agentscope-ai/mmx-cli
skills/mmx-cli/SKILL.md
Generate text, images, video, speech, and music via the MiniMax AI platform. Covers text generation (MiniMax-M3 model), image generation (image-01), video generation (Hailuo-2.3), speech synthesis (speech-2.8-hd, 300+ voices), music generation (music-2.6 with lyrics, cover, and instrumental), and web search. Use when the user needs to create AI-generated multimedia content, produce narrated audio from text, compose music, or search the web through MiniMax AI services.
$ install --global
skillsauthnpx skillsauth add agentscope-ai/openjudge mmx-cliInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 10, 2026, 3:47 AM36.4s1 file scanned
SKILL.md
- name:
- mmx-cli
- description:
- >
mmx-cli Skill
Generate multimedia content (text, images, video, speech, music) via the MiniMax AI platform.
Install
npx skills add MiniMax-AI/cli@skill -g -y
Or manually:
npm install -g @minimax-ai/cli
Set your API key:
export MINIMAX_API_KEY=your_api_key_here
Capabilities
| Capability | Command | Model |
|------------|---------|-------|
| Text generation | mmx text generate | MiniMax-M3 |
| Image generation | mmx image generate | image-01 |
| Video generation | mmx video generate | Hailuo-2.3 |
| Speech synthesis | mmx speech generate | speech-2.8-hd |
| Music generation | mmx music generate | music-2.6 |
| Web search | mmx search | — |
Quick Examples
# Generate text
mmx text generate "Summarize the key benefits of reinforcement learning"
# Generate an image
mmx image generate "A futuristic city skyline at sunset, photorealistic"
# Generate a short video clip
mmx video generate "A golden retriever playing in autumn leaves"
# Synthesize speech from text
mmx speech generate --text "Hello, welcome to the demo." --voice Calm_Woman
# Generate music with lyrics
mmx music generate --lyrics "Rise and shine, a brand new day" --style "pop upbeat"
# Web search
mmx search "latest advances in LLM evaluation"
Gather from user before running
| Info | Required? | Notes |
|------|-----------|-------|
| MINIMAX_API_KEY | Yes | From MiniMax platform |
| Prompt or text | Yes | Describe what to generate |
| Voice name | No | For speech; run mmx speech list-voices to browse 300+ options |
| Output path | No | Default saves to current directory |
Tips
- Use
--output jsonflag for structured output suitable for pipelines. - Use
--non-interactiveand--quietflags in automated / agent workflows. - Run
mmx --helpormmx <subcommand> --helpto see all options. - The SKILL.md in the upstream repo is always up-to-date with the latest flags and models.
Related Skills
agentscope-ai/rl-reward
development
VerifiedTrustedCommunity
Build RL reward signals using the OpenJudge framework. Covers choosing between pointwise and pairwise reward strategies based on RL algorithm, task type, and cost; aggregating multi-dimensional pointwise scores into a scalar reward; pairwise tournament reward for GRPO on subjective tasks (net win rate across group rollouts); generating preference pairs for DPO/RLAIF; and normalizing scores for training stability. Use when building reward models, scoring rollouts for GRPO/REINFORCE, generating preference data for DPO, or doing Best-of-N selection.
493SKILL.mdUpdated Mar 27, 2026
agentscope-ai/ref-hallucination-arena
tools
VerifiedTrustedCommunity
Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination rate, per-field accuracy (title/author/year/DOI), discipline breakdown, and year constraint compliance. Supports tool-augmented (ReAct + web search) mode. Use when the user asks to evaluate, benchmark, or compare models on academic reference hallucination, literature recommendation quality, or citation accuracy.
493SKILL.mdUpdated Mar 27, 2026
agentscope-ai/paper-review
testing
VerifiedTrustedCommunity
Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports PDF files and LaTeX source packages (.tar.gz/.zip). Covers 10 disciplines: cs, medicine, physics, chemistry, biology, economics, psychology, environmental_science, mathematics, social_sciences. Use when the user asks to review, evaluate, critique, or assess a research paper, check references, or verify a BibTeX file.
493SKILL.mdUpdated Mar 27, 2026
agentscope-ai/openjudge
development
VerifiedTrustedCommunity
Build custom LLM evaluation pipelines using the OpenJudge framework. Covers selecting and configuring graders (LLM-based, function-based, agentic), running batch evaluations with GradingRunner, combining scores with aggregators, applying evaluation strategies (voting, average), auto-generating graders from data, and analyzing results (pairwise win rates, statistics, validation metrics). Use when the user wants to evaluate LLM outputs, compare multiple models, design scoring criteria, or build an automated evaluation system.
493SKILL.mdUpdated Mar 27, 2026