Generate, edit, analyze, and convert images via configured vision models.
npx skills add https://github.com/Acosmi/CrabClaw --skill image-acosmi
Please help me install this Agent Skill. Skill: image Source: https://github.com/Acosmi/CrabClaw/tree/main/docs/skills/tools/ai/image Command: npx skills add https://github.com/Acosmi/CrabClaw --skill image-acosmi
图像处理全能工具提供一站式能力来生成、编辑、分析、缩放和格式转换，减少在不同工具间切换的复杂性与时间成本。
Use the image tool to generate or edit an image by supplying an action and a prompt.
High-intent search queries and answers about installing and using this skill.
Image generation and editing are handled through a unified tool that accepts an action and a prompt to create or modify visual content without switching applications.
Batch resizing and format conversion are supported natively, allowing you to process and transform images directly within design, marketing, and development workflows.
Image analysis uses configured vision models to identify content and extract text from images, processing multimodal inputs based on your selected provider.
You must configure vision models and providers to execute generation, analysis, and transformation commands, ensuring the underlying processing logic matches your task requirements.
Multimodal content creation and image enhancement are streamlined by supplying action-based prompts to a single tool, enabling rapid generation and micro-adjustments of visual assets.
John2143Describe images from local paths or URLs using vision-capable models.
mecolejrGenerate and retrieve images, videos, and stock images on demand.
KrishavRajSinghAutomate PDF text extraction, merging, and form filling with Python libraries.
KjdraganGenerate and edit images from text prompts using Gemini.
