer --out song.mp3

# Instrumental (no vocals)
mmx music generate --prompt "Cinematic orchestral" --instrumental --out bgm.mp3

# Cover (generate cover from reference audio)
mmx music cover --prompt "Jazz, piano, warm female vocal" --audio-file original.mp3 --out cover.mp3

# Cover from URL
mmx music cover --prompt "Indie folk" --audio https://example.com/song.mp3 --out cover.mp3

Vision / Image Understanding

# Local file
mmx vision photo.jpg

# Describe with custom prompt
mmx vision describe --image https://example.com/img.jpg --prompt "What breed?"

# From file-id
mmx vision describe --file-id file-123

Web Search

# Basic
mmx search "MiniMax AI"

# Structured JSON output
mmx search query --q "latest news" --output json

Utility

# Check quota
mmx quota

# Show config
mmx config show

# Set region (global or cn)
mmx config set --key region --value cn

# Set default model
mmx config set --key default-text-model --value MiniMax-M2.7-highspeed

# Export schema
mmx config export-schema | jq .

# Update CLI
mmx update
mmx update latest

Common Use Cases

Task	Command
Generate image for Arif's geology viz	mmx image generate --prompt "<description>" --aspect-ratio 16:9 --out-dir ./output/
Create video clip	mmx video generate --prompt "<scene>" --async
TTS voice message	mmx speech synthesize --text "<message>" --voice <voice> --out voice.mp3
Compose background music	mmx music generate --prompt "<mood>" --instrumental --out bgm.mp3
Analyze geology photo	mmx vision <path-to-image>
Quick fact check	mmx search "<query>"
Research synthesis	Use mmx-text-researcher skill instead