Skill UI

NeMo Curator streams GPU-accelerated curation for LLM training, with super-fast fuzzy deduplication, multimodal quality filters, semantic dedupl, PII redaction, NSFW checks, and RAPIDS-scaled pipelines for prepping massive corpora.

Prepares structured meeting materials by pulling context from Notion, enriching it with Claude research, and publishing both an internal pre-read and an external agenda so every participant arrives informed.

This tool gathers comprehensive diagnostic evidence from an Obsidian vault. It collects details such as app versions, installed plugins, appearance settings, file statistics, and console errors into a structured markdown report. Use it when troubleshooting persistent issues or preparing detailed bug reports for developer support.

Auto-activating ML training skill that kicks in whenever you mention optuna study creator, then guides you through data prep, model training, hyperparameter tuning, and experiment tracking with production-ready code and validations.

Provides a comprehensive checklist for planning, scoping, executing, and wrapping up penetration tests, covering objectives, authorization, environment prep, scans, tester selection, methodologies, reporting, and remediation tracking.

This comprehensive checklist guides the deployment of Perplexity Sonar API integrations to a robust production environment. It covers critical aspects including API key management, robust code quality practices (retries, rate limiting), performance optimization (caching, streaming), detailed monitoring setup, and cost control strategies. Use this checklist when preparing for a major Perplexity feature launch or going live to production.

This skill builds and executes automated pipelines to clean, validate, and transform data for machine learning, covering ETL workflows, error handling, and quality reporting so Claude can deliver analysis-ready datasets.

Automates PyTorch training workflows by guiding data preparation, model configuration, hyperparameter tuning, and experiment tracking while following industry best practices for production readiness.

Ray Data offers scalable distributed data processing for ML workloads, streaming across CPU/GPU clusters and integrating with PyTorch, TensorFlow, and Ray Train. Use it for batch inference, ETL, and multi-modal preprocessing from a laptop up to hundreds of nodes.

Automatically collects comprehensive diagnostic information for Replit workspaces, deployments, and databases. This tool gathers system state, runtime versions, environment variables, network logs, and package details. It is essential for troubleshooting persistent issues or preparing detailed evidence for support tickets.

A comprehensive, step-by-step guide for deploying applications on Replit to production environments. It covers crucial best practices, including configuring deployment settings, managing environment secrets, implementing robust health checks, handling global errors, setting up custom domains, and defining rollback strategies. Essential for developers preparing an app for a live launch or scaling up.

Automates ROC curve plotting tasks in ML training, guiding data prep, model training, tuning, tracking, and code generation for production-ready results.