MLOps
模型部署、评估与运维
ai-system-training-feedback
Eitanvinokur12345
"Refining AI agent behavior and capabilities through continuous learning."
training-data-curation
sundial-org
Guidelines for creating high-quality datasets for LLM post-training (SFT/DPO/RLHF). Use when preparing data for fine-tuning, evaluating data quality, or designing data collection strategies.
tinker
sundial-org
Fine-tune LLMs using the Tinker API. Covers supervised fine-tuning, reinforcement learning, LoRA training, vision-language models, and both high-level Cookbook patterns and low-level API usage.
tinker-training-cost
sundial-org
Calculate training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.
nemotron-nano3
toxicwind
Reference desk for Nemotron 3 Nano / Llama-Nemotron Nano 3 — architecture, training data, recipes, evaluation, quantization, deployment. Use when the architect asks facts about the model rather than building a pipeline.
nemotron-customize
toxicwind
"Plan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation, translation, SFT/PEFT (AutoModel or Megatron-Bridge), pretraining/CPT, RL alignment (DPO/RLVR/GRPO/RLHF), BYOB/MCQ benchmarks, checkpoint conversion, ModelOpt optimization, env profiles, and evaluation of trained checkpoints or existing/hosted endpoints. Use when a request names a Nemotron step or workflow, or asks to clean, translate, train, fine-tune, align, convert, optimize, evaluate, or compose these into a pipeline. Do NOT use for frontend/dashboard/visualization work, generic ML advice, billing/access, or non-Nemotron coding tasks."
nemotron-ultra
toxicwind
Reference desk for NVIDIA Nemotron 3 Ultra (550B-A55B) — architecture, NVFP4 pretraining, SFT, MOPD (multi-teacher on-policy distillation), MTP boosting, quantization, inference. Use when the architect asks facts about Ultra rather than building a pipeline.
human-in-the-loop-data-collection
Eitanvinokur12345
"Collecting diverse and nuanced data for AI systems that require understanding of human behavior, interaction with environments, and complex physical tasks."
dataverse-plugins
DanielKerridge
Use when developing, registering, or deploying Dataverse plugins (C# server-side extensions). Covers the IPlugin interface, execution pipeline stages, entity images, common patterns (auto-numbering, cascading updates, validation), and registration/deployment. Triggers on: "plugin", "server-side logic", "business logic", "auto-number", "cascading update", "pre-operation", "post-operation", "plugin registration", "IPlugin", "execution pipeline", "plugin trace", "InvalidPluginExecutionException", "PreValidation", "PostOperation".
nemotron-super3
toxicwind
Reference desk for NVIDIA Nemotron 3 Super — architecture, training data, recipes (pretrain/SFT/RL/eval/quantization), and deployment notes. Use when the architect asks facts about Super3 rather than building a pipeline.
speech-to-text
martinholovsky
"Expert skill for implementing speech-to-text with Faster Whisper. Covers audio processing, transcription optimization, privacy protection, and secure handling of voice data for JARVIS voice assistant."
llm-integration
martinholovsky
"Expert skill for integrating local Large Language Models using llama.cpp and Ollama. Covers secure model loading, inference optimization, prompt handling, and protection against LLM-specific vulnerabilities including prompt injection, model theft, and denial of service attacks."
model-quantization
martinholovsky
"Expert skill for AI model quantization and optimization. Covers 4-bit/8-bit quantization, GGUF conversion, memory optimization, and quality-performance tradeoffs for deploying LLMs in resource-constrained JARVIS environments."
gemini
G1Joshi
Google Gemini AI models for multimodal tasks. Use for multimodal AI.
arboreto
ovachiever
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.
huggingface
G1Joshi
Hugging Face transformers library and hub. Use for NLP models.
aeon
ovachiever
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.
ray
G1Joshi
Ray distributed computing framework. Use for scaling ML.
cost-planning-for-solana-apps
SanctifiedOps
Estimate and control costs for Solana apps: RPC, indexing, storage, bots, and on-chain fees. Use for budgeting and scaling.
domain-driven-design
G1Joshi
DDD tactical and strategic patterns. Use for complex domains.
deepseek
G1Joshi
DeepSeek AI models for coding. Use for code AI.
pytorch
G1Joshi
PyTorch deep learning framework with dynamic graphs. Use for neural networks.
capa-officer
ovachiever
Senior CAPA Officer specialist for managing Corrective and Preventive Actions within Quality Management Systems. Provides CAPA process management, root cause analysis, effectiveness verification, and continuous improvement coordination. Use for CAPA investigations, corrective action planning, preventive action implementation, and CAPA system optimization.
clip
ovachiever
OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.