Skill UI

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.

This utility is designed to build reusable, composable command-line scripts for interacting with the Hugging Face API and the `hf` command line tool. It enables complex data workflows by supporting chaining, piping, and intermediate processing across models, datasets, and repositories, streamlining the automation of Hub tasks.

MolyKit is a comprehensive toolkit designed for building robust, cross-platform AI chat applications. It provides core utilities for integrating large language models (LLMs) like OpenAI, handling real-time SSE streaming responses, and managing complex cross-platform asynchronous patterns (PlatformSend, spawn()). The kit includes ready-to-use widgets for messages, prompt inputs, and avatars, making it ideal for developers creating sophisticated, multilingual chat experiences.

Guides writing and running Odoo TransactionCase, HttpCase, and browser-tour tests, covering setup, tagging, and CLI commands so you can add CI-friendly automation for models and controllers.

Guides building custom Odoo modules by scaffolding manifests, models, views, and security rules, reviewing existing code, and applying ORM best practices across Community and Enterprise editions.

A comprehensive utility for handling asset loading within Three.js environments. It supports various formats, including GLTF/GLB models, textures, HDR environments, and complex image assets. Features include robust asynchronous loading patterns, progress tracking via LoadingManager, and detailed configuration for PBR materials and environment mapping.

A set of behavioral guidelines derived from Andrej Karpathy's observations to help users writing, reviewing, or refactoring code with Large Language Models (LLMs). It guides developers to avoid overcomplication, make surgical changes, explicitly surface assumptions, and define verifiable success criteria, promoting clean, simple, and robust code development.

A comprehensive technical module covering foundational deep learning principles and cutting-edge computer vision architectures, drawing from Yann LeCun's research. Topics include CNN fundamentals, backpropagation theory, and advanced self-supervised learning (SSL) models such as SimCLR, MAE, and the modern Joint Embedding Predictive Architecture (JEPA). Provides detailed theoretical explanations and complete PyTorch code for implementation.

This skill provides methods for reliably extracting typed, validated, and structured data from Large Language Models (LLMs), moving beyond simple text parsing. It covers best practices across major APIs (OpenAI's response_format, Anthropic's tool_use, Google's responseSchema) and local models. Key workflows include defining schemas (Pydantic/Zod), implementing constrained decoding, and building robust retry loops for production-grade data pipelines.

A comprehensive strategy for regression testing in AI-assisted development. It focuses on identifying systematic blind spots, such as schema inconsistencies between sandbox and production paths, and integrating automated bug checks into the development workflow. This guide teaches how to build robust, database-free API tests to ensure code quality when AI models contribute to the codebase.

Detects Modbus/TCP and RTU anomalies in OT environments using Zeek, Suricata OT rules, and Python-based Markov models to validate function codes, register ranges, timing, and client authorization during passive monitoring.

Executes a structured VC valuation workflow that ingests SaaS or startup metrics, runs DCF, comparable revenue multiples, and SaaS health models via Python, and synthesizes a defensible valuation, runway, and capital-efficiency narrative for users planning fundraising or benchmarking.