Skill UI

A comprehensive guide to configuring and maximizing the potential of Claude Code, an advanced agentic coding tool. This resource details best practices, setup templates (CLAUDE.md), advanced prompting techniques (e.g., thinking keywords), and debugging strategies for building reliable, complex software autonomously.

SGLang is a high-performance serving framework for LLMs and VLMs that uses RadixAttention prefix caching to deliver structured outputs (JSON/regex/grammar) and agentic workflows with function calls, providing up to 5× faster inference than vLLM across multi-GPU production deployments.

This skill provides detailed guidance on authoring effective `specs.md` files for autonomous development workflows. It teaches users how to clearly define sprint goals, establish explicit scope boundaries (In/Out of Scope), and configure rigorous testing requirements (QA, UI Testing). This ensures that agentic development remains focused and prevents scope creep.

torchforge is Meta's advanced PyTorch-native library designed for agentic Reinforcement Learning (RL). It fundamentally separates core RL algorithms from complex distributed infrastructure concerns. This allows researchers to rapidly prototype and experiment with novel RL methods (like GRPO) using clean, PyTorch-native abstractions, while automatically handling large-scale tasks like distributed training across thousands of GPUs using Monarch and TorchTitan.

A powerful agentic workflow for complex software development. Cascade Write mode acts as an autonomous coding agent, allowing users to build features, refactor code across multiple files, run terminal commands, and debug errors—all from a single natural language prompt. Ideal for full-stack development, complex system building, and large-scale code refactoring.

This skill provides a comprehensive, hands-on introduction to Windsurf's core AI capabilities. Users will experience Supercomplete for advanced tab completions, Cascade for agentic chat and direct code modifications (Write mode), and Command for targeted inline code adjustments. It is ideal for developers starting with Windsurf or needing a quick overview of its powerful IDE integrations.

Audits GitHub Actions workflows that invoke AI coding agents to surface prompt injection and sandbox risks, tracing attacker-controlled inputs through env vars, reusable actions, and workflow references before deployment or code review.

Performs static security analysis on GitHub Actions workflows that incorporate AI coding agents (e.g., Claude, Gemini, OpenAI). This skill helps identify critical data flow vulnerabilities, such as where attacker-controlled input can reach AI agent prompts or internal systems via CI/CD pipelines, going beyond simple expression checks.

This comprehensive guide outlines a rigorous, human-in-the-loop engineering workflow for leveraging advanced AI agents to complete complex implementation tasks. It mandates defining clear completion criteria, decomposing work into manageable units, and strategically routing models (Haiku, Sonnet, Opus) based on task complexity. The workflow emphasizes continuous evaluation, regression testing, security review of invariants and edge cases, and strict cost discipline to ensure robust and reliable software development using AI assistance.

A comprehensive expert for deploying and scaling AI agents using AWS Bedrock AgentCore. This guide covers the full lifecycle of agent management, including service selection (Gateway, Runtime, Memory, Identity, etc.), deployment patterns, credential management, and advanced integration workflows required for enterprise-scale AI solutions.

A comprehensive domain orchestrator designed to manage the entire project delivery lifecycle. It can route specific project management inquiries (e.g., Jira permissions, sprint velocity) to specialized sub-skills, or execute complex, goal-oriented workflows through a gated agentic loop. This process pulls live data from Jira/Atlassian, runs deterministic analytics, and verifies every step to ensure auditability and successful closure.

Provides patterns and techniques for building robust evaluation loops for AI agents. This skill guides the implementation of self-critique, evaluator-optimizer pipelines, and test-driven refinement workflows. Use it to significantly enhance the accuracy and quality of complex outputs like code, reports, and analyses by implementing structured, iterative improvement cycles (Generate → Evaluate → Critique → Refine).