Skill UI

This comprehensive checklist guides the operational setup (MLOps) for AI applications using Together AI's OpenAI-compatible API. It covers critical production concerns, including secure API key management, implementing robust rate limit handling, building error resilience features (circuit breakers, exponential backoff), and setting up comprehensive monitoring for latency, cost control, and model availability. Essential for reliable, scalable LLM deployment.

A comprehensive reference architecture for building scalable, cost-effective, and robust AI services. This system manages the full AI lifecycle, including intelligent model routing (for quality/cost trade-offs), response caching (using Redis), asynchronous batch processing, and fine-tuning pipeline management via Together AI's OpenAI-compatible API. Ideal for enterprise applications requiring high availability across multiple open-source models.

A comprehensive guide to implementing production-ready patterns for interacting with the Together AI API. This includes a singleton client for seamless OpenAI-compatible integration, robust error wrappers with retry logic, and a fluent request builder. It covers best practices for LLM inference, model setup, and handling diverse response types (chat, embedding, fine-tuning).

This guide provides comprehensive strategies for migrating applications using the Together AI platform. It addresses common issues like model ID deprecations, API schema changes (for fine-tuning or chat completions), and best practices for robust inference and deployment using their OpenAI-compatible API.

NVIDIA garak is an open-source LLM vulnerability scanner designed for comprehensive red-teaming and security assessment. It systematically probes large language models (via OpenAI-compatible APIs, Hugging Face, etc.) using thousands of adversarial prompts. It covers critical vulnerabilities such as prompt injection, jailbreaking, data leakage, and toxicity. Use this tool to establish a repeatable security baseline before or after deployment, validate the effectiveness of safety guardrails, or generate quantitative evidence for AI risk assessments.

A comprehensive guide and skill for deploying large language models (LLMs) locally using the llama.cpp framework and GGUF quantization format. It covers searching the Hugging Face Hub, selecting optimal quantizations (e.g., Q4_K_M), running local servers, and achieving OpenAI-compatible API endpoints. Supports various hardware backends including CPU, Mac Metal, CUDA, and ROCm. Ideal for developers needing offline, private LLM inference.

The Neon AI Gateway provides a single API endpoint and one credential to access a diverse catalog of frontier and open-source LLMs (including OpenAI, Anthropic, Google Gemini, Meta, Alibaba, and DeepSeek). This unified layer simplifies integration by eliminating the need for separate provider accounts and managing model-specific SDK complexities. It allows developers to switch between models seamlessly by changing only the model name, while also providing crucial branch-scoped isolation for development and CI environments.

A powerful plugin enabling Claude Code to delegate complex tasks to external AI CLIs (such as OpenAI Codex or Google Antigravity/Gemini) without exiting the conversation. It supports multi-model workflows, allowing users to seek a second opinion, cross-check deep analysis, or delegate side tasks (like research or code review). The core value is that Claude synthesizes the raw outputs, providing a critical review and reconciliation of findings across all consulted models.

RouterBase acts as a unified, OpenAI-compatible API gateway, allowing applications to route requests across diverse large language models (LLMs) like GPT, Claude, and Gemini. It helps developers migrate existing OpenAI SDK calls, implement sophisticated primary/fallback model selection based on cost, latency, and quality, and manage multimodal payloads (image, audio, video) from a single, standardized endpoint.

Delegates coding, code review, and plan review tasks to OpenAI Codex CLI with sandbox controls and security boundaries. Supports autonomous execution, multiple modes, and safe review handling.

A powerful skill for generating brand-new images or performing professional edits on existing photos using the OpenAI GPT Image API. Users can provide detailed prompts, specify desired aspect ratios (e.g., 1024x1536), select background types, and control output quality. Ideal for creative projects, logo design, concept art, and advanced photo manipulation.

Queries the AIHOT (aihot.news) service to fetch the latest Chinese AI news and trends. Provides real-time updates on AI events, model releases, product launches, and industry headlines. Ideal for users asking about today's AI happenings, daily AI briefings, hot topics, or specific AI subjects like OpenAI, Anthropic, or Google. No API key required, read-only access.