This skill should be used when the user asks to "generate video with LTX-2", "create video from text", "animate an image", "use GAMMA for video generation", or needs local AI video generation on the GAMMA GPU server. Covers text-to-video, image-to-video, and auto-cataloging workflows with the LTX-2 19B model.
Generate and edit images using Google Gemini's Nano Banana image generation API via undyapi.com proxy. Use when users want to generate images from text descriptions, edit existing images with AI, or create visual content. Supports aspect ratio and quality control.
Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.
Build a complete data clustering and visualization pipeline from any data source. Use when the user wants to analyze patterns in text data (GitHub issues, Slack messages, support tickets, code reviews, forum posts, customer feedback, etc.), cluster similar items, or build an interactive visualization to explore the patterns. Triggers on: "cluster", "analyze patterns", "group similar", "clio-style", "pattern analysis", "visualize clusters", "find themes", "topic modeling", "semantic clustering".
Use when creating new skills or editing existing skills - combines official skill authoring best practices with TDD methodology (test with subagents before deployment, iterate until bulletproof). Activates when user wants to create/update a skill that extends Claude's capabilities.
Manage Gemini RAG stores with Code-RAG support
Used to create a new agent. Used when a user wants to create a new agent
Checklist สำหรับตรวจสอบและกำจัด bloat ใน context, prompt, และ response เพื่อลด token cost และเพิ่ม signal-to-noise ratio
Bootstrap skill that teaches Claude about the shared Agent-memory system for cross-session and cross-team knowledge
Guide implementation of production-ready Python RAG components by enforcing correct abstractions, error handling, observability, and safety at coding time.
Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need to summarize conversation history, or when optimizing tokens-per-task rather than tokens-per-request.
This skill should be used when the user asks to "demonstrate minimal skill", "show basic skill structure", or needs a simple skill example. Provides a minimal working skill template.
Develop pre-fluency cognitive habits: recognize when not to use AI, separate thinking from generation, resist automation bias and output authority.
Use when creating new agents, defining agent roles, or configuring agent handoff protocols and model selection.
Compare and evaluate embedding models for semantic search
This skill should be used when users want to restore, reload, or copy their Claude Code configuration files (commands, skills, agents) from a backup directory back to ~/.claude/. Triggered by phrases like "restore my claude config", "reload claude settings", "copy config back to ~/.claude/", "restore from backup", "recover claude configuration", "import commands and skills from backup", "I accidentally deleted my commands", "restore my old skills", "copy config from backup", or "I need to recover my claude settings from a backup".
Build custom Model Context Protocol servers to extend Claude's capabilities
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Test Bob The Skull with virtual audio injection instead of speaking. Use when testing wake word detection, STT accuracy, full conversation pipeline, or automated testing. Covers setup, configuration, injection methods, and troubleshooting.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. 사용 시기: (1) MCP 서버 구축 시 (2) 외부 API를 MCP로 통합 시 (3) "MCP", "Model Context Protocol" 키워드 사용 시 (project)
Use when implementing on-device AI with Apple's Foundation Models framework (iOS 26+), building summarization/extraction/classification features, or using @Generable for type-safe structured output.
