minimax-h3-prompting

Write or refine prompts for MiniMax H3 video generation via comfy-agent (minimax_h3_t2v / minimax_h3_i2v presets). Use whenever composing the --104_prompt for an H3 run, when a user asks for a video clip on an H3 environment, or when an H3 output missed the intent (wrong audio, ignored camera move, style drift, rushed pacing) and the prompt needs iteration.

Jump to install

Repository: shinshin86/comfy-agent
Last source activity: August 16, 2026 at 08:02
Detected SKILL.md language: English
Stars: 14
Forks: 1

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/shinshin86/comfy-agent --skill minimax-h3-prompting

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

SKILL.md

Source instructions · Read-only preview

Back to search Back to installation

comfy-agent

Generate images, video, or music/audio with ComfyUI via the comfy-agent CLI. Use when the user asks to create/generate an image, video clip, animation, song, BGM, or sound effect, or asks to set up / reconnect a ComfyUI environment (local or Google Colab). Covers picking the right Colab kit, presenting a setup blueprint, running generations, and recovering from MISSING_MODEL_ON_SERVER / SERVER_UNREACHABLE errors.

2026-08-16

View all from this repository

name	minimax-h3-prompting
description	Write or refine prompts for MiniMax H3 video generation via comfy-agent (minimax_h3_t2v / minimax_h3_i2v / minimax_h3_r2v presets). Use whenever composing the --104_prompt for an H3 run, when a user asks for a video clip on an H3 environment, or when an H3 output missed the intent (wrong audio, ignored camera move, style drift, rushed pacing) and the prompt needs iteration.