Deep Learning

Discover insights through non-linear, associative exploration where connections emerge naturally rather than through predetermined paths. Use when: (1) asked to trace unexpected connections between concepts from different domains, (2) system interconnections are so thorough that linear analysis misses key relationships, (3) information from diverse sources resists organizing into single hierarchy, (4) understanding emerges through following natural associations rather than planned structure.

Generate professionally formatted README.md files following a specific centered table-based structure. Use when creating or reformatting README files for GitHub repositories, particularly for Ghost's projects across 48hour-solutions, Automotive-9, LLMTooling, MCDxAI, Orbital-8, Parallel-7, and GhostTypes organizations. Triggers include "create a readme", "reformat this readme", "update the readme", or any request to document a repository.

This skill should be used when the user asks about testing Rails applications, Minitest, test-driven development (TDD), unit tests, integration tests, system tests, fixtures, factories, mocking, stubbing, test coverage, continuous integration, test organization, or Rails testing best practices. Also use when discussing testing philosophy, test speed, or debugging failing tests. Examples:

Reviews existing repository issues, code structure, and domain to create or refresh a semantic label system with appropriate colors aligned to the repository's specific context and needs. Use for initial setup or periodic maintenance (every 6-12 months) when users mention "labels", "label organization", "repository cleanup", "label system", or when detecting labeling inconsistencies.

Expert code review specialist for quality, security, and maintainability. Use when reviewing code changes, ensuring high development standards, or conducting security audits. Provides actionable feedback organized by priority.

Generate organizational hierarchy charts from CSV, JSON, or nested data. Supports multiple layouts, department coloring, and PNG/SVG/PDF export.

Write unit and integration tests following the project's testing patterns with Jest. Use this skill when creating test files (*.spec.ts), writing unit tests for DTOs and domain entities, writing integration tests for use cases and queries, setting up test fixtures, or using test utilities. This includes organizing tests in test/unit/ and test/integration/ directories, using proper test naming conventions, mocking external dependencies, and testing with real database transactions for integration tests. Apply when working with any *.spec.ts file, test fixtures, or implementing the project's test-behavior-not-implementation philosophy.

Generate URLs for the LimaCharlie web application interface. Quickly open the web UI for any feature: dashboard, sensors, detections, D&R rules, FP rules, secrets, outputs, lookups, payloads, YARA rules, artifacts, investigations, extensions, adapters, installation keys, billing, users, playbooks, AI agents, and more. For sensor-specific pages: timeline, console, processes, network, file-system, live-feed. For groups: members, organizations, permissions. Use for "open dashboard", "link to detections", "web UI for sensor", "open D&R rules page", "browser link", "app link", "open in web", "show me URL for", "go to".

Generate comprehensive sensor health and status reports across all LimaCharlie organizations. Use when users ask about sensor connectivity, data availability, offline sensors, sensors not reporting events, or fleet-wide health queries (e.g., "show me sensors online but not sending data", "list sensors offline for 7 days across all orgs").

Map unfamiliar codebases by identifying landmarks, boundaries, and flows to build a navigable mental model. Use when: (1) asked to explain code organization, architecture, or system structure, (2) multiple searches for individual files have been made without first examining directory structure, (3) changes or refactoring are proposed before analyzing what currently exists, (4) knowledge is limited to individual file contents rather than system-level organization.

Clean up and organize markdown files dumped at project root. Routes files to appropriate directories (memos/, docs/, devops/docs/) or deletes obsolete content. Follows project file organization guidelines from CLAUDE.md.

Creates breathtaking iOS/Mac and web apps with organic, non-AI aesthetic. Expert in SwiftUI, React animations, physics-based motion, and human-crafted design. Use for iOS/Mac app UI, React/Vue animations, native-feel web apps, physics-based motion design. Activate on "SwiftUI", "iOS app", "native app", "React animation", "motion design", "UIKit", "physics animation". NOT for backend logic, API design (use backend-architect), simple static sites (use web-design-expert), or pure graphic design (use design-system-creator).

Extract and structure data from documents about the illegal antiquities trade, including dealers, collectors, artifacts, locations, and relationships. Use when processing news reports, academic articles, legal documents, encyclopedia entries, or research materials pertaining to looted artifacts, antiquities trafficking, provenance research, or cultural heritage crimes. Returns structured JSON with entities (persons, organizations, artifacts, locations) and their relationships.

Write clean, efficient, maintainable code. Use when implementing features, writing functions, or creating new modules. Covers SOLID principles, error handling, and code organization.

Write correct, idiomatic Apple MLX code for Apple Silicon ML. Use when working with MLX arrays, neural networks, training loops, lazy evaluation, unified memory, mx.eval, mx.compile, Metal GPU, memory optimization, quantization, or Apple Silicon performance. Covers critical API differences from PyTorch/NumPy, array indexing gotchas (lists must be mx.array, slices create copies), NHWC format for Conv2d, __call__ not forward(), float64 CPU-only, mlx-lm integration, and debugging patterns.

Manage Todo operations (Create, Read, Update, Delete) using SQLModel and Postgres. Use when the user wants to organize tasks.

Generate Schema.org JSON-LD for Swiss/Spanish SEO (Person, JobPosting, CreativeWork, Organization)

Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre/post task hooks, session management, Git integration, memory coordination, and neural pattern training for enhanced development workflows.

[Utility] ⛔ MANDATORY skill for ANY Brain canvas operations. AI MUST invoke this skill BEFORE creating/modifying ANY files in Docs/Brain/. Failure to follow = broken canvas.

This skill should be used when the user asks about "Rails philosophy", "the Rails way", "Rails doctrine", "DHH's approach", "Rails conventions", "fat models skinny controllers", "majestic monolith", "service objects", or discusses architectural patterns and best practices for Rails applications. Load this skill when providing guidance on Rails architectural decisions, code organization, or when determining whether an approach aligns with Rails philosophy.