Skill UI

Automates SOC2 audit preparation by invoking the soc2-audit-helper plugin to gather evidence, assess controls, and flag compliance gaps, streamlining readiness reporting and remediation planning.

Builds AutoML pipelines by analyzing user requests, generating code for data preparation, model selection, hyperparameter tuning, validation, and metrics, then documenting artifacts for streamlined automated machine learning workflows.

Automates cross validation setup for ML training requests, offering best-practice guidance, production-ready code samples, and validation steps across data preparation, model tuning, and experiment tracking.

A comprehensive guide for diagnosing and fixing common Deepgram API errors. Covers HTTP error codes, WebSocket issues, optimal audio preparation using ffmpeg, and implementing robust retry patterns for reliable Speech-to-Text integration.

Automatically activates when you mention feature engineering helper, offering guidance on data preparation, model training, hyperparameter tuning, and experiment tracking for ML projects.

This skill orchestrates a comprehensive, multi-stage Git development workflow, simulating the process from code commit to PR preparation. It leverages specialized AI agents (code reviewers, test automators, prompt engineers) to systematically enforce best practices. Key functions include code quality assessment, breaking change analysis, running unit/integration/E2E tests, and generating Conventional Commit messages, ensuring code readiness and high quality before merging.

This expert tool orchestrates the complete onboarding experience for new team members in technical or remote-first organizations. It provides a structured roadmap covering pre-arrival preparation (access setup, documentation), Day 1 orientation, technical stack immersion (CI/CD, codebases), and cultural integration (buddy system). Use this when you need a comprehensive, step-by-step guide to rapidly transition new hires into productive, integrated team members.

This specialized, end-to-end workflow guides the deployment of applications onto Kubernetes clusters. It systematically covers all critical production phases, including Docker container preparation, generating K8s manifests, structuring applications with Helm charts, configuring advanced service meshes (like Istio), enforcing robust security policies (RBAC, NetworkPolicy), and implementing full observability and GitOps pipelines for reliable, scalable deployments.

nanoGPT is a simplified, minimalist implementation designed specifically for educational purposes. It reproduces the core architecture of GPT-2 (124M) using clean, hackable code, allowing users to understand the entire transformer pipeline from scratch. The framework supports full workflows, including data preparation on various datasets (e.g., Shakespeare, OpenWebText), model training, and text generation, making it ideal for students and researchers learning NLP and deep learning principles.

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

Auto-activating skill that guides tensorflow model trainer workflows, covering data preparation, model training, hyperparameter tuning, and experiment tracking with production-ready code and standards validation.

Transforms LaTeX or PDF papers into interactive websites, narrated videos, and print-ready posters via the Paper2All pipeline, ideal for conference preparation, research promotion, and explorable academic showcases.