MLOps
模型部署、评估与运维
single2spatial-spatial-mapping
Starlitnightly
Map scRNA-seq atlases onto spatial transcriptomics slides using omicverse's Single2Spatial workflow for deep-forest training, spot-level assessment, and marker visualisation.
context-fundamentals
guanyang
This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Provides foundational understanding of context engineering for AI agent systems.
stac-custom-extensions
StacDev
Scaffold and integrate custom Stac widgets and actions with parsers and registration checks. Use when users ask to build new StacParser or StacActionParser implementations, generate custom model classes, or verify parser registration inside Stac.initialize.
video-generate
bytedance
Generate videos using Seedance models. Invoke when user wants to create videos from text prompts, images, or reference materials.
content-modeling
adobe
Create effective content models for your blocks that are easy for authors to work with. Use this skill anytime you are building new blocks, making changes to existing blocks that modify the initial structure authors work with.
audiocraft-audio-generation
NousResearch
PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.
nemo-curator
NousResearch
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
modal-serverless-gpu
NousResearch
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.
llava
NousResearch
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.
huggingface-tokenizers
NousResearch
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
gguf-quantization
NousResearch
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
grpo-rl-training
NousResearch
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
obliteratus
NousResearch
Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods (+ 4 Python-API-only), 15 analysis modules, 116 model presets across 5 compute tiers. Use when a user wants to uncensor, abliterate, or remove refusal from an LLM.
evaluating-llms-harness
NousResearch
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
dspy
NousResearch
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming
jupyter-live-kernel
NousResearch
Use a live Jupyter kernel for stateful, iterative Python execution via hamelnb. Load this skill when the task involves exploration, iteration, or inspecting intermediate results — data science, ML experimentation, API exploration, or building up complex code step-by-step. Uses terminal to run CLI commands against a live Jupyter kernel. No new tools required.
huggingface-accelerate
NousResearch
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
outlines
NousResearch
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library
peft-fine-tuning
NousResearch
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
huggingface-tokenizers
NousResearch
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
nemo-curator
NousResearch
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
llama-cpp
NousResearch
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
huggingface-hub
NousResearch
Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces and buckets.
lambda-labs-gpu-cloud
NousResearch
Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.