H3mlx

Autonomous AI agent execution skill for high-speed, photorealistic MiniMax-H3 video and 48kHz audio generation on Apple Silicon (Metal 4 / MLX / Pure C). Includes Fast Master (8-step) and FastVideo (4-step) presets, hardware auto-profiling, and broadcast mastering.

23 stars 1 forksImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add RobZombAI/H3MLX --skill h3mlx

Manual install

git clone --depth 1 https://github.com/RobZombAI/H3MLX.git /tmp/H3MLX
mkdir -p ~/.claude/skills
cp -r /tmp/H3MLX/. ~/.claude/skills/h3mlx

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# H3MLX: AI Agent Execution Skill for MiniMax-H3 on Apple Silicon

This skill enables any autonomous agent (such as Hermes, Antigravity, or LangChain agents) to programmatically invoke, benchmark, and orchestrate photorealistic video and synchronized 48kHz audio generation using the high-performance C/Metal 4 MiniMax-H3 engine on Apple Silicon.

---

## ⚡ Agent Capability Matrix

| Action | Preset ID | Command Pattern | Denoise Latency (1.6s) | Primary Use-Case |
| :--- | :--- | :--- | :---: | :--- |
| **8K Gold Master** | `champion` | `./h3_master_cli.sh champion "<prompt>"` | **$\approx 12.5\text{ s}$** | High-definition commercial portraits, natural skin texture, iris reflections. |
| **Sub-15s Turbo** | `turbo` | `./h3_master_cli.sh turbo "<prompt>"` | **$\approx 6.5\text{ s}$** | Fast iterations, storyboard generation, rapid social media clips. |
| **Anamorphic 16:9** | `cinema` | `./h3_master_cli.sh cinema "<prompt>"` | **$\approx 16.4\text{ s}$** | Cinematic landscape shots ($960 \times 544$). |
| **Vertical Reel 9:16** | `reel` | `./h3_master_cli.sh reel "<prompt>" 544 960 39 <img_path>` | **$\approx 16.4\text{ s}$** | Vertical social videos ($544 \times 960$) with image conditioning. |
| **Ultra Draft** | `draft` | `./h3_master_cli.sh draft "<prompt>"` | **$\approx 3.2\text{ s}$** | Prompt validation and lighting checks in sub-10s total turnaround. |

---

## 🛠️ Autonomous Agent Invocation Protocol

When an AI agent needs to generate or master video assets:

Read the full skill on GitHub

Details

Skill name: h3mlx
Repository: RobZombAI/H3MLX
Repo updated: 6 September 2026

FAQ

What does the H3mlx skill do?

How do I install the H3mlx skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add RobZombAI/H3MLX --skill h3mlx. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is H3mlx popular?

It lives in RobZombAI/H3MLX, which has 23 GitHub stars and 1 forks.

Related skills

Whisper Skill

Mobiss11/Whisper-Skill

Используй этот скилл когда пользователю нужна локальная транскрибация аудио/видео через Whisper, голосовой ввод (диктовка вместо клавиатуры, push-to-talk hotkey), или вшивание субтитров в MP4 в стиле CapCut. Активируй при задачах "транскрибируй файл/папку/TikTok/YouTube/подкаст", "сабы для shorts/reels/тиктока", "speech-to-text локально", "speaker diarization", "диктовка голосом", "Superwhisper alternative", "Wispr Flow alternative", "voice dictation". Скилл автоматически определяет ОС/CPU/GPU и подбирает оптимальный бэкенд (faster-whisper / whisper.cpp / whisperx / mlx-whisper / openvino) и м

Images, Video & Audio14

Biaoqing Yanyi

dashian1/biaoqing-yanyi-skill

Use when creating Chinese AI video acting prompts for micro-expressions, emotional dialogue, eye movement, mouth shape, breathing, posture, voice rhythm, restrained crying, anger, coquettish acting, one-line emotional variations, and time-coded performance breakdowns.

Images, Video & Audio

Fish Audio

AceDataCloud/Skills

Generate text-to-speech, find saved voices, create a persistent public voice model, or make a one-shot clone from an HTTPS audio URL and exact transcript via AceDataCloud API.

Images, Video & AudioIn 1 list

Vox Style Collage Video

sadekxD/vox-style-collage-video-skill

Turn a script or fact list into a finished Vox-style paper-collage explainer video: flat torn-edge photographic cut-outs, off-white newsprint ground with ONE bold accent color, big kinetic typography synced to the voiceover, infographic motifs (maps, arrows, redlines, timelines, charts), limited low-frame-rate cutout motion, narration-first pacing. ALL image/video/music generation runs on Unsora (create_image nano-banana-pro, create_video seedance-2.0, create_music mureka-7.5); the VOICEOVER is the one thing Unsora cannot make, so it comes from a supplied file or the session's own TTS tool, th

Images, Video & Audio

Html2video

cclank/lanshu-html2video-skill

Turn a web article URL into a polished 1920x1080 edited video (MP4) — code-driven editing with Remotion, not AI video generation. Use this whenever the user wants an article, blog post, research page or changelog made into a video, or says 文章转视频, 网页转视频, 把这篇做成视频, article-to-video, url-to-video, or asks for an explainer or montage cut of written content. It harvests the page's real structure, full-resolution figures and design tokens, mines the content for what matters (including the caveats most tools skip), commits to a reviewable storyboard.json, then renders through a hardened Chinese-typogr

Images, Video & Audio

AI Product Video

dlazy-ai/ai-product-video

Create cinematic product videos from shot recipe cards, a validated template, and code/audio assets (Remotion + real page screenshots + 2.5D camera moves + beat-synced cuts + sound design). Use when the user asks to turn a frontend project or webpage into a product video, says "use ai-product-video to make a video/promo", names the Ink Press template or asks to reproduce its effect, or wants a single shot card's motion. 用镜头配方卡 + 已验收模板 + 代码/音频资产制作电影感产品视频（Remotion + 真实页面截图 + 2.5D 运镜 + 节奏卡点 + 声音设计）。当用户要求"用 ai-product-video 做视频/宣传片"、把前端项目/网页做成产品视频、点名 Ink Press 模板或要求复刻模板片效果，或要用镜头卡做单个动效镜头时使用。

Images, Video & Audio

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.