Deep Learning

Follow development best practices including consistent project structure, clear documentation with README files, version control best practices with clear commit messages, environment configuration using environment variables, minimal dependency management, code review processes, testing requirements, feature flags for incomplete features, and changelog maintenance. Use this skill when organizing project files and directories, writing commit messages, managing dependencies, setting up environment configurations, establishing code review processes, or maintaining project documentation. This skill applies when working on project organization, git workflows, dependency management, or any project-level conventions.

This skill should be used when TODO: specify the domain knowledge or organization context this skill provides and when it should be invoked.

Explains the standardized API organization pattern for this codebase. Use when creating new API endpoints, API clients, or modifying existing API structure. Covers the 5-file system (endpoint-types, endpoints, api-client, admin-api-client, protected-endpoints), role-based access patterns (admin vs regular users), and TypeScript type safety across the API layer. All API code lives in src/lib/api/ following this exact pattern.

This skill should be used when working with reinforcement learning tasks including high-performance RL training, custom environment development, vectorized parallel simulation, multi-agent systems, or integration with existing RL environments (Gymnasium, PettingZoo, Atari, Procgen, etc.). Use this skill for implementing PPO training, creating PufferEnv environments, optimizing RL performance, or developing policies with CNNs/LSTMs.

Save Q&A conversations to Obsidian notes with proper formatting, metadata, and organization. Use this skill when the user explicitly requests to save a conversation, question-answer exchange, or explanation to their Obsidian vault. Automatically formats content as document-style notes with timestamps, tags, and project links.

Computer vision library for PyTorch featuring pretrained models, advanced image transforms (v2), and utilities for handling complex data types like bounding boxes and masks. (torchvision, transforms, tvtensor, resnet, cutmix, mixup, pretrained models, vision transforms)

Panduan senior/lead developer 20 tahun pengalaman untuk Vue.js 3 + Nuxt 3 + TanStack Query development. Gunakan skill ini ketika: (1) Membuat project Nuxt 3 baru dengan arsitektur production-ready, (2) Integrasi TanStack Query untuk data fetching, (3) Debugging Vue/Nuxt yang kompleks, (4) Review code untuk clean code compliance, (5) Optimisasi performa aplikasi Vue/Nuxt, (6) Setup folder structure yang scalable, (7) Mencari library terpercaya untuk Vue ecosystem, (8) Menghindari common pitfalls dan bugs, (9) Implementasi state management patterns, (10) Security hardening aplikasi Nuxt.Trigger keywords: vue, vuejs, nuxt, nuxtjs, tanstack, vue-query, composition api, pinia, vueuse, vue router, clean code vue, debugging vue, folder structure nuxt.

Use when changes affect component organization, technology stack, or cross-container communication - triggered by new components, pattern changes, or needing to map external interfaces to internal components

Generate detailed research budgets and project timelines for grants, proposals,evaluations, and consulting. Provides NIH/NSF-compliant budgets, multi-tier scenarios,and Gantt-style timelines with UNC-specific rates.USE WHEN user says "create budget", "generate timeline", "project budget","research budget", "grant budget", "proposal budget", "cost estimate","work plan", "Gantt chart", or requests budget/timeline planning.

Create psychologically compelling, accessibility-grounded frontend interfaces using avant-garde design concepts not yet mainstream in 2025. Integrates shadcn registries, experimental layout systems beyond traditional grids, and design patterns that elicit visceral "WOW" responses. Use when building React/Next.js components, landing pages, dashboards, or any interface requiring distinctive visual identity with biomorphic aesthetics, kinetic typography, soft tactile UI, or computational organic forms. Triggers on requests for unique design systems, custom shadcn themes, registry integration, or when users want interfaces that feel genuinely designed rather than templated.

Core PyTorch fundamentals including tensor operations, autograd, nn.Module architecture, and training loop orchestration. Covers optimizations like pin_memory and lazy module initialization. (pytorch, tensor, autograd, nn.Module, optimizer, training loop, state_dict, pin_memory, lazylinear, requires_grad)

Format recipes using Cooklang markup syntax. Use when creating, editing, or converting recipes to Cooklang format. Covers ingredients, equipment, timers, metadata, and file organization.

Manage Obsidian knowledge base - capture ideas, YouTube videos, articles, repositories, create study guides, and publish to GitHub Pages. Use smart AI tagging for automatic organization.

Documentation organization and maintenance system with automated indexing, content deduplication, cross-reference management, and navigation file generation for scalable documentation systems

Project-specific code patterns for Server Actions, data fetching, error handling, file organization. Use when implementing features to follow established patterns, or when user asks about project conventions/patterns/architecture.

Create, update, and maintain clear, accurate, and well-organized technical documentation for complex codebases. This agent focuses on understanding the current state of the code and existing documentation before proposing or making changes, ensuring documentation remains up to date, discoverable, and trustworthy for developers.

Library for Graph Neural Networks (GNNs). Covers MessagePassing layers, modular aggregation schemes, and handling large graphs via mini-batching with disjoint graph representation. (pyg, messagepassing, gnn, gcn, gat, edge_index, knn_graph, global_mean_pool)

Enforces documentation standards and structure for this project. This skill should be used when creating, updating, or organizing documentation to ensure compliance with project rules, prevent redundancy, and maintain screen-based organization. Activates when user asks to create/update docs or when documentation needs to be generated.

Expert guidance for creating syntactically correct and well-structured Mermaid diagrams following best practices. Use when creating flowcharts, sequence diagrams, class diagrams, state diagrams, Gantt charts, ER diagrams, data lineage visualizations, or any other Mermaid visualization.

⚡ PRIMARY TOOL for: 'what's the architecture', 'system design', 'how are layers organized', 'find design patterns', 'audit structure', 'map dependencies'. Uses claudemem v0.3.0 AST structural analysis with PageRank. GREP/FIND/GLOB ARE FORBIDDEN.