MLOps
模型部署、评估与运维
catboost
G1Joshi
CatBoost gradient boosting with categoricals. Use for tabular ML.
stable-diffusion
G1Joshi
Stable Diffusion image generation models. Use for image AI.
mlflow
G1Joshi
MLflow ML lifecycle management. Use for ML experiment tracking.
weights-biases
G1Joshi
Weights & Biases ML experiment tracking. Use for ML monitoring.
mistral
G1Joshi
Mistral AI efficient open models. Use for efficient AI.
jax
G1Joshi
JAX high-performance numerical computing. Use for ML research.
xgboost
G1Joshi
XGBoost gradient boosting library. Use for tabular ML.
Comunicador Documentación
scaleto
Enlace A2A del Grupo Documentación.
Comunicador Seguridad
scaleto
Enlace A2A del Grupo Seguridad.
Comunicador Marketing
scaleto
Enlace A2A del Grupo Marketing.
rails-model-patterns
ag0os
ActiveRecord model patterns and conventions for Rails. Automatically invoked when working with models, associations, validations, scopes, callbacks, or database schema design. Triggers on "model", "ActiveRecord", "association", "has_many", "belongs_to", "validation", "validates", "scope", "callback", "migration", "schema", "index", "foreign key".
local-tts
krishagel
Local text-to-speech using MLX and Kokoro model
event-modeling
jwilger
Event modeling facilitation for discovering and designing event-sourced systems. Four phases: domain discovery, workflow design (9-step process), GWT scenario generation, and model validation. Activate when starting a new project, designing features, modeling domains, writing Given/When/Then scenarios, or discussing event sourcing and domain-driven design.
ai-ml-senior-engineer
mOdrA40
Elite AI/ML Senior Engineer with 20+ years experience. Transforms Claude into a world-class AI researcher and engineer capable of building production-grade ML systems, LLMs, transformers, and computer vision solutions. Use when: (1) Building ML/DL models from scratch or fine-tuning, (2) Designing neural network architectures, (3) Implementing LLMs, transformers, attention mechanisms, (4) Computer vision tasks (object detection, segmentation, GANs), (5) NLP tasks (NER, sentiment, embeddings), (6) MLOps and production deployment, (7) Data preprocessing and feature engineering, (8) Model optimization and debugging, (9) Clean code review for ML projects, (10) Choosing optimal libraries and frameworks. Triggers: "ML", "AI", "deep learning", "neural network", "transformer", "LLM", "computer vision", "NLP", "TensorFlow", "PyTorch", "sklearn", "train model", "fine-tune", "embedding", "CNN", "RNN", "LSTM", "attention", "GPT", "BERT", "diffusion", "GAN", "object detection", "segmentation".
pipeline
jwilger
Autonomous build-phase orchestrator. Manages slice queue, TDD pair dispatch, full-team code review, mutation testing, CI integration, and auto-merge with quality gates. Replaces manual coordinator overhead during build phase. Activate when running factory mode with ensemble-team.
chunking-strategies
latestaiagents
Optimize document chunking for RAG performance and retrieval quality. Use this skill when splitting documents, choosing chunk sizes, implementing semantic chunking, or improving RAG retrieval accuracy. Activate when: chunking, split documents, chunk size, text splitting, document processing, RAG performance, semantic chunking, overlap.
elevenlabs-tts
krishagel
Generate high-quality audio from text using Eleven Labs API. Use for podcasts, narration, voice-overs, and audio summaries.
multi-model-research
krishagel
Orchestrate multiple frontier LLMs (Claude, GPT-5.1, Gemini 3.0 Pro, Perplexity Sonar, Grok 4.1) for comprehensive research using LLM Council pattern with peer review and synthesis
x-algo-pipeline
CloudAI-X
Explain the complete X recommendation algorithm pipeline. Use when users ask how posts are ranked, how the algorithm works, or want an overview of the recommendation system.
dlt-extract
dtsong
"Use this skill when building DLT pipelines for file-based or consulting data extraction. Covers Excel/CSV/SharePoint ingestion via DLT, destination swapping (DuckDB dev to warehouse prod), schema contracts for cleaning, and portable pipeline patterns. Common phrases: \"dlt pipeline for files\", \"extract Excel with dlt\", \"portable data pipeline\", \"dlt filesystem source\". Do NOT use for core DLT concepts like REST API or SQL database sources (use data-integration) or pipeline scheduling (use data-pipelines)."
ac-complexity-assessor
adaptationio
Assess feature and project complexity. Use when estimating effort, determining spec pipeline type, calculating cost estimates, or planning resource allocation.
x-algo-ml
CloudAI-X
Explain the Phoenix ML model architecture for X recommendations. Use when users ask about embeddings, transformers, how predictions work, or ML model details.
agent-cost-optimizer
adaptationio
Real-time cost tracking, budget enforcement, and ROI measurement for AI agent operations. Track token usage, predict costs, enforce budget caps ($50-70/month typical), optimize model selection, cache results, measure cost-to-value. Use when tracking AI costs, preventing budget overruns, optimizing spend, measuring ROI, or ensuring cost-effective AI operations.
cnn-vision
levy-n
Implements CNN architectures for computer vision tasks. Covers convolution operations, pooling, CNN design patterns (LeNet, ResNet, VGG), transfer learning, fine-tuning pretrained models, data augmentation, and image preprocessing. Use when building image classifiers, doing object detection, or when user mentions 'CNN', 'convolution', 'pooling', 'ResNet', 'VGG', 'transfer learning', 'fine-tuning', 'image augmentation', 'ImageNet', 'feature maps', 'MNIST', 'image classification', 'multi-modal', 'image captioning', or 'multimodal network'.