ML Ops
Machine learning operations
car-advisor
by deusyu
实时汽车问答与对比分析系统。当用户询问任何买车、选车、汽车参数对比、车型评测、价格分析相关问题时触发此 Skill。 触发场景（只要涉及以下任一情形就必须使用此 Skill）： - 车型参数对比："小米SU7和Model 3哪个好"、"国产车和特斯拉对比" - 配置/价格查询："Model Y 焕新版座椅加热有吗"、"问界M9多少钱" - 真实车主评价："XX车口碑怎么样"、"懂车帝评分" - 购车决策辅助："20-30万预算推荐什么车"、"新能源SUV怎么选" - 车辆功能查询："这款车支持V2L吗"、"有没有露营模式" - 销量/市场数据："2024年最畅销新能源车" 即使用户没有明确说"帮我对比"或"查一下"，只要话题涉及具体车型的任何属性，都应该主动触发此 Skill 进行实时数据检索，而不是依赖训练数据回答。
refactor:scikit-learn
by SnakeO
Refactor Scikit-learn and machine learning code to improve maintainability, reproducibility, and adherence to best practices. This skill transforms working ML code into production-ready pipelines that prevent data leakage and ensure reproducible results. It addresses preprocessing outside pipelines, missing random_state parameters, improper cross-validation, and custom transformers not following sklearn API conventions. Implements proper Pipeline and ColumnTransformer patterns, systematic hyperparameter tuning, and appropriate evaluation metrics.
mlflow
by G1Joshi
MLflow ML lifecycle management. Use for ML experiment tracking.
debug:pytorch
by SnakeO
Debug PyTorch issues systematically. Use when encountering tensor errors, CUDA out of memory errors, gradient problems like NaN loss or exploding gradients, shape mismatches between layers, device conflicts between CPU and GPU, autograd graph issues, DataLoader problems, dtype mismatches, or training instabilities in deep learning workflows.
refactor:pytorch
by SnakeO
Refactor PyTorch code to improve maintainability, readability, and adherence to best practices. Identifies and fixes DRY violations, long functions, deep nesting, SRP violations, and opportunities for modular components. Applies PyTorch 2.x patterns including torch.compile optimization, Automatic Mixed Precision (AMP), optimized DataLoader configuration, modular nn.Module design, gradient checkpointing, CUDA memory management, PyTorch Lightning integration, custom Dataset classes, model factory patterns, weight initialization, and reproducibility patterns.
xgboost
by G1Joshi
XGBoost gradient boosting library. Use for tabular ML.
deepchem
by hxk622
Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first PyTorch workflows use torchdrug; for benchmark datasets use pytdc.
scvi-tools
by hxk622
Deep generative models for single-cell omics. Use when you need probabilistic batch correction (scVI), transfer learning, differential expression with uncertainty, or multi-modal integration (TOTALVI, MultiVI). Best for advanced modeling, batch effects, multimodal data. For standard analysis pipelines use scanpy.
runpod-serverless-builder
by AvivK5498
Build production-ready RunPod serverless endpoints with optimized cold start times. Use when creating or modifying RunPod serverless workers for (1) vLLM-based LLM inference, (2) ComfyUI image/video generation, or (3) custom Python inference. Supports both baked models (fastest cold starts) and dynamic loading (shared models). Generates complete projects including Dockerfiles, worker handlers, startup scripts, and configuration optimized for minimal cold start latency.
arboreto
by hxk622
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.
agentform
by AvivK5498
Create and debug Agentform AI agent configurations (.af files). Use when: (1) Creating new agentform projects or workflows (2) Debugging agentform syntax errors (3) Adding MCP server integrations (4) Configuring agents, models, policies, or capabilities (5) Writing workflow steps with routing and human approval Agentform is "Infrastructure as Code for AI agents" - declarative .af files define agents, workflows, and policies.
geniml
by hxk622
This skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), building consensus peaks (universes), or any ML-based analysis of genomic regions. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.
