Results for “munger”

Configure fault tolerance, straggler detection, preemption, in-process restart, and re-run state machine for Megatron Bridge training jobs.

Build production-quality Model Context Protocol (MCP) servers in C#/.NET using the official 1.x NuGet packages, covering transports, tools, prompts, resources, and common pitfalls.

Plan, debug, tune, evaluate, export, or deploy public Nemotron embedding and reranking retrieval recipes using the current checkout.

Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks, including model serving, feature engineering, A/B testing, and monitoring.

Create a dark monochrome procedural background with enlarged square pixels and visible Bayer-style ordered dithering. Use when a page needs an atmospheric near-black dither field, broad organic waves or cloud masses, and restrained gray-white highlights behind framed UI, hero content, or data overlays.

💻 MacBook Optimizer

Official Puppeteer Model Context Protocol Server for browser automation.

Orchestrates three frontier models to debate a question and synthesizes their best insights into a single superior answer.

List, configure, authenticate, call, and inspect MCP servers/tools with mcporter over HTTP or stdio.

Optimize MATLAB design files for GPU Coder to generate faster CUDA code. Iteratively profiles, rewrites, and benchmarks until performance targets are met or diagnostics are resolved. Use when asked to: optimize for GPU Coder, improve GPU codegen performance, profile generated GPU/CUDA code, profile GPU MEX, fix gpuPerformanceAnalyzer diagnostics, speed up GPU MEX, reduce GPU memory transfers, improve kernel parallelism, rewrite MATLAB for CUDA, or run gpuPerformanceAnalyzer.

Mechanics for building and managing pollers — subprocess scripts that check external services on a schedule and emit events when something has changed. Use when authoring a new poller (a `pollers.json` manifest plus a script in any language), debugging why a poller isn't firing, or extending an existing one. Pollers run on cron, emit JSONL events when there's something to report, and stay silent otherwise (silence-as-filter). The framework discovers `<home>/skills/<name>/pollers.json` files at startup and via `reload_pollers`; each emitted event becomes a fresh turn on a `poller:<name>` synthetic channel. Companion to the `world-scanning` skill, which catalogs *what's worth polling*. Distinct from `async-tasks` (one-shot wake-up via bash_async, not recurring) and from in-process scheduler callables (saga-consolidate, oauth-usage-poll — those mutate mimir-internal state and aren't subprocess-isolated).

Entrena modelos de machine learning con Scikit-learn, LightGBM y XGBoost, desde un baseline hasta un modelo productivo con validación robusta y explicabilidad.

Build Windows images with Packer using WinRM communicator and PowerShell provisioners. Use when creating Windows AMIs, Azure images, or VMware templates.

Expert guidance for Mojo, the programming language by Modular that combines Python's usability with C-level performance. Helps developers write high-performance AI/ML code, optimize numerical computations with SIMD and parallelism, and gradually port Python code to Mojo for orders-of-magnitude speedups.

MLOps Engineer IA — Expert en déploiement de modèles ML (A/B testing, feature stores, MLflow, Kubeflow). Industrialise le ML du notebook à la production.

Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring. Use PROACTIVELY for ML model deployment, inference optimization, or production ML infrastructure.

Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.

Analyze Framer's marketing site design system, including color palette, typography hierarchy, spacing, and component patterns, to produce a structured design specification.

Apply Miller's Law and chunking strategies to group information into meaningful units, making interfaces easier to scan, understand, and recall.

Use when the request is broad and spans idea evaluation, MVP planning, UX, frontend, backend, database, auth, integrations, and launch strategy. Trigger on asks like "build this app", "turn this idea into a product", "design the whole system", or "plan everything end to end".

Containeriza aplicaciones con Docker: crea Dockerfiles multi-stage, docker-compose.yml, y manifiestos de Kubernetes, optimiza imágenes y depura contenedores.

Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring.

Use when building a cursor trail whose spacing stays constant at any hand speed by emitting motes per distance travelled (not on a timer)—sub-segment placement, ring-buffer ordering, idle breath, 3D screen anchoring, coasting, touch and reduced-motion fallbacks—for wisps, sparks, embers, comet tails, plankton, or dust.

Interact with MCP servers directly from the command line, including listing, calling tools, managing authentication, and generating client code.

Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring.

Use when the user wants to negotiate a price, rate, compensation, contract, purchase, hotel, service, vendor deal, discount, upgrade, fee, renewal, refund, or other commercial terms; asks what to say to improve leverage or get a better deal; provides an offer/counteroffer and wants a response; or wants to maximize coupons, direct-booking value, bundles, competing configurations, or all-in economics. Do not trigger for ordinary writing, simple price lookup/comparison, arithmetic, generic persuasion, or conflict mediation without a concrete negotiated outcome.

Creates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, and reusable prompt templates with evals.

Launch, monitor, stop, and debug NeMo-RL recipes on a Kubernetes cluster using the nrl-k8s CLI, supporting ephemeral and long-lived RayCluster modes.

Enables decoupled pub/sub messaging between ViewModels using CommunityToolkit.Mvvm Messenger, covering weak/strong references, request/reply patterns, channel tokens, and lifecycle management.

Diagnoses Qdrant production issues using metrics and observability tools, covering optimizer problems, memory spikes, and slow queries.

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), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

Guides setting up and using Atheris for coverage-guided fuzzing of Python code and C extensions, including Docker setup, harness writing, and corpus management.

Build, refactor, or review macOS menubar apps that use Tuist and SwiftUI, with a focus on Tuist-first workflows, strict architecture boundaries, and reliable local launch scripts.

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), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

Mock Service Worker API mocking, request handlers, and integration testing.