h3-video-prompt-enhancer
Use when making MiniMax H3 video prompts from media + ideas.
Hermes Agent · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add benjiyaya/Minimax-H3-Prompt-AgentSkill --skill h3-video-prompt-enhancer技能说明
name: h3-video-prompt-enhancer description: "Use when making MiniMax H3 video prompts from media + ideas." version: 1.0.0 author: Hermes Agent license: MIT metadata: hermes: tags: [video, prompt-engineering, minimax-h3, comfyui, text-to-video, image-to-video, creative] related_skills: [comfyui]
H3 Video Prompt Enhancer
Overview
Transform a user's rough video idea + attached assets into a production-grade MiniMax H3 video generation prompt. The skill handles two H3 generation modes:
- Ref2VA — when the user provides reference assets (character sheets, style images, reference videos, voice samples). Outputs a 6-section structured prompt. Load
references/ref2va-format.mdfor the full spec. - Base MultiShot (T2VA / I2VA / FL2VA / L2VA) — for text-to-video or image-anchored generation. Outputs a timed multi-shot prompt. Load
references/base-multishot-format.mdfor the full spec.
The skill's distinctive value: it doesn't just format-comply — it creatively enhances the brief with professional-grade cinematic detail (camera aesthetics, visual texture, lighting design, pacing arcs, spatial choreography, continuity tracking) before mapping everything into the exact H3 output format. Load references/creative-showcase.md for quality benchmarks and pattern examples from advanced long-form prompts.
When to Use
Trigger when the user:
- Attaches 1+ images/videos/audio files and describes a video they want to create
- Says "make a video prompt" / "enhance this for H3" / "write a Ref2VA prompt" / "img2vid" / "txt2vid"
- Provides a video concept and wants it structured for MiniMax H3 generation
- Mentions H3, MiniMax, Ref2VA, ComfyUI video generation
- Pastes a creative brief (CAMERA/LOOK/STYLE format) and wants it converted to H3 format
Don't use for:
- Non-H3 video models (Sora, Runway, Kling, etc.) — the output format is H3-specific
- Pure image generation prompts
- Video editing tasks that don't involve new generation
Step 0: Classify the Mode
Determine the H3 mode from what the user attached and stated:
| User provides | Mode | Format reference |
|---|---|---|
| Reference images/videos/audio (character sheets, style refs, voice clips) | Ref2VA | references/ref2va-format.md |
| Nothing — just a text idea | T2VA (text-to-video) | references/base-multishot-format.md |
| 1 image as the first frame | I2VA (image-to-video) | references/base-multishot-format.md |
| 2 images (first frame + last frame) | FL2VA (first-last-to-video) | references/base-multishot-format.md |
| 1 image as the last frame only | L2VA (last-frame-to-video) | references/base-multishot-format.md |
Key distinction: An image used as a first/last frame anchor = I2VA/FL2VA/L2VA. An image used as a character/style reference (not a frame position) = Ref2VA. When ambiguous, ask the user: "Is this image a frame anchor (first/last frame of the video) or a reference (character/style/scene)?"
Step 1: Gather Parameters
Confirm these before enhancing (ask if missing, but proceed if the idea is clear enough):
- duration_s: 4–15 seconds (integer). Default to 8 if unspecified.
- aspect ratio: 16:9, 9:16, 1:1, 4:3, 21:9. Default to 16:9.
- shot count: Let the planner decide, or respect user's explicit count. Budget: 4–6s → 1–2 shots; 7–10s → 2–3 shots; 11–15s → 3–5 shots.
- asset inventory: What each attached file is and its role. Numbering per modality defines labels: Image k →
<Picture k>or<Subject N>; Video k →<Video k>; Audio k →<Audio k>.
Step 2: Creative Enhancement
This is the core value-add. Take the user's idea and enrich it across seven dimensions. The goal: produce a prompt with the depth and cinematic intelligence of a professional storyboard. Consult references/creative-showcase.md for full examples of each pattern.
Enhancement Dimensions
1. Camera Identity — Assign a distinct camera aesthetic that matches the scene's tone:
- Physical type: handheld, tripod, drone, steadicam, dolly, security cam, dashcam, POV, arc shot
- Imperfections to preserve (when stylistically appropriate): hand tremor, autofocus hunting, exposure fluctuation, lens flare, motion blur, awkward zoom
- Format/aesthetic hint: 16mm film, DV tape, digital clean, anamorphic, vintage camcorder, broadcast
2. Visual Texture (LOOK) — Define the image quality and color science:
- Grain/noise: film grain, electronic noise, clean digital, VHS tracking, subtle blur
- Color palette: warm/cool, saturated/desaturated, high/low contrast, natural skin tones
- Lighting design: natural, studio, neon, golden hour, mixed sources, practical lights
- Lighting transitions: if locations change across shots, describe how the light shifts
3. Pacing Arc — Plan the energy progression across the full duration:
- Build patterns: quiet→energetic, tense→release, slow build→explosive peak→settle, steady rhythm
- Cut rhythm: accelerating cuts toward climax, slow contemplative holds, musical cutting on beats
- Match the pacing arc to the emotional intent of the brief
4. Character Detail — Flesh out every on-screen person with specificity:
- Physical: age range, build, hair color/style, skin tone, distinctive features (scars, freckles, heterochromia)
- Wardrobe: specific garments with colors, materials, textures, accessories — note changes across locations or time
- Visual signature: a recurring color or visual element that makes the character instantly recognizable in every shot (e.g., "electric purple energy trails", "glossy teal jacket reflections", "always wears a red scarf")
- Coverage note: describe outfits fully — avoid implying revealing clothing unless the user explicitly requests it
5. Spatial Geography — For action sequences or multi-location videos:
- Screen direction: who enters from where, movement vectors (Left→Right, Deep→Front, foreground↔background)
- Key action moments: the 2–3 critical motion beats that define the