MiniMax H3 Video Prompting

MiniMax H3 Video Prompting is an AI Engineering skill for Claude Code, published by unknowlei in minimax-h3-opencode-skills.

48 stars1 forkson unknowlei/minimax-h3-opencode-skillsAdded 2026/08/11+182% in starsRepository updated 2026/08/09

View source on GitHub Download repo ZIP

agent-skillsminimax-h3multimodalopencodeprompt-engineeringvideo-generation

Install in seconds

Install MiniMax H3 Video Prompting

Copy MiniMax H3 Video Prompting 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/unknowlei/minimax-h3-opencode-skills/tree/main/skills/minimax-h3-reference-video-prompt ~/.claude/skills/minimax-h3-reference-video-prompt

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/unknowlei/minimax-h3-opencode-skills.git

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

In this catalog

Source file: skills/minimax-h3-reference-video-prompt/SKILL.md in unknowlei/minimax-h3-opencode-skills
Installs to: ~/.claude/skills/minimax-h3-reference-video-prompt
Collection: One of 6 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What MiniMax H3 Video Prompting does

Writes traceable six-section reference prompts for the MiniMax H3 video model, ensuring consistent character, object, and scene reuse across image-to-video generation, editing, and continuation.

MiniMax H3 Video Prompting is cataloged under AI Engineering on DirSkills. MiniMax H3 Video Prompting comes from a repository tagged agent-skills, minimax-h3, multimodal, opencode and prompt-engineering.

Documentation

README

Excerpt

MiniMax H3 Full-Reference Video Prompt

Convert mixed reference assets and user intent into a traceable six-section full-reference prompt. Make every asset role explicit and write the target video as a detailed audiovisual timeline.

Routing Contract

New MiniMax H3 requests should enter through minimax-h3-creative-director. This is the default specialist for any request containing images. Route away only when the user explicitly declares pure first/last boundary roles and no image also carries identity, character, person, object, costume, scene, style, action, camera, composition, or another reusable reference responsibility. Ambiguity stays here. Full-reference may use prompt-level first/key/last-frame anchoring while maintaining consistency.

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

Frequently asked about MiniMax H3 Video Prompting

What else does unknowlei publish alongside MiniMax H3 Video Prompting?
MiniMax H3 Video Prompting is one of 6 skills that DirSkills catalogs from unknowlei/minimax-h3-opencode-skills, the repository it ships in. Its siblings there include MiniMax H3 Creative Director, MiniMax H3 Keyframe Video Prompting and MiniMax H3 Multishot Planner. Each one is a separate skill with its own page in this directory, installs the same way MiniMax H3 Video Prompting does, and is maintained by unknowlei in that same repository. The rest of the collection is listed on the unknowlei/minimax-h3-opencode-skills page.
How does MiniMax H3 Video Prompting compare to other AI Engineering skills?
MiniMax H3 Video Prompting ranks #2288 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 H3 Video Prompting against them. Open each page to compare what they document and how they install.