How to use MiniMax M3's native multimodal input (image, video) for grounded decisions in coding work. Covers reading attached images/frames, treating them as ground truth for visual claims, screenshot diffing, design parity from mockups, and routing visual evidence through reports and PRs. Load when the user attaches…
MiniMax-native multimodal workflow for image, video, voice, music, and media-processing tasks. Use when the user asks to generate image/video/audio assets, wants MiniMax-specific media APIs, needs TTS or voice workflows, wants reproducible local media outputs, or needs FFmpeg-style processing around generated media.…
Generate a content-first marketing landing page using MBA design rules. Auto-detects vertical (SaaS vs retail/hospitality/wellness) and adapts skeleton, mode, and reference system accordingly.
Vertical → aesthetic mapping. Read whenever the brief mentions a specific business, industry, or product. Prevents tonal mismatches like "pet shop styled as a fintech dashboard".
Platform-specific deltas for iOS, Android, desktop apps (Electron/Tauri). Apply ONLY when targeting these platforms — read this rule when the task mentions iOS, iPhone, iPad, Android, Material Design, desktop app, Electron, Tauri, Swift, SwiftUI, or Kotlin.