MLOps
模型部署、评估与运维
fine-tuning-expert
Jeffallan
Use when fine-tuning LLMs, training custom models, or optimizing model performance for specific tasks. Invoke for parameter-efficient methods, dataset preparation, or model adaptation.
ml-pipeline
Jeffallan
Use when building ML pipelines, orchestrating training workflows, automating model lifecycle, implementing feature stores, or managing experiment tracking systems.
claudish-usage
MadAppGang
CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with any AI model (OpenRouter, Gemini, OpenAI, local models). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, Gemini, OpenAI, Ollama, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.
Write Social Media Announcements
Agenta-AI
Count the em dashes. More than one? Rewrite.
llm-icon-finder
daymade
Finding and accessing AI/LLM model brand icons from lobe-icons library. Use when users need icon URLs, want to download brand logos for AI models/providers/applications (Claude, GPT, Gemini, etc.), or request icons in SVG/PNG/WEBP formats.
ai-engineer
rmyndharis
Build production-ready LLM applications, advanced RAG systems, and
image-generate
bytedance
Generate images using Seedream models. Invoke when user wants to create images from text prompts or reference images.
threejs-loaders
CloudAI-X
Three.js asset loading - GLTF, textures, images, models, async patterns. Use when loading 3D models, textures, HDR environments, or managing loading progress.
surf
nicobailon
Control Chrome browser via CLI for testing, automation, and debugging. Use when the user needs browser automation, screenshots, form filling, page inspection, network/CPU emulation, DevTools streaming, or AI queries via ChatGPT/Gemini/Perplexity/Grok/AI Studio.
step-by-step
elie222
Execute tasks one step at a time with user confirmation
wait
elie222
Pause execution for a user-specified duration
next-step
elie222
Continue execution with the next requested step
llm-cli
glebis
Process textual and multimedia files with various LLM providers using the llm CLI. Supports both non-interactive and interactive modes with model selection, config persistence, and file input handling.
livewire-development
coollabsio
Develops reactive Livewire 3 components. Activates when creating, updating, or modifying Livewire components; working with wire:model, wire:click, wire:loading, or any wire: directives; adding real-time updates, loading states, or reactivity; debugging component behavior; writing Livewire tests; or when the user mentions Livewire, component, counter, or reactive UI.
livewire-development
coollabsio
Develops reactive Livewire 3 components. Activates when creating, updating, or modifying Livewire components; working with wire:model, wire:click, wire:loading, or any wire: directives; adding real-time updates, loading states, or reactivity; debugging component behavior; writing Livewire tests; or when the user mentions Livewire, component, counter, or reactive UI.
hugging-face-evaluation
huggingface
Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.
hugging-face-paper-publisher
huggingface
Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.
hugging-face-trackio
huggingface
Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API) or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, HF Space syncing, and JSON output for automation.
ray-data
Orchestra-Research
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.
awq-quantization
Orchestra-Research
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.
pytorch-lightning
Orchestra-Research
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. Use when you want clean training loops with built-in best practices.
training-llms-megatron
Orchestra-Research
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.
fine-tuning-with-trl
Orchestra-Research
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
ML Training Recipes
Orchestra-Research
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.