Loading...
Loading...
Found 116 Skills
Understand images with Alibaba Cloud Model Studio Qwen VL models (qwen3-vl-plus/qwen3-vl-flash and latest aliases). Use when building image Q&A, visual analysis, OCR-like extraction, chart/table reading, or screenshot understanding workflows.
Process and generate multimedia content using Google Gemini API for better vision capabilities. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (better image analysis than Claude models, captioning, reasoning, object detection, design extraction, OCR, visual Q&A, segmentation, handle multiple images), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image with Imagen 4, editing, composition, refinement), generate videos (text-to-video with Veo 3, 8-second clips with native audio). Use when working with audio/video files, analyzing images or screenshots (instead of default vision capabilities of Claude, only fallback to Claude's vision capabilities if needed), processing PDF documents, extracting structured data from media, creating images/videos from text prompts, or implementing multimodal AI features. Supports Gemini 3/2.5, Imagen 4, and Veo 3 models with context windows up to 2M tokens.
Convert documents (PDF, Word, Excel, PowerPoint, images, HTML) to Markdown using microsoft/markitdown. Use for document analysis, content extraction, preprocessing for LLMs, or batch document conversion. Supports images with OCR/LLM descriptions, audio transcription, and ZIP archives.
Straightforward text extraction from document files (text-based PDF only for now, no OCR or docx). Use when you just need to read/extract text from binary documents.
Return public original model architecture diagrams for user-specified LLM, VLM, MoE, diffusion, OCR, and SGLang/sgl-cookbook model families. Use when the user asks for a model structure chart, architecture diagram, or rendered image link for a specific model such as DeepSeek, GLM, Qwen, Kimi, MiniMax, Step, Hunyuan, or Qwen3-VL.
AI screen memory — search everything you've seen or heard on your computer. Integrates with Screenpipe's local MCP server for OCR text, audio transcripts, and app usage history.
MCP server for computer use & browser automation - screenshot, OCR, click, type, find_text, Chrome/Electron CDP, template matching on macOS, Windows & Android
Official skill for recognizing handwritten text from images using ZhiPu GLM-OCR API. Supports various handwriting styles, languages, and mixed handwritten/printed content. Use this skill when the user wants to read handwritten notes, convert handwriting to text, or OCR handwritten documents.
Extract text and metadata from PDF files using pdf-parse. Use when: user uploads a PDF or asks to read/analyze PDF content. NOT for: creating PDFs, editing PDFs, or OCR on scanned documents.
macOS screen capture, window recording, GIF conversion, and agent evidence bundles from the terminal. Built on ScreenCaptureKit for window-level targeting ffmpeg cannot do. Use when the user wants a screenshot of a specific window or app, a screen recording, a GIF conversion, a before/after diff, an evidence bundle for a PR, OCR text from a window, a terminal VHS recording, a Remotion render, or wants to watch a UI for changes. Requires macOS Screen Recording permission on first run.
Async media + document derivations via `platform.media.transforms` and the declarative `transforms` block in `maravilla.config.ts`. Media: transcode video, thumbnail extraction, image resize/variants, OCR. Documents (.docx/.odt/.pptx/.xlsx/...): convert to PDF, render page thumbnails, generic format conversion, Markdown extraction (RAG-ready), single-file HTML with inlined images, image-replacement templating ({{TAG}} swap + named-object swap), QR-code injection. Use when ingesting user uploads that need normalised renditions, generating contracts/invoices from templates, or extracting structured content for LLMs. Critical: derived keys are content-addressed — `keyFor(srcKey, spec)` is known up front, before the worker starts, so clients can render placeholder UI without round-trips. Declarative config is the default; imperative `transforms.*` calls are for one-offs.
Score and compare images using vision LLMs as judges. YAML-defined criteria presets for 11 use cases (text-to-image, photorealism, document OCR, charts, UI, portrait, product, scientific, invoice, alt-text, artistic style). Supports OpenAI, Anthropic, Gemini, Mistral, and OpenRouter as judge providers. Keys auto-decrypted via SOPS + age.