Deep Learning

Deploy a temporary LimaCharlie EDR agent on the local Linux or Mac OS host for testing. Downloads and runs the LC sensor in a temp directory with automatic cleanup. Use for testing detection rules, investigating sensor behavior, or development. Requires selecting or creating a LimaCharlie organization first.

Integration with AppFlowy project management tool for task tracking, database management, and workspace organization. Use when working with AppFlowy, managing project tasks, creating databases, organizing workspaces, syncing agent work with project tracking, syncing documentation or tasks to AppFlowy, setting up automated sync workflows, or when the user mentions AppFlowy, project tracking, task management, or sync automation. Includes generic sync script that works with ANY project. Supports rich text formatting (bold, italic, code, links, strikethrough) and git pushsync workflow for automated syncing.

Use when creating, modifying, or understanding Svelte components in SikhAid project. Covers component naming conventions, file organization, component hierarchy, import patterns, and reusable UI patterns.

Write self-documenting code with minimal, helpful comments that explain large sections of logic without cluttering the codebase. When writing or editing any code files and deciding whether to add comments. When reviewing existing comments to ensure they remain relevant and helpful. When structuring code to be self-explanatory through clear naming and organization. When adding comments to explain complex logic or non-obvious implementation details. This skill applies universally to all code files to maintain clean, well-documented code.

Understand the toy relational database architecture, crate organization, data flow, and implementation patterns. Use when exploring the database codebase, understanding query execution, debugging storage/indexing, or planning new features. Keywords: sql-database, database, crate, storage, executor, planner, parser, catalog, WAL, buffer pool, index, architecture

Organize, create, and maintain documentation for projects. Use when the user asks to set up docs structure, write documentation, update existing docs, create READMEs, ADRs, guides, or any project documentation. Triggers include "organize my docs", "set up documentation", "write docs for this", "update the README", "document this", or when working on a project that needs documentation.

Comprehensive context and token usage management for Claude Code. Use this skill when working with large codebases, managing context window budget, optimizing file loading strategies, or when responses indicate context limitations. Helps with token analysis, file organization, query optimization, and context-efficient development workflows.

Design, organize, and operate Deepnote projects as the InsightPulseAI Data Lab workspace for exploration, jobs, and Superset-ready summary tables.

Organizational coding standards and architectural patterns. References comprehensive skills for detailed patterns. Use when making architecture decisions or implementing features.

Interpretive guidance for Claude Code memory management system. Helps choose between memory locations, organize modular rules, use path-specific rules, and avoid common pitfalls. Use when setting up CLAUDE.md files, organizing .claude/rules/ directories, or deciding where to put project instructions.

Implement Clerk multi-tenant organization features with RBAC, role-based access control, organization switching, member management, and tenant isolation. Use when building multi-tenant SaaS applications, implementing organization hierarchies, configuring custom roles and permissions, setting up organization-scoped data isolation, or when user mentions organizations, RBAC, multi-tenancy, roles, permissions, organization switcher, member management, or tenant isolation.

Extracts hidden data from files and analyzes forensic artifacts. Use when working with images, memory dumps, disk images, steganography, file carving, or when searching for hidden flags in files.

WordPress custom theme development specialist focused on clean, maintainable code following VIP standards. Includes modular theme structure, dart-sass via Homebrew, proper script/style enqueueing, template parts organization, text domain management, and comprehensive security practices (escaping, sanitization, file paths).

Use when auditing, scaffolding, or validating MetaSaver React portal app directory structure. Includes file organization patterns, domain grouping, feature composition, routing configuration, and Auth0 integration setup. File types: .tsx, .ts, directory layouts.

This skill provides comprehensive knowledge for integrating Clerk authentication in React, Next.js, and Cloudflare Workers applications. It should be used when setting up user authentication, implementing protected routes, verifying JWT tokens, creating custom JWT templates with user metadata and organization claims, configuring Clerk middleware, integrating with shadcn/ui components, testing authentication flows, or troubleshooting Clerk authentication errors.Use when: adding Clerk to React/Vite projects, setting up Clerk in Next.js App Router, implementing Clerk authentication in Cloudflare Workers, configuring clerkMiddleware for route protection, creating custom JWT templates with shortcodes (user.id, user.email, user.public_metadata.role), accessing session claims for RBAC, integrating with Supabase/Grafbase, verifying tokens with @clerk/backend, integrating Clerk with Hono, using Clerk shadcn/ui components, writing E2E tests with Playwright, generating test session tokens, using test email addresses a

Comprehensive Python AI/ML development expert with 10+ years experience using UV package manager. Covers PyTorch, TensorFlow, scikit-learn, transformers, langchain, pandas, numpy, OpenCV, and all major AI/ML libraries. Automatically audits projects, generates production-ready code with type hints, optimizes performance, sets up RAG pipelines, manages dependencies with UV, and ensures best practices. Use for AI/ML project setup, model training, data processing, LLM applications, computer vision, code generation, dependency management, performance optimization, and comprehensive project auditing. Excludes Tkinter and desktop UI libraries.

Distributed training strategies including DistributedDataParallel (DDP) and Fully Sharded Data Parallel (FSDP). Covers multi-node setup, checkpointing, and process management using torchrun. (ddp, fsdp, distributeddataparallel, torchrun, nccl, rank, process-group)

Maintain consistent file structure - components/ui for base shadcn, components/shared for composed components, pages for routes, always use barrel exports

Provides Notion workspace organization patterns, layout preferences, and workflow automation for personal productivity systems. Includes structure guidelines, content reuse patterns, and integration with external tools. MANDATORY: Claude must read this skill file