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.
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…
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.
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…
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…
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.
Prepare high-quality datasets for LLM fine-tuning with filtering, deduplication, augmentation, and RLHF data formatting.
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 Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots. — from ilderaj/agent-plugin-marketplace
Use when when you have: (1) a collection of molecules represented as molecular graphs (nodes=atoms, edges=bonds with chirality/order attributes); (2) structured metadata…
Use when you have a baseline GNN model trained on a molecular property prediction task (e.
Use when evaluating GraphRAG system quality across knowledge graph completeness, retrieval relevance, answer correctness, and reasoning verification.
Use when designing complete GraphRAG systems that combine graph retrieval with LLM reasoning. Invoke when user mentions GraphRAG system, technology stack, Neo4j with LLM,…
Hybrid interview that probes AI-engineering mastery by tip-vocabulary depth — entity referencing, loop closure, observability, harness improvement — not by token usage or LOC.
Hierarchical Task Network planning (provably correct plans via symbolic decomposition + LLM fallback) and AlphaEvolve evolutionary code search (fitness-gated genetic algorithm).
Manage Huawei ModelArts training jobs (GPU and Ascend NPU cost governance), Pangu foundation model deployment, AI Gallery model management, and MLOps pipeline automation for AI/ML…
Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots. — from yanochka11/harness_bro
Deploys models from Hugging Face Hub to Inference Endpoints using the huggingface_hub client and REST API.
Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference…
Receive and verify Hugging Face webhooks. Use when setting up Hugging Face webhook handlers, debugging X-Webhook-Secret verification, or handling events on models, datasets, and…
AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU. Use when writing or reviewing code that uses `@spaces.GPU`, configuring `python_version` or…
Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, o — from…
Design, generate, and fully deploy a stylish, production-ready Retrieval-Augmented Generation (RAG) chatbot embedded directly into any website/project.
Build the internal link graph for a site, run PageRank-style authority distribution, detect orphan pages, and recommend new internal links via embedding-based semantic similarity…
Use when you have defined a Keras model architecture (convolutional and dense layers) accepting raw mass spectrometry imaging data tensors and need to prepare it for training on…
KV-cache optimization patterns for LLM inference. Prefix caching, sliding window attention, cache reuse across turns, static cache for fixed prompts, and TTFT reduction…
Use when implementing a LangChain-based agent runtime from an approved ai-architecture.md agent control-flow design.
LightRAG is a Python-based retrieval-augmented generation framework that builds knowledge graphs from documents for more connected, contextual retrieval.
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral).
Automatically applies when building LLM applications. Ensures proper async patterns for LLM calls, streaming responses, token management, retry logic, and error handling.
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring.
Build automated LLM evaluation pipelines with benchmarks, regression tests, RAGAS, and human eval workflows.
Use when user needs ML model deployment, production serving infrastructure, optimization strategies, and real-time inference systems.
Supervised and unsupervised learning, bias-variance tradeoff, cross-validation, decision trees, ensemble methods, neural network fundamentals, and the practitioner's workflow from…
MemGPT virtual context — OS virtual-memory analogy for LLM context management. Two-tier (main context = RAM, external store = disk), page-in/page-out tools, archival/core memory…
Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring.
Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring.
Operate as an ML engineer who takes a research model to reliable production behind eval gates and keeps it healthy across its lifecycle.
Expert in building scalable ML systems, from data pipelines and model training to production deployment and monitoring.
Déploiement de modèles ML en production (MLOps). Se déclenche avec "déployer un modèle", "ML deployment", "MLOps", "model serving", "inference", "model registry", "ML pip — from…
Build end-to-end ML pipelines with automated data processing, training, validation, and deployment using Airflow, Kubeflow, and Jenkins
Complete end-to-end MLOps pipeline orchestration from data preparation through model deployment.
Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment.
Design and implement ML operations — model registry, serving patterns, deployment strategies (shadow/canary/blue-green), drift detection, feature stores, retraining triggers, and…