AI/ML

Provides a Python wrapper for Google's Gemini CLI, enabling Claude to execute Gemini models for code analysis and generation tasks. Offers multiple execution methods with clear timeout controls and environment variable configuration.

This skill provides direct access to Google's Gemini Pro image generation API from within Claude. It handles text-to-image creation, image editing, style transfers, and multi-turn refinement. The documentation is thorough, covering common pitfalls like JPEG format handling and offering practical examples for different use cases like logos and product mockups.

Provides vector database functionality for semantic search with AgentDB integration. Includes CLI tools for database management, TypeScript API for programmatic use, and MCP server for Claude Code. Supports multiple quantization methods and distance metrics for performance optimization.

This skill integrates ReasoningBank adaptive learning with AgentDB's high-performance vector database for building self-improving AI agents. It provides trajectory tracking, verdict judgment, memory distillation, and pattern recognition with 150x faster retrieval speeds. Includes CLI tools, TypeScript API, and backward compatibility with legacy systems.

A Claude Skill that helps design progressive learning sequences by breaking complex concepts into manageable steps. It uses Bloom's taxonomy and CEFR levels to manage cognitive load, includes validation checkpoints, and integrates AI collaboration at appropriate stages. The skill provides a structured framework for instructional designers and educators.

Provides a structured workflow for Bayesian modeling with PyMC, covering data prep, model building, prior/posterior checks, MCMC diagnostics, and variational inference. Includes practical code examples for common tasks like hierarchical models and model comparison.

A powerful AI-powered video editing tool that automates the removal of filler words and pauses from videos using speech transcription and intelligent analysis.

A CLI tool that bundles multiple Z.AI capabilities including image/video analysis with GLM-4.6V, real-time web search with filtering, web page extraction to markdown, and GitHub code exploration. It provides a unified interface for developers needing visual content analysis, research, or code investigation tasks.

This skill provides access to Hugging Face Transformers library for loading pre-trained models, performing inference, and fine-tuning across NLP, vision, and audio tasks. It includes practical code examples for pipelines, model loading, text generation, and training workflows with clear installation and authentication guidance.

This skill helps diagnose and fix context degradation in AI agents. It identifies patterns like lost-in-middle effects and context poisoning, provides monitoring tools, and suggests recovery strategies for long-running conversations.

Provides a structured framework for designing AI-integrated learning experiences using the Three Roles model. Offers concrete templates, balance guidelines, and verification mechanisms to ensure students learn foundational skills while effectively collaborating with AI tools.

Provides memory management patterns for AI agents using AgentDB's persistent storage. Offers session memory, long-term storage, pattern learning, and context management. Includes CLI tools, API examples, and integration with reasoning agents. Supports multiple learning algorithms and performance optimization.