archive-reprocessing
by ilude
Flexible, version-tracked reprocessing system for archive transformations using design patterns (Strategy, Template Method, Observer). Activate when working with tools/scripts/lib/, reprocessing scripts, transform versions, archive transformations, metadata transformers, or incremental processing workflows.
esm
by hxk622
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel proteins; generating protein embeddings; performing inverse folding; or conducting protein engineering tasks. Supports both local model usage and cloud-based Forge API for scalable inference.
deep-learning
by Aznatkoiny
"Comprehensive guide for Deep Learning with Keras 3 (Multi-Backend: JAX, TensorFlow, PyTorch). Use when building neural networks, CNNs for computer vision, RNNs/Transformers for NLP, time series forecasting, or generative models (VAEs, GANs). Covers model building (Sequential/Functional/Subclassing APIs), custom training loops, data augmentation, transfer learning, and production best practices."
hytale-custom-assets
by MnkyArts
Create and manage custom assets for Hytale including models, textures, sounds, particles, and asset packs. Use when asked to "add custom assets", "create textures", "make models", "add sounds", "configure particles", or "build an asset pack".
Computer Vision Helper
by jmsktm
Assist with image analysis, object detection, and visual AI tasks
hytale-custom-blocks
by MnkyArts
Create custom block types for Hytale with textures, physics, states, farming, and interactions. Use when asked to "add a custom block", "create a new block type", "make blocks farmable", "add block interactions", or "configure block physics".
cloudflare-workers-ai
by jackspace
Complete knowledge domain for Cloudflare Workers AI - Run AI models on serverless GPUs across Cloudflare's global network. Use when: implementing AI inference on Workers, running LLM models, generating text/images with AI, configuring Workers AI bindings, implementing AI streaming, using AI Gateway, integrating with embeddings/RAG systems, or encountering "AI_ERROR", rate limit errors, model not found, token limit exceeded, or neurons exceeded errors. Keywords: workers ai, cloudflare ai, ai bindings, llm workers, @cf/meta/llama, workers ai models, ai inference, cloudflare llm, ai streaming, text generation ai, ai embeddings, image generation ai, workers ai rag, ai gateway, llama workers, flux image generation, stable diffusion workers, vision models ai, ai chat completion, AI_ERROR, rate limit ai, model not found, token limit exceeded, neurons exceeded, ai quota exceeded, streaming failed, model unavailable, workers ai hono, ai gateway workers, vercel ai sdk workers, openai compatible workers, workers ai vectorize
flash-attention
by tylertitsworth
"Flash Attention, FlashInfer, SDPA backends, PagedAttention, and attention kernel selection/configuration. Use when choosing or configuring attention backends for training or inference (FlashAttention-2/3, FlashInfer, SDPA, xFormers, PagedAttention, Ring Attention, FlexAttention/FlexDecoding, varlen_attn)."
transformers-js
by nico-martin
Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in Node.js and browsers (with WebGPU/WASM) using pre-trained models from Hugging Face Hub.
fermi-estimation
by tumf
Solve user questions with defensible Fermi estimates using explicit assumptions, source-backed inputs, uncertainty ranges, and sensitivity analysis. Use when exact data is unavailable or too slow to collect but the user still needs a quantitative answer for counts, market size, demand, costs, revenue, capacity, timing, or operational scale. Autonomously gather accessible evidence, prefer current primary sources, and drive to a conclusion without asking for approval.
aiconfigurator
by tylertitsworth
"NVIDIA AIConfigurator — optimal LLM serving configuration for disaggregated/aggregated deployments, parallelism selection (TP/PP/EP/DP), quantization, and MOE planning. Use when planning model deployment topology on NVIDIA GPUs."
jackyshen-design-workshop-outline
by mebusw
Use when user asks to "generate workshop outline", "create training agenda", "design course structure", "build workshop schedule", or requests help planning training sessions. Applies MECE structure, TfBR design (4Cs), and VAK-inclusive learning.