Skip to content
OpenAgentSkill
Browsing is open · Catalog captured 2026-11-21 · Automatic updates and account services are paused.
Video & audio

minimax-h3-reference-video-prompt

Default downstream MiniMax H3 specialist for every image-based request unless the user explicitly declares boundary-only first/last frames with no reusable reference role. Use the official six-section full-reference format for character/person/object consistency, scene/style/action/camera/storyboard/voice/audio reference, source-video editing or continuation, ambiguous image roles, ordinary image animation, and prompt-level first/key/last-frame anchoring.

unknowlei · AI review on file

Installation

Read the source and dependencies before running a command. Copying does not install or execute anything.

npx skills add unknowlei/minimax-h3-opencode-skills --skill minimax-h3-reference-video-prompt

About this skill


name: minimax-h3-reference-video-prompt description: "Default downstream MiniMax H3 specialist for every image-based request unless the user explicitly declares boundary-only first/last frames with no reusable reference role. Use the official six-section full-reference format for character/person/object consistency, scene/style/action/camera/storyboard/voice/audio reference, source-video editing or continuation, ambiguous image roles, ordinary image animation, and prompt-level first/key/last-frame anchoring."

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.

Official Format Authority

Before drafting, read ../h3-prompt-writing/SKILL.md and ../h3-prompt-writing/references/ref-en.txt. Consult ../h3-prompt-writing/references/base-en.txt for the shared shot, camera, dialogue, visible-text, and sound rules when needed. Treat these official MiniMax files as the canonical prompt-format specification. If this skill or its local references conflict with them, follow the official files.

Read references/reference-rules.md before drafting.

Confirmed Multishot Handoff

When the director supplies a confirmed multishot_plan, treat its shot count, timing, content, framing, performance, camera, transitions, sound, active references, and continuity decisions as already answered. Do not ask those questions again. Map every confirmed shot into detailed_description, keep reference labels and responsibilities stable, and carry the continuity ledger into retention and preservation instructions. Reopen a decision only when the plan is physically impossible, conflicts with a source asset, or exceeds the effective duration.

Official Input Envelope

For the official online product/API, keep output within 4-15 seconds at 24 FPS and the prompt within 7000 characters. Accept at most 9 images, 3 videos, 3 audio files, and 12 mixed files total. Each video or audio file must be 2-15 seconds; combined video duration and combined audio duration must each be at most 15 seconds. Audio cannot be the only reference type. Respect the documented per-file and API-body limits. Treat local ComfyUI constraints separately when they are narrower.

Mandatory Format

Always return the official six sections in their required order. Never return a free-form natural-language paragraph, keyword list, abbreviated prompt, base three-field prompt, or alternate schema as the final English prompt for a full-reference task.

Interactive Direction Check

Before assigning labels or drafting, use the host's structured-choice tool whenever the brief is sparse; gives only an image plus a generic motion request; omits two or more of action progression, scene treatment, preservation priorities, visual style, camera/editing, dialogue/voice, sound/music, or endpoint; leaves a decisive reference responsibility unclear; or asks the AI to improvise.

In OpenCode, call the built-in question tool rather than displaying Markdown options. In Codex, use the available structured user-input tool; if unavailable, ask one concise plain-text question.

Ask as many related questions as the current decision stage requires; normally 1-5, but three is not a per-call, per-turn, or per-session ceiling. A strict yes/no question may contain exactly two options; every other choice question must contain at least five materially different, feasible options. Put the context-specific recommendation first and append (Recommended) to its label. Explain the consequence of each choice, omit Other, and use multiple selection only when roles can truly be combined. Before every question tool call, count the options in the actual payload. If any non-binary choice has fewer than five, do not submit it; expand it with meaningful alternatives or make it open-ended. Do not create near-duplicates merely to reach five.

Prioritize:

  • Task relationship: reference generation, source-video editing, continuation, or a combination
  • Asset responsibility: identity/appearance, clothing/scene, action/camera, storyboard/keyframe, audio/voice/music
  • Fidelity policy: strict preservation, balanced adaptation, attribute transfer, broad stylistic reference
  • Prompt-level picture anchor: no concrete anchor, first frame, intermediate keyframe, last frame
  • Audio policy: direct reuse, partial reuse, timbre/style reference, newly designed sound

For sparse or delegated briefs, ask enough high-impact questions in one batch to establish the current stage, normally 3-5, even when the asset itself is visually clear. Do not ask the user to classify every asset; default images to character/object/scene consistency and ask about the desired creative outcome. Skip questions only when the user explicitly prohibits them. A request to improvise still requires questions.

Workflow

  1. Inventory every supplied image, video, audio asset, upload order, and text requirement; validate the official input envelope, then run the interactive direction check when required.
  2. Map what each asset contributes: identity, appearance, clothing, object, environment, style, pose, action, camera, storyboard, edit source, continuation point, voice, sound, music, or rhythm.
  3. Distinguish reusable visible content from source files. Assign stable <Subject N>, <Picture N>, <Video N>, and
Read the complete source ↗