AI Agent Skills

Wonky Cute Doodles 是 Skillry 提供的图像技能。原站标注的任务与风格包括 Create Doodle Illustration · Hand Drawn · Crayon Doodle · Naive Art。可先查看案例，再根据创作需求选择。

Apple Style OG Image 是 Skillry 提供的图像技能。原站标注的任务与风格包括 Create Og Image · Colorful Interface · Device Fan · Photoreal Mockup。可先查看案例，再根据创作需求选择。

Raycast Style OG Image 是 Skillry 提供的图像技能。原站标注的任务与风格包括 Create Og Image · Oversized Type · Gradient Italic · Neon Purple。可先查看案例，再根据创作需求选择。

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

A toolkit to run Ray applications on Kubernetes

REX-Ray is a container storage orchestration engine enabling persistence for cloud native workloads

Notebooks for the O'Reilly book "Learning Ray"

We are building an open database of COVID-19 cases with chest X-ray or CT images.

Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales f…

Build raymarched space phenomena in Three.js. Use for black-hole lensing, accretion disks, wormhole throat transits, curved-ray and null-geodesic integration, lensed cel…

[IROS'25] Source code for "RayFronts: Open-Set Semantic Ray Frontiers for Online Scene Understanding and Exploration"

Create new discussion roles and persona bundles that are compatible with ray-multi-party-mode. Use when Codex needs to add roles, design new personas, extend a role rost…

An open-source AI financial advisor that learns your situation and gets smarter every conversation.

从源文案/白皮书/长文拆解选题，生成完整的内容发布计划：20 个候选选题 → 5 个精选方向 → 备选标题 → 文案结构 → 多角色评分 → 发布节奏。 支持历史文案校准（提供 3-5 篇历史文章即可提取内容 DNA 并重新评分）。 当用户说「拆选题」「选题规划」「内容拆解」「topic planning」「拆一下选题」「从白皮书出选题…

Standalone multi-role discussion skill with built-in cross-functional personas. Supports both simulated role-play and true subagent orchestration. Use when the user asks…

A comprehensive guide to building RAG-based LLM applications for production.