← Back to skills
extension
Category: Content & MediaAPI key requirement unconfirmed

H3 Prompt Writing

提示词技能。它把用户提供的文本、图片、视频或音频需求改写为 MiniMax H3 可执行的视频生成提示词。

personAuthor: stormflyhubModelScope

H3 Prompt Writing

External Agent Runtime (Mandatory)

This skill is standalone for Claude, Codex, OpenCode, and other external Agent runtimes. Read references/platform-api.md and check LINGJING_API_KEY before any model call. All model calls must use the LingJing external /api/v1 API.

  • Use scripts/lingjing_api.py when available, or make equivalent HTTP requests.
  • Do not call Hub tools, Canvas APIs, localhost, X-Agent-Key, internal /api/ecommerce/*, or upstream model APIs.
  • Write long rewrites and locked prompts to local Markdown files.
  • If the user only wants a prompt, stop after the rewrite. Call the video API only when the user explicitly asks to generate the video.

Workflow

  1. Identify the input mode: T2VA, I2VA, FL2VA, L2VA, or full-reference Ref2VA.
  2. For base text/keyframe modes, read references/base-en.txt and follow its final prompt structure.
  3. For full-reference mode, read references/ref-en.txt and follow its six-section rewrite format.
  4. Preserve the exact field names, section order, labels, and timing notation from the selected guide.

Base Modes

  • T2VA: build the full audiovisual timeline from text.
  • I2VA: start from the first frame and develop forward from it.
  • FL2VA: describe the continuous path between the first and last frames.
  • L2VA: infer a plausible opening and converge to the supplied last frame.

Use integrated_multimodal_description, overall_soundscape, and non_diegetic_music in the order shown in references/base-en.txt.

Full-Reference Mode

Ref2VA rewrites use subject_definitions, summary, retention_analysis, detailed_description, overall_soundscape, and non_diegetic_music in that order. Reference labels stay consistent across all sections.

Read references/ref-en.txt for label rules, retention analysis, and complete examples.

Output Rules

  • Write rewrite sections in English; preserve dialogue, lyrics, and visible scene text in their original language.
  • Describe each shot by composition, subjects, environment, actions, camera, sound, and the exact point where referenced content appears.
  • Avoid plot summaries, unresolved reference labels, and timing that does not match the requested duration.