Skill UI

This skill provides comprehensive methods to significantly reduce expenditure when using the Ideogram API for image generation. Techniques include implementing two-phase generation workflows (drafting with cheap models, finalizing with premium models), batching multiple images in a single API call, caching identical prompts, and setting up robust budget tracking alerts. Ideal for developers managing large-scale creative AI projects.

A comprehensive guide for configuring API access across development, staging, and production environments. This setup ensures strict isolation of API keys and environment-specific parameters (like models, speed, and caching). It covers best practices for secret management using major CI/CD and secret services (GitHub Actions, AWS Secrets Manager, GCP Secret Manager).

This guide outlines the process of migrating codebase dependencies and logic when upgrading the Ideogram API from legacy versions (V1/V2) to the robust V3 endpoints. It addresses critical breaking changes, including the shift from JSON body to multipart/form-data, changes in model naming, aspect ratio syntax, and the integration of new V3 features like rendering speed and style presets. Provides structured code adapters for smooth transition.

This skill enables the extension of existing video content using the Kling AI continuation model. By providing the task ID of a completed video and a descriptive prompt, it generates a seamless, continuous segment. This is ideal for content creators who need to build longer, multi-part narratives, expand short clips into full scenes, or generate complex, cohesive cinematic sequences by chaining multiple extensions.

Master the LangChain framework, the industry standard for building sophisticated and production-grade Large Language Model (LLM) applications. This skill covers core concepts including autonomous agents, multi-step chains, memory management, Retrieval-Augmented Generation (RAG), and external tool integration, enabling the development of complex, stateful AI systems.

This module implements comprehensive Role-Based Access Control (RBAC) for multi-tenant LangChain applications. It provides granular permission models for controlling model access, tool execution, and chain invocation. Key features include multi-tenant data isolation in vector stores, enforcing usage quotas (token limits), and integrating middleware for robust security enforcement. Ideal for building secure, scalable, and compliant enterprise LLM systems.

This guide details best practices for configuring LangChain applications across development, staging, and production environments. It ensures strict environment isolation by managing separate API keys, model settings, and LangSmith project names. The setup utilizes Zod for robust validation and integrates secure secret management via GitHub Actions, AWS Secrets Manager, or GCP, guaranteeing reliable and secure deployments.

This guide provides comprehensive strategies for optimizing the execution speed, reliability, and cost efficiency of AI agents. Learn how to minimize latency, right-size models (e.g., Flash vs. Opus), consolidate multiple LLM steps into single prompts, and optimize workflow triggers. Ideal for use when agents are slow, consuming excessive credits, or producing inconsistent results.

Provides expert guidance for using llama-factory to fine-tune LLMs through its WebUI, covering QLoRA/LoRA quantized setups, multimodal models, and automation tips for developers exploring models like Llama, Qwen, or Gemma.

LLaVA is an open-source vision-language assistant pairing CLIP vision encoders with Vicuna/LLaMA models to power multimodal chatbots, multi-turn image Q&A, captioning, and instruction-following tasks.

This skill guides the design and implementation of a complete, production-grade Machine Learning pipeline. It employs a multi-agent orchestration workflow, systematically covering all stages of the ML lifecycle: data ingestion and quality assurance, feature engineering, model training, optimization, and robust deployment (MLOps). It ensures built-in reproducibility, monitoring, and scalability.

This skill guides the integration of Model Context Protocol (MCP) into Claude Code plugins. It enables plugins to securely connect to external services, APIs, databases, and file systems by exposing capabilities as structured tools. Supports multiple connection methods (stdio, SSE, HTTP, WebSocket) and handles complex authentication flows like OAuth and token-based access for robust tool access.