OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M...
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with...
Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI...
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with...
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models...
A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery.
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any...
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state...
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code....
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge,...
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create...
Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object...
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit
代码重构专家/代码重构，专注于大规模数据处理系统的代码重构。遵循 SOLID 原则、Go 语言惯用法（idiomatic Go）和企业级设计模式。当用户需要以下帮助时触发：(1) 重构代码 (2) 优化函数或方法 (3) 询问如何改进代码质量 (4) 降低代码复杂度 (5) 提升代码可维护性、可扩展性或可测试性。
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support
Write tests to reach a coverage target. Uses 4 agents (analyzer, writer, checker, fixer) to iteratively generate and fix tests. Exits non-zero with explanation if production code needs changes.
Feature planning with 4 phases - Specify requirements, Design architecture, break into granular Tasks, Implement and Validate. Creates atomic tasks that agents can implement without errors....
Git 命令包装器、仓库信息查询、Changelog 生成工具。用于执行 git 命令、查询仓库信息（分支/标签/远程）、生成变更日志。支持链式调用、gitmoji emoji 转换、GitHub Actions 集成。使用场景：(1) 需要在代码中执行 git 命令，(2) 查询仓库状态和分支信息，(3) 生成版本变更日志，(4) 解析 gitmoji 提交信息