Agent skill

Minimax H3

by calesthio in calesthio/OpenMontage

Generate MiniMax H3 (Hailuo 3.0) video through the official MiniMax v2 API, fal.ai, Runway, ComfyUI Partner Nodes, or local open weights in ComfyUI.

AGPL-3.0Auto-check passedMedia & Creative

Install Minimax H3

skills CLI
$ npx skills add calesthio/OpenMontage --skill minimax-h3 -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install calesthio/OpenMontage minimax-h3 --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/calesthio/OpenMontage.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/minimax-h3 .claude/skills/minimax-h3 && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
minimax-h3
GitHub stars
66k
Token cost
~580 tokens
SKILL.md length
257 words
Files
1
Skills in repo
41
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Generate MiniMax H3 (Hailuo 3.0) video through the official MiniMax v2 API, fal.ai, Runway, ComfyUI Partner Nodes, or local open weights in ComfyUI.

  • 4-15 second 2K clips
  • SKILL.md covers Choose a route, Operations and prompting and Provider differences
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • First/last-frame animation

What it does

Minimax H3 is an agent skill from calesthio/OpenMontage. Generate MiniMax H3 (Hailuo 3.0) video through the official MiniMax v2 API, fal.ai, Runway, ComfyUI Partner Nodes, or local open weights in ComfyUI. Use for 4-15 second 2K clips, first/last-frame animation, and image/video/audio reference-conditioned video.

Its SKILL.md is about 580 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Media & Creative, covering Diffusion and image models. It works with MiniMax, ComfyUI and fal. The repository describes itself as: World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant… The licence is AGPL-3.0.

When your agent uses it

  • 4-15 second 2K clips
  • First/last-frame animation
  • Image/video/audio reference-conditioned video

Example prompts

  • “/minimax-h3”

What it can do on your machine

Read from SKILL.md and the folder at commit 9327439. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Minimax H3 loads about 580 tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 257 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~67
When it runs · the whole SKILL.md, loaded when a task matches
~580

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from calesthio/OpenMontage at commit 9327439, republished under its AGPL-3.0 licence (© calesthio). 257 words, ~580 tokens.

Download SKILL.mdSave it as .claude/skills/minimax-h3/SKILL.md (or your agent's skills folder).
name
minimax-h3
description
Generate MiniMax H3 (Hailuo 3.0) video through the official MiniMax v2 API, fal.ai, Runway, ComfyUI Partner Nodes, or local open weights in ComfyUI. Use for 4-15 second 2K clips, first/last-frame animation, and image/video/audio reference-conditioned video.

MiniMax H3

MiniMax H3 is the Hailuo 3.0 family. The first-party API identifier is MiniMax-H3; fal.ai exposes the family as hailuo-03, and Runway uses hailuo3. Do not substitute one provider's identifier into another API.

Choose a route

RouteTool callExecution
MiniMax directminimax_video, model: "MiniMax-H3"Hosted first-party v2 API; global or mainland-China region
fal.aiminimax_fal_videoHosted gateway; T2V, I2V, reference-to-video
Runwayrunway_video, model: "hailuo3"Hosted; 768P or 2K, 5–15 seconds
ComfyUI Partner Nodecomfyui_video, model_family: "minimax_h3_api"Hosted and billed in Comfy credits
ComfyUI open weightscomfyui_video, model_family: "minimax_h3_local"Local GPU with official workflow and model stack

For local ComfyUI, export the official workflow in API format and pass workflow_json or workflow_path plus output_node. OpenMontage reports the required diffusion model, Qwen3-VL text encoder, video VAE, and audio VAE; it does not silently download large weights.

Operations and prompting

  • Text-to-video: concrete ratio; do not use adaptive without visual input.
  • Image-to-video: provide a first frame.
  • First/last-frame: provide both images and describe the motion between them.
  • Reference-to-video: images, videos, and audio can be combined. Audio needs at least one visual reference.

Write prompts as subject + action + camera path + environment + lighting + audio intent. MiniMax responds well to explicit camera direction. Keep the requested motion achievable within 4–15 seconds and inspect native audio as carefully as the image track.

Provider differences

The direct MiniMax v2 route currently outputs 2K and supports 4–15 seconds. Runway's Hailuo 3.0 route supports 768P/2K and documents 5–15 seconds. Partner Nodes require network access and credits. Only the open-weight ComfyUI route is local/offline after all models are installed.

© calesthio, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/minimax-h3 of calesthio/OpenMontage.

Open the folder on GitHubat commit 9327439

Compare with similar skills

Minimax H3 next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Minimax H3 compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Minimax H3 this skillcalesthio/OpenMontage66k—~580Automated safety check: PassAGPL-3.0
9Router Image Generationdecolua/9router31k—~830Automated safety check: PassMIT
H3 Videoagent-next/video-agent120—~2.9kAutomated safety check: PassApache-2.0
ComfyUI Local DriverSlavaSexton/ComfyUI-Agent-Kit105—~12kAutomated safety check: PassApache-2.0
Open Videoagent-next/video-agent120—~3.2kAutomated safety check: PassApache-2.0
H3 Video Prompt Enhancerbenjiyaya/Calliope242—~4.6kAutomated safety check: PassMIT

Similar skills

  • Generates images through a 9Router gateway's image endpoint, with model discovery, the request fields and per-provider quirks for OpenAI, Gemini, MiniMax and others.

