Image & Video Generation

This skill generates academic diagrams and figures from text descriptions of research methodologies.

This tool helps extract text from PDF documents and images, supporting both Chinese and English languages.

This skill uses an AI model to generate images from text descriptions or reference images, with options for different styles and resolutions.

This skill generates a pack of themed photos from a single reference image, ensuring the person's identity remains consistent across all generated images.

This skill transforms raw text content into a mobile-friendly newspaper-style image, suitable for sharing.

This skill allows you to create, modify, and organize images using OpenAI's AI image generation tools.

This skill allows you to generate and edit images using the Gemini 3 Pro Image model.

This skill generates photorealistic architectural visualizations and renders from text descriptions, sketches, and floor plans using the each::sense AI service.

This skill generates AI images using the EvoLink API, allowing users to create pictures from text prompts.

This skill helps you resize images using the ImageMagick command-line tool.

This skill generates images based on your text descriptions using the Nano Banana Pro model via OpenRouter.

This skill allows you to generate images using the Zhipu AI CogView model.

This skill generates animated pixel art GIFs from your photos, allowing you to create custom animations like waving or dancing sprites.

This skill helps you sync and process notes, sketches, and drawings from your reMarkable tablet using a cloud API.

This skill helps you log your calorie intake and view reports, automatically updating the report image after each entry.

This skill helps protect your OpenClaw configuration by automatically backing it up before making changes, verifying the changes, and providing a way to revert if something goes wrong.

This tool analyzes your posting patterns in a profile file to classify whether you are an Agent, Human, Cron, or Hybrid.

This skill acts as an early childhood education assistant, providing guidance on lesson planning, activity design, and child development for ages 45 days to 2 years, based on the EYFS framework and Reggio Emilia approach.

This skill allows you to automate tasks on your Windows desktop by taking screenshots, extracting text from images, and locating UI elements.

This skill helps you quickly send local images to a specified channel, automatically compressing large images before sending.

This skill automatically sends you a notification whenever the OpenClaw gateway restarts, informing you of its status.

Generates standardized text descriptions for scientific figures and images.

This skill uses the Tesseract OCR engine to extract text from images.

This skill helps you create various types of charts and graphs from your data using an online service.