普莫雍措 · AI技能市场

Extract frames or short clips from videos using ffmpeg.

Resize, crop, compress, and convert images.

A framework for high-performance medical image processing, neural network inference and visualizatio...

an architecture for neural network inference in real-time audio applications

Neural network inference template for real-time cricital audio environments - presented at ADC23

AMD OpenVX modules: such as, neural network inference, 360 video stitching, etc.

Hermes-first 智能体技能 that turns long videos into captioned, viral-ready social clips — local engine, a...

传统相术图片分析技能 - 面相、手相、骨相、体相 Chinese Physiognomy Image Analysis Skill

Spec-first gpt-image-2 workbench: bilingual prompt packs, CLI/Skill 工作流s, cost estimates, preflight ...

Text to Video API 生成 文档

即梦网页端生图技能 / Dreamina image skill with reference-image upload, model controls, and local downloads

個人在用ㄉGemini介面，我覺ㄉ蠻好用的給大家用用看，需申請自己的 API 才能用，Gemini 2.5 Pro 訂閱價650不白嫖一下嗎？Advanced Gemini API interface...

Turn your Dropbox into a searchable knowledge base. OpenClaw skill with delta-based sync, multi-form...

Installable agent 技能： generating Android and iOS app icon sets from a single source image via npx sk...

智能体技能: Generate SRT subtitle files from video using Whisper. Free, local, no API key.

The **2D to 3D Image Converter** project showcases the intersection of artificial intelligence and 3...

OpenClaw 技能： generating Xiaohongshu cover and carousel images as SVG, PNG, and JPG.