cinematic-video-prompt-h3
v1.0.0Cinematic video prompt vocabulary pack adapted for MiniMax H3 video generation. Three Agent Skills: the main prompt-writing skill (H3 field schema + 700+ cinematography terms translated into H3's natural-language shot-description grammar across 10 reference files), a character-sheet-lite skill for I2VA/Ref2VA character consistency, and an oriental-scene-lite skill for Wuxia and Eastern-aesthetic scenes. Pure-skills plugin; no MCP servers.
By SergeLicense: MIT0 GitHub starsUpdated 9 hours ago
Directory evidence
- Runtimes
- Agent Plugins
- Parsed components
- 3 skill or MCP entries
- Source updated
- Sep 30, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Get the plugin
git clone https://github.com/ssm82/cinematic-video-prompt-h3-pluginClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.
This listing currently publishes only the generic Agent Plugins format. Automatic install commands for other clients are not generated yet.
Plugin files
├── plugin.json├── skills/character-sheet-lite-h3/SKILL.md├── skills/cinematic-video-prompt-h3/SKILL.md└── skills/oriental-scene-lite-h3/SKILL.md
Included Skills3
Use when you need a character reference-sheet prompt (three full-body views + one close-up in a single image) for H3 video generation. The sheet's output image feeds into H3 as <Picture 1> for I2VA mode or as the source defining <Subject 1> for Ref2VA mode, so the same character stays consistent across shots. Lite version.
Use when writing or fixing prompts for MiniMax H3 video generation (T2VA, I2VA, FL2VA, L2VA, Ref2VA) — cinematic camera angles, camera movement, lighting, composition, style, color grading, mood, and a H3-aware prompt template that produces the three required fields (integrated_multimodal_description, overall_soundscape, non_diegetic_music) or the six required Ref2VA sections. Translates free-form cinematic vocabulary into H3's natural-language shot-description grammar.
Use when writing H3 prompts for Wuxia, Chinese-fantasy, period-oriental, or Eastern-aesthetic scenes (celestial palaces, sea of clouds, swordmasters, mirror lakes) — folds the 6-layer scene formula into [Shot 1] integrated_multimodal_description so the result reads like a cinematic concept-art poster. Lite version.
Plugin manifests1
{
"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
"name": "cinematic-video-prompt-h3",
"version": "1.0.0",
"description": "Cinematic video prompt vocabulary pack adapted for MiniMax H3 video generation. Three Agent Skills: the main prompt-writing skill (H3 field schema + 700+ cinematography terms translated into H3's natural-language shot-description grammar across 10 reference files), a character-sheet-lite skill for I2VA/Ref2VA character consistency, and an oriental-scene-lite skill for Wuxia and Eastern-aesthetic scenes. Pure-skills plugin; no MCP servers.",
"author": {
"name": "Serge",
"url": "https://github.com/ssm82"
},
"homepage": "https://github.com/ssm82/cinematic-video-prompt-h3-plugin#readme",
"repository": "https://github.com/ssm82/cinematic-video-prompt-h3-plugin",
"license": "MIT",
"keywords": [
"video-generation",
"minimax",
"minimax-h3",
"cinematography",
"prompt-writing",
"t2va",
"i2va",
"fl2va",
"l2va",
"ref2va",
"camera",
"lighting",
"composition",
"sound-design",
"facs",
"editing"
]
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[cinematic-video-prompt-h3 on Agent Plugins Marketplace](https://pluginsmp.com/plugins/cinematic-video-prompt-h3)