Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Delegates image understanding to an OpenAI-compatible vision model through a script. Supports reading, describing, and reasoning about screenshots, photos, diagrams, charts, UI mockups, and scanned pages from local files or URLs.
Uses the MiniMax vision MCP tool to describe and extract information from images, screenshots, diagrams, and photos. Supports OCR, chart data extraction, object identification, UI mockup review, wireframe analysis, and design critique.
Implements computer vision features using modern Vision APIs and legacy VNRequest patterns. Covers image segmentation, document and live camera scanning, face detection, object tracking, and custom Core ML inference.
Adapt vision-language models to visual domains or tasks through supervised learning. Covers frozen-vision-tower LoRA configuration and troubleshooting runs that train without learning.
Supports visual content production for marketing channels, including social post images and infographics. Covers image specifications and adapting existing visuals for reuse across channels.
Uses foundational visual design principles to improve hierarchy and consistency. Supports design token creation, style guides, and cohesive use of typography, color, spacing, and icons.
Supports frontend changes informed by visual selections, screenshots, or drawn annotations. Uses element identity, DOM references, and layout data to supplement textual change requests.
Анализирует скриншот сайта или приложения как визуальное доказательство, определяет вероятный продукт и страницу, ищет официальную документацию, сверяет с живым сайтом и отвечает с URL и оценкой уверенности. Use для идентификации сайта, поиска функции, подсказок по интерфейсу и вопросов о содержимом экрана; не для генерации UI-кода.
Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data. Use when the user asks for a diagram, architecture overview, diff review, plan review, project recap, comparison table, or any visual explanation of technical concepts. Also use proactively when you are about to render a complex ASCII table (4+ rows or 3+ columns) — present it as a styled HT…
Establish a visual hierarchy so viewers encounter elements in the intended order. Uses size, weight, colour, spacing, and position when composing new work.
Produce a coherent visual identity (palette, typography, spacing, radius) from a brief and serialise to JSON for the design-tokens skill. Use when establishing brand identity.
Combines branching scripts with character and background presentation and choice-based text boxes. Includes saving, loading, backlog, skip, and automatic playback for visual novels and dating sims.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name