glmv-prompt-gen

Official

Create copy-paste AI art prompts from visuals

Authorzai-org
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Converting reference images or video clips into high-quality, ready-to-use prompts for text-to-image and text-to-video generators is time-consuming and requires prompt engineering skill. This Skill automates visual analysis and crafts detailed prompts that capture subject, style, lighting, composition, and mood so creators can reproduce or remix visuals quickly.

Core Features & Use Cases

  • Automated visual analysis: Extracts subject, style, color, lighting, composition, and atmosphere from images or videos.
  • Multi-mode outputs: Produces prompts tailored for text-to-image, text-to-video, or both (image/video/auto modes).
  • Language-aware prompts: Automatically chooses Chinese or English based on visual cues and text in the content.
  • CLI and programmatic use: Includes a Python script with validation, streaming support, output saving, and error handling.
  • Use Case: A designer uploads a reference photo and receives a polished Midjourney-ready prompt plus a breakdown explaining key prompt elements.

Quick Start

Ask the skill to analyze this image URL and produce a copy-paste-ready prompt for Midjourney that describes the subject, style, lighting, composition, color palette, and mood.

Dependency Matrix

Required Modules

requests

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: glmv-prompt-gen
Download link: https://github.com/zai-org/GLM-skills/archive/main.zip#glmv-prompt-gen

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.