Use when deciding which misq-* sub-skill to invoke next, or when sequencing manuscript work from topic selection through revision for a MIS Quarterly (MISQ) manuscript.
Use when after feature extraction and quality control filtering (blank masking, sample dropping, normalization) have been applied, but before statistical analysis or machine…
Use Mission Control with NVIDIA AI-Q, NVIDIA Dynamo, and GPU diagnostics for deeper research and GPU-backed coding workflows.
Mission Reunite SAR platform API. Read cases, post intel enrichments, analyze spatial patterns. Experimental branch at shadowhound-case-api-experimental.up.railway.app.
Board Paper und Business Judgment: Erstellt Entscheidungsunterlagen für Vorstand/Geschäftsführung/Aufsichtsrat mit Informationsgrundlage, Alternativen, Risiken und KI-Ein — from…
Research YouTube videos by topic/keyword — filter by views, subscriber count, and breakout ratio (views/subs).
Evidence-driven ML repository verification skill. Treats every Claude Code claim as a hypothesis to test, not a statement to trust.
ML conference paper formatting for NeurIPS, ICML, ICLR, and AAAI — official style-file usage, anonymization and camera-ready toggles, page-limit accounting, natbib citations,…
Detects and prevents data leakage in machine learning and mathematical modeling. Use after ML tasks involving data cleaning, feature engineering, data augmentation, algorithm…
Auto-evolving ML competition agent. Learns from each experiment, accumulates HCC multi-layer memory, and continuously improves LB scores.
Use when starting, logging, or reviewing ML experiments — maintains a persistent experiment journal with hypotheses, results, and learnings across sessions
Use when designing ML experiments, choosing evaluation metrics, tracking experiments, tuning hyperparameters, debugging training, ensuring reproducibility, or building ML…
Suivi d'expériences ML avec MLflow, W&B, versioning de modèles et comparaison de métriques — from science/science-misc
Plan reproducible ML experiment runs with explicit parameters, metrics, and artifacts. Use before model training to standardize tracking-ready experiment definitions.
Make ML experiments reproducible and comparable by tracking hyperparameters, metrics, artifacts, and environments.
POC validation patterns to catch issues before committing to long-running ML experiments. TRIGGERS - fail-fast, POC validation, preflight check, experiment validation, schema…
Mentor for machine-learning work in Triptych — wires data exploration, seed control, overfit-1-batch, W&B (External), /autoresearch, and show_progress into the canonical order,…
Use when the user asks to fine-tune, train, evaluate, audit, or ship a machine-learning model on the Hugging Face ecosystem — SFT, DPO, GRPO, RLHF, LoRA/QLoRA, post-training,…
Use when the user is stuck, needs ranked next steps, or wants alternatives after initial experiments — "I tried X and got Y, what next?
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, o — from…
Designs and implements production-grade ML pipeline infrastructure: configures experiment tracking with MLflow or Weights & Biases, creates Kubeflow or Airflow DAGs for t — from…
Automate ML workflows with Airflow, Kubeflow, MLflow. Use for reproducible pipelines, retraining schedules, MLOps, or encountering task failures, dependency errors, experiment…
Designs and implements production-grade ML pipeline infrastructure: configures experiment tracking with MLflow or Weights & Biases, creates Kubeflow or Airflow DAGs for t — from…
Use when the user wants to understand an ML/AI topic, compare approaches, or survey framework capabilities — "how does X work?", "compare X vs Y
ML research for RAN with reinforcement learning, causal inference, and cognitive consciousness integration.
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics.
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics.
Run final-scoring pass on an MLE-bench experiment. Inferences the trained model on the held-out test/ directory (the only skill allowed to read test/), produces submission.csv in…
Scaffold an MLE-bench task into the active project. Resolves the task's prepared data from the local MLE-bench cache, creates a dated experiment folder with train/ and test/…
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform — from…
MLflow integration skill for experiment tracking, model registry, and artifact management. Enables LLMs to log experiments, compare runs, manage model lifecycle, and retrieve…
Build and manage end-to-end MLOps pipelines using MLflow for experiment tracking, model registry, artifact logging, autologging, model evaluation, and deployment serving.
Onboards users to MLflow by determining their use case (GenAI agents/apps or traditional ML/deep learning) and guiding them through relevant quickstart tutorials and initial…
ML experiment tracking, model registry, and deployment with MLflow for reproducible machine learning workflows.
Prepare, validate, and submit UMA/fairchem machine-learning interatomic potential calculations on Genkai with the established PJM launcher and UMA virtual environment.
Build comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tools. — from stanfish06/my-skills
Build comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tools. — from majiayu000/claude-skill-registry
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform — from…
MLOps lifecycle patterns — experiment tracking (MLflow/W&B), model registry, FastAPI serving with canary deployments, drift detection, fine-tuning workflows, retraining pipelines,…
MLOps pipeline design workflow for orchestrating training, validation, packaging, and promotion with explicit gates.
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualizatio — from…
Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLO — from…
Comprehensive MLOps workflows for the complete ML lifecycle - experiment tracking, model registry, deployment patterns, monitoring, A/B testing, and production best practices with…
Use when preparing an accepted MLSys paper for publication on proceedings.mlsys.org, covering de-anonymization of the research-track PDF, restoring company and repository…
Use when designing or auditing the evaluation of an MLSys paper, selecting representative workloads and hardware, tuning baselines symmetrically, reporting throughput, latency…
Use when auditing an MLSys submission for OpenReview readiness, covering the two-column 10-page body excluding references, the separate appendix upload, double-blind rules that…
Use when deciding whether a project belongs at MLSys rather than OSDI, SOSP, NSDI, ASPLOS, ATC, EuroSys, or the ML conferences, testing for genuine ML-systems co-design, choosing…
Use when revising an MLSys paper's prose and structure, building the measured-bottleneck opening, naming the mechanism instead of listing optimizations, writing evaluation…
Použij pro MLŽIDLA.cz při tvorbě prezentací, webových sekcí, vizualizací, videí, obchodních argumentů a marketingových materiálů zaměřených na městské ochlazování, mlžné zóny,…
Compose a ready-to-copy prompt for the user's OTHER Claude Code instance (running in PowerShell). Use when the user asks to "напиши промпт для powershell", "сгенерируй задание для…
Stage 3.5 of the mathematical modeling pipeline. Performs global quality review of all task outputs using an independent subagent with percent-based scoring.
Derive requirements and create a phased execution plan. Use after discussion or research to crystallize what we know into actionable work.
Investigate unknowns identified during discussion. Selects research strategies based on discussion context, runs parallel subagents, and produces RESEARCH.md with a summary and…
Production-grade data science specialist with TensorFlow 2.20.0, PyTorch 2.9.0, Scikit-learn 1.7.2 expertise.
Enterprise Machine Learning specialist with TensorFlow 2.20.0, PyTorch 2.9.0, Scikit-learn 1.7.2 expertise.
Market and ecosystem research specialist for /moai brain Phase 3. Executes parallel WebSearch + Context7 queries, handles tool failures gracefully, and produces structured…
Loads human-authored design briefs from .moai/design/ (research, system, spec, pencil-plan) and injects them into /moai design workflow context with priority truncation when token…
Self-research workflow for optimizing moai-adk components through binary eval experimentation loops. Adapted from autoresearch pattern with 5-layer safety architecture.
Use when designing or auditing the evaluation of a MobiCom submission — building real-device testbeds, choosing RF and channel measurement methodology, injecting realistic…
Use when planning a MobiCom campaign across the rolling two-deadlines-per-year calendar — deciding which round to target and which edition it feeds, building a backward schedule…