Back to Skills

co-op-game-intro-generator

For users creating a two-player co-op game menu or opening animation. Users provide two player names, a game title, a target visual style, and optional character reference images. The Skill locks identity cues, generates an approval image from a fixed menu framework with coordinated color, buttons, icons, and typography, then uses the approved result to rebuild the character, UI-copy, and event timing instructions for the final video. It outputs a co-op game intro featuring two characters, playe

6,479stars396forksUpdated 8/20/2026

Security Assessment

Safe(95/100)
Security Score95/100

About co-op-game-intro-generator

Co-op Game Intro Generator produces a two-player co-op game menu or opening-animation video. It solves the problem of getting a coherent, style-consistent intro by using a confirm-before-generate workflow: the user supplies two player names, a game title, a target visual style, and optional character reference images, and the skill first generates one approval image from a fixed menu framework before committing to the final video, so visual direction is locked before generation cost is spent.

The workflow collects visual style (which has top priority over all supplemental style language, palette, UI colors, and typography), player and game info, and optional character references used only for identity mapping (face silhouette, hairstyle, glasses, proportions) without inheriting photographic realism. It then builds a confirmation-image prompt from a mandatory template with fixed framework plus dynamic style fill and a palette-linked structure (overall style, five-color palette, 16:9 composition, background, character style, per-character detail, UI copy, and typography), and after approval refills a final MiniMax H3 video prompt template covering timeline, UI events, player positions, and negative constraints. Two reference templates are required runtime inputs; if either is missing the skill stops and reports the package is incomplete rather than improvising.

It targets game creators, indie developers, and social-content makers wanting character-led menus and menu-interaction motion, and is explicitly not for playable game development, complex multi-page UI, exact brand-logo replication, or character-free title sequences. Note the stated compatibility constraint: it requires the MiniMax Hub agent (canvas workspace and MiniMax H3 generation) and is not portable to generic agent harnesses.

FAQ

What inputs do I provide?

Two player names, a game title, a target visual style (preset or custom), and optionally character reference images used only for identity mapping such as face, hairstyle, glasses, and proportions.

Why does it make an image before the video?

It generates one framework-preserving confirmation image so you can approve color, layout, buttons, icons, and typography before the final H3 video is built, avoiding wasted generation on the wrong direction.

What platform does it require?

The MiniMax Hub agent with its canvas workspace and MiniMax H3 generation. The skill states it is not portable to generic agent harnesses.

What is it not suitable for?

Playable game development, complex multi-page UI, exact brand-logo replication, and generic character-free title sequences.

What happens if a template is missing?

The two reference templates (confirmation-image and video-prompt) are mandatory runtime inputs; if either is unavailable the skill stops and reports the package is incomplete instead of inventing a different prompt structure.

All Files

5 files
meta.yaml1.4 KB
View
references/h3-video-prompt-template.md5.7 KB
View
SKILL.md8.0 KB
View
references/h3-confirmation-image-template.md13.5 KB
View
SKILL.cn.md3.0 KB
View

Install co-op-game-intro-generator

Download and extract the skill files to your .claude/skills/ directory.

Quick Setup:

  1. Copy the skill folder to .claude/skills/
  2. Claude will automatically detect and use the skill