Copilot agent that assists with machine learning model development, training, evaluation, deployment, and MLOps
Use this when: design an AI system, RAG vs fine-tuning, my agent keeps looping, architect a multi-agent system, which LLM should I use, context window keeps overflowing, add…
Delegate a coding task to Aider (`aider`) as a background implementer, then review its diff and land it yourself.
Create components using Angular CDK utilities including drag-drop, overlay, portal, scrolling, a11y, clipboard, and platform detection for ng-events project
Anime.js 4.0 animations for Web Components — drag-drop, click feedback, swaps, cancelable motion. Use when adding animations, drag interactions, visual feedback, or motion to…
Use when an approved ai-architecture.md defines an Anthropic Claude retrieval-augmented capability. Produces a retrieval adapter, context packing, grounding prompt, Citations-API…
Use when an approved ai-architecture.md needs an Anthropic Claude capability returning schema-bound JSON, typed objects, classifications, or extractions.
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring.
Together AI SDK patterns for TypeScript — client setup, chat completions, streaming, structured output, function calling, embeddings, image generation, fine-tuning, and O — from…
Azure Data Scientist Associate (DP-100) grounded skill. Covers ML solution design, data exploration, model training, AutoML, hyperparameter tuning, model deployment, MLflow, and…
Expert knowledge for Azure Machine Learning development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security,…
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics.
Machine learning toolkit for big data teams. Includes scikit-learn, PyTorch Lightning, Transformers, SHAP for model training, deployment, and interpretation.
Use this for disciplined software implementation work that should follow planning-first execution, test-guided development, review-before-finalization, and explicit verification.
Use this when starting any non-trivial coding work to apply the four engineering principles — Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution.
Build or repair game inventory, loot, equipment, tooltips, drag-and-drop, persistence, and progression systems.
Build automated machine learning pipelines with feature engineering, model selection, and hyperparameter tuning.
Build persistent memory systems for AI agents using Mem0, claude-mem, or custom implementations. Use when adding conversation memory, user preferences, or contextual reca — from…
Build persistent memory systems for AI agents using Mem0, claude-mem, or custom implementations. Use when adding conversation memory, user preferences, or contextual reca — from…
Use ao tocar arquitetura do Cidadão.AI backend — request flow, services layer, LLM providers, infraestrutura.
Install, manage, and run ComfyUI instances. Use when setting up ComfyUI, launching servers, installing/updating/debugging custom nodes, downloading models from…
Build computer vision systems using CNNs and modern architectures. Use for image classification, object detection (YOLO, Faster R-CNN), image segmentation, face recognition, and…
Use when designing or evaluating a Salesforce conversational AI deployment that involves Agentforce agents, Einstein Bots, or a combination of both.
Builds a portable, embedding-free knowledgebase from a set of files and delivers it as a self-contained `.skill` bundle (BM25 index + bundled searcher + query protocol).
Use when an approved ai-architecture.md defines a multi-agent workflow and CrewAI is the chosen framework.
Use when an approved ai-architecture.md defines CrewAI tasks or callable tools. Produces task decomposition, tool schemas, an auth-enforcing execution adapter, idempotency, audit…
Deep GPU/CUDA operational intuition — nvidia-smi/dcgm fields, NCCL tuning, MIG vs MPS, NVLink/InfiniBand/GPUDirect, Nsight profiling, Xid/ECC diagnosis, Hopper/Blackwell…
Comprehensive data science, machine learning, and AI guide covering Python, deep learning, NLP, LLMs, prompt engineering, and MLOps.
Master machine learning, data engineering, AI engineering, LLMs, prompt engineering, and MLOps. Build intelligent systems with Python.
Create your LLMOps data engineering skill in one prompt, then learn to improve it throughout the chapter — from majiayu000/claude-skill-registry
Debug why inference.local, direct external inference, or supervisor-only system inference is failing.
Use when you have two augmented versions of the same ion image (from mass spectrometry imaging data) and need to extract learnable 512-dimensional feature representations using a…
Build and train deep neural networks including CNNs, RNNs, Transformers, and advanced architectures. Use for image classification, object detection, NLP, sequence modeling,…
Use when after converting or loading a Keras model to HDF5 TensorFlow 2.3.0 format, especially when the model will be served through a pipeline (e.g., NP Classifier) that expects…
Use when you have a pretrained deep learning model, a reserved test set with ground-truth annotations, and need to evaluate prediction quality or generate embeddings for…
Use when you have cloned or loaded a deep-learning architecture extension (e.g., chemprop-IR) and need to verify that its feature extraction component can be instantiated and…
Guidelines for deep learning development with PyTorch, Transformers, Diffusers, and Gradio for LLM and diffusion model work.
Compose Multiplatform Desktop patterns for the `desktopApp/` module. Use when working with (1) Desktop-only APIs (Window, WindowState, Tray, MenuBar, Dialog), (2) keyboard…
UNIFIED DEBUGGER - Use when tasks disappear, data is lost, things are broken, or bugs need fixing. Debug Vue.js reactivity, Pinia state, task store CRUD, keyboard shortcuts,…
Déploiement de modèles ML en production (MLOps). Se déclenche avec "déployer un modèle", "ML deployment", "MLOps", "model serving", "inference", "model registry", "ML pip — from…
Diffusion model training and inference patterns including UNet/DiT architectures, noise schedules, CFG, ControlNet, and LoRA.
PDF/DOCX/XLSX/PPTX generation and parsing on Cloudflare Workers. Covers CF Browser Rendering → PDF, pdf-lib Worker-native generation, docx/exceljs output, pptxgenjs slides, and…
Use when deciding whether a computer-vision project should target ECCV — weighing the two-year even-year cadence against CVPR, ICCV, WACV, BMVC, ACCV, NeurIPS, and journal routes,…
Embedding backends (InsightFace/PyTorch+ONNXRuntime vs TensorRT). Use when optimizing embedding throughput or debugging drift/fallbacks.
Optimizing vector embeddings for RAG systems through model selection, chunking strategies, caching, and performance tuning.
Embed and execute external binaries (sidecars) in Tauri apps: configuration, cross-platform executable naming, and Rust/JavaScript spawn APIs.
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), imple — from…
Execute create, select, and transform features to improve machine learning model performance. Handles feature scaling, encoding, and importance analysis.
Eval-driven agent development — 3-layer evaluation (static benchmarks, custom offline, online production). Evaluator-optimizer tight loop. Evals in CI, score-gated PRs.
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics.
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics.
Build face recognition systems with InsightFace, ArcFace, enrollment pipelines, HDBSCAN clustering, and privacy-compliant architecture.
ML Engineer role: LLM APIs (OpenAI, Claude, Gemini), embeddings, RAG pipelines, fine-tuning, LangChain, LlamaIndex, vector databases (Pinecone, Chroma, Weaviate), prompt…
Prepare high-quality datasets for LLM fine-tuning with filtering, deduplication, augmentation, and RLHF data formatting.
Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO — from…
Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO en — from…
Forge playbook for production ML systems (opt-in Python) — training-to-serving lifecycle. Use for MLOps, model registry, MLflow, drift monitoring, A/B test, canary, rollback.
Manage Vertex AI Training jobs (GPU/TPU cost governance), Vertex AI Pipelines, Model Registry, Feature Store, Endpoints, and Gemini API integration for production MLOps.
Build RAG systems and semantic search with Gemini embeddings (gemini-embedding-001). 768-3072 dimension vectors, 8 task types, Cloudflare Vectorize integration.
Build RAG systems and semantic search with Gemini embeddings (gemini-embedding-001). 768-3072 dimension vectors, 8 task types, Cloudflare Vectorize integration.