New skills

TRL provides post-training methods for aligning language models with human preferences.

Create powerful GitHub Actions workflows to automate testing, building, security scanning, and deployment processes directly from your GitHub repository.

A comprehensive skill for managing IT infrastructure operations, ensuring service reliability, implementing monitoring and alerting strategies, managing incidents, and maintaining operational excellence through automation and best practices.

Comprehensive assistance with llama-factory development, generated from official documentation.

Memory optimization improves application performance, stability, and reduces infrastructure costs. Efficient memory usage is critical for scalability.

Build scalable infrastructure as code with Terraform, managing AWS, Azure, GCP, and on-premise resources through declarative configuration, remote state, and automated provisioning.

Source provenance, compatibility, automated checks, and current evidence depth are available on the full page.

Implement industry-standard OAuth 2.0 and OpenID Connect authentication flows with JWT tokens, refresh tokens, and secure session management.

Source provenance, compatibility, automated checks, and current evidence depth are available on the full page.

Comprehensive guide for evaluating iOS, macOS, tvOS, watchOS, and visionOS app code against Apple's App Store Review Guidelines. This skill covers EVERY guideline point to identify potential rejection issues before submission.

Effective requirements gathering establishes a shared understanding of what will be built, preventing misalignment and expensive changes later in the project.

SymPy is a Python library for symbolic mathematics that enables exact computation using mathematical symbols rather than numerical approximations. This skill provides comprehensive guidance for performing symbolic algebra, calculus, linear algebra, equation solving, physics calculations, and code generation using...

nanoGPT is a simplified GPT implementation designed for learning and experimentation.

Master containerizing and deploying Node.js applications with Docker for consistent, portable deployments.

Comprehensive guide to using Meta AI's Segment Anything Model for zero-shot image segmentation.

Root cause analysis (RCA) identifies underlying reasons for failures, enabling permanent solutions rather than temporary fixes.

Systematically identify, measure, and manage technical debt to make informed decisions about code quality investments.

Accurate project estimation determines realistic timelines, budgets, and resource allocation. Effective estimation combines historical data, expert judgment, and structured techniques to minimize surprises.

Manage existing Railway deployments: list, view logs, redeploy, or remove.

Source provenance, compatibility, automated checks, and current evidence depth are available on the full page.

High-performance serving framework for LLMs and VLMs with RadixAttention for automatic prefix caching.

Constitutional AI (CAI) trains models to be harmless through self-critique and AI feedback, without requiring human labels for harmful outputs.

NetworkX is a Python package for creating, manipulating, and analyzing complex networks and graphs. Use this skill when working with network or graph data structures, including social networks, biological networks, transportation systems, citation networks, knowledge graphs, or any system involving relationships...

Comprehensive guide to running ML workloads across clouds with automatic cost optimization using SkyPilot.