Deep Learning

Crear diagramas Mermaid compatibles con Obsidian (flowchart, sequence, gantt). Evita errores comunes y produce diagramas simples y mantenibles.

Documentation organization, maintenance, and cleanup.USE WHEN: organizing docs, cleaning project root, updating documentation,checking for redundancy, maintaining docs structure.NOT FOR: technical implementation (use relevant technical skill).Examples:<example>Context: User added documentation to wrong location.user: "I added a new API doc file to the root directory"assistant: "I'll use docs-keeper to organize it in the proper docs/ location."<commentary>File organization is docs-keeper responsibility.</commentary></example><example>Context: User needs to update docs after code changes.user: "I modified the auth system and need to update the docs"assistant: "I'll use docs-keeper to update the authentication documentation."<commentary>Documentation updates are docs-keeper responsibility.</commentary></example>

Automatically maintain repository cleanliness and organization by scanning for misplaced files, organizing loose scripts, and ensuring professional folder structure

Git worktree patterns, best practices, templates, and quick reference. Use when user asks about "worktree best practices", "worktree patterns", "git worktree help", "worktree template", "worktree mode semantics", "what are worktree modes", "explain worktree metadata", or needs guidance on worktree organization and workflows.

Ensure proper code organization with class names, directories, namespaces, and naming consistency following the principle "Directory X contains ONLY class type X (project)

Create powerful presentations using Steve Jobs's 3-Second Rule methodology. Applies the Billboard Test principles for minimal cognitive load, maximum visual impact, and elegant slide design. Use when creating product launches, pitches, explanations, or any live presentation that requires high audience retention and visual clarity. Automatically integrates with Claude's PPTX skill to generate professional PowerPoint files and always applies the Sentient Brand Guidelines skill to ensure consistent branding.

Expert guidance for creating, updating, and maintaining CLAUDE.md memory files following best practices for hierarchical memory, structure, content organization, and team collaboration

Optimize PyTorch with torch.compile (TorchDynamo/Inductor), focusing on compile overhead, graph breaks, and benchmark methodology. Use when speeding up PyTorch models or debugging compile behavior; triggers: torch.compile, torchdynamo, inductor, graph break, pytorch optimization.

This skill should be used when setting up a production-ready dashboard shell with resizable sidebar, two-level navigation (Sections → Pages), mobile drawer, user menu with organization switcher, and localStorage persistence in a Next.js application. Use this skill when implementing a responsive dashboard layout with react-resizable-panels, shadcn/ui components, and server-first data fetching patterns.

Maintaining code quality and standards in StickerNest. Use when refactoring code, checking file sizes, splitting large files, reviewing code structure, or when files exceed length limits. Covers file length limits, refactoring patterns, code organization, and the "check existing code first" principle.

Design and implement end-to-end type-safe APIs using tRPC with proper router organization, procedure definitions, input validation with Zod schemas, context management, and middleware. Use this skill when creating or modifying tRPC router files like server/routers/*.ts, src/server/api/routers/*.ts, *.router.ts, or any files containing tRPC procedure definitions, queries, and mutations. Use this when defining tRPC routers with .query() for read operations and .mutation() for write operations, implementing input validation using Zod schemas with .input(z.object({...})) for type-safe runtime validation of all procedure parameters, creating and organizing reusable sub-routers by feature or domain (user router, post router, comment router) and composing them into a main app router using mergeRouters or router nesting, setting up tRPC context in createContext functions to provide request-scoped data like user sessions, database connections, or authentication state to all procedures, implementing tRPC middleware wit

Systematic approach for migrating patterns between directories in Storybook-based design systems while maintaining cross-references and documentation integrity. Use this skill when reorganizing Storybook structure, moving patterns to new categories, refactoring documentation hierarchy, or performing bulk pattern migrations that require careful tracking of Meta titles, URLs, and cross-references.

The digital librarian for Claude Code projects. Enforces structured document lifecycle management - organizing, indexing, and archiving project documentation automatically. Use when creating, organizing, or managing project documentation. Ensures documents are created in the proper `docs/` directory structure with required metadata, handles temporary documents in system temp directories, maintains an auto-generated index, and performs automatic archiving of old/complete documents. Use for any task involving document creation, organization, or maintenance.

Transformer architecture fundamentals. Covers self-attention mechanism,multi-head attention, feed-forward networks, layer normalization, andresidual connections. Essential concepts for understanding LLMs.

Handle complex-valued tensors in PyTorch for astronomical imaging applications. This skill should be used when working with Fourier transforms, phase/amplitude representations, and complex arithmetic in PRISM.

Add comprehensive type hints to Python functions and methods, including PyTorch tensor types. This skill should be used when improving code quality through static type checking or when preparing code for mypy validation.

Use when building SaaS applications needing data isolation between customers - implements owner-based filtering for secure multi-tenant document storage and search with workspace, organization, or tenant-level separation

TensorFlow, PyTorch, CNNs, RNNs, transformers, neural networks

Provides Things3 task management workflows, organization patterns, and productivity methodologies. Includes personal taxonomy integration, priority systems, and automation patterns for effective task management. MANDATORY: Claude must read this skill file before using any Things3 MCP tools (read_tasks, create_task, edit_task, migrate_inbox_to_notion).

Orchestrator AI-specific Git conventions and standards. Branch naming, commit workflow, repository organization. CRITICAL: Follow conventional branch names, use conventional commits, maintain clean git history.