    31k GitHub stars~830 tokensUpdated 3 days ago
    Media & CreativeAuto-check passed
  • H3 Video

    agent-next/video-agent

    OpenVideo skill (v0.1.0): generate high-quality local video with the OpenVideo product (MiniMax H3 backend).

    120 GitHub stars~2.9k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • ComfyUI Local Driver

    SlavaSexton/ComfyUI-Agent-Kit

    Drives a local ComfyUI install over its HTTP API to generate and edit images, video and audio, with per-model prompt recipes and workflow guidance.

    105 GitHub stars~12k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Open Video

    agent-next/video-agent

    Generate, edit, or direct videos via open-source models (MiniMax H3 baseline; Wan2.2 / LTX future).

    120 GitHub stars~3.2k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • H3 Video Prompt Enhancer

    benjiyaya/Calliope

    A skill your agent uses when making MiniMax H3 video prompts from media + ideas.

    242 GitHub stars~4.6k tokensUpdated 3 days ago
    Media & CreativeAuto-check passed
  • Moonvalley Marey

    calesthio/generative-media-skills

    Produce video with Moonvalley's Marey model family (Marey Realism v1.5) — a filmmaker-oriented, 1080p/24fps generative video model marketed as trained exclusively on licensed data.

    197 GitHub stars~5.2k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed

More from calesthio/OpenMontage

All 41 skills in this repo
  • Video Understand

    calesthio/OpenMontage

    Understand video content locally using ffmpeg frame extraction and Whisper transcription.

    66k GitHub stars~841 tokensUpdated 7 days ago
    Auto-check passed
  • Avatar Video

    calesthio/OpenMontage

    Create AI avatar videos with precise control over avatars, voices, scripts, scenes, and backgrounds using HeyGen's v2 API.

    66k GitHub stars~1.6k tokensUpdated 7 days ago
    Auto-check passed
  • D3 Viz

    calesthio/OpenMontage

    Creating interactive data visualisations using d3.js. An agent skill from calesthio/OpenMontage.

    66k GitHub starsUsed in 3 repos~5.4k tokens
    Auto-check passed
  • Create Video

    calesthio/OpenMontage

    Create videos from a text prompt using HeyGen's Video Agent.

    66k GitHub stars~1.3k tokensUpdated 7 days ago
    Auto-check passed
  • Threejs World Generation

    calesthio/OpenMontage

    Build deterministic, editable, free-viewpoint Three.js worlds from text or structured briefs.

    66k GitHub stars~2k tokensUpdated 7 days ago
    Auto-check passed
  • Video Edit

    calesthio/OpenMontage

    Edit videos locally using ffmpeg. An agent skill from calesthio/OpenMontage.

    66k GitHub stars~855 tokensUpdated 7 days ago
    Auto-check: notes

Questions about Minimax H3

What does Minimax H3 do?

Generate MiniMax H3 (Hailuo 3.0) video through the official MiniMax v2 API, fal.ai, Runway, ComfyUI Partner Nodes, or local open weights in ComfyUI. Minimax H3 is an agent skill from calesthio/OpenMontage.ai, Runway, ComfyUI Partner Nodes, or local open weights in ComfyUI.

When should I use Minimax H3?

Minimax H3 fits situations like: 4-15 second 2K clips; first/last-frame animation; image/video/audio reference-conditioned video.

How do I install Minimax H3 in Claude Code?

Run `npx skills add calesthio/OpenMontage --skill minimax-h3 -a claude-code`. Or copy the skill folder (.agents/skills/minimax-h3 in calesthio/OpenMontage) into .claude/skills/minimax-h3 in your project. Claude Code loads it when a task matches its description.

How do I install Minimax H3 in Codex?

Run `npx skills add calesthio/OpenMontage --skill minimax-h3 -a codex`. Or copy the skill folder (.agents/skills/minimax-h3 in calesthio/OpenMontage) into .agents/skills/minimax-h3 in your project. Codex loads it when a task matches its description.

Can I use Minimax H3 in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add calesthio/OpenMontage --skill minimax-h3 -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/minimax-h3, .gemini/skills/minimax-h3, .github/skills/minimax-h3 and .opencode/skills/minimax-h3 in your project.

What does Minimax H3 need to run?

SKILL.md names no scripts, command-line tools or credentials: Minimax H3 is instructions for the agent only.

Does Minimax H3 access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Minimax H3 safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Minimax H3 use?

Minimax H3 is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Minimax H3 use?

About 580 tokens (SKILL.md is roughly 2.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Minimax H3?

Skills that share tags, products or a category with Minimax H3: 9Router Image Generation (decolua/9router, 31k stars), H3 Video (agent-next/video-agent, 120 stars), ComfyUI Local Driver (SlavaSexton/ComfyUI-Agent-Kit, 105 stars) and Open Video (agent-next/video-agent, 120 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Minimax H3?

calesthio (a GitHub user) maintains it in calesthio/OpenMontage, which has 65,930 GitHub stars. The repository holds 41 skills in this directory. The repository was last updated on October 3, 2026.

Source: calesthio/OpenMontage on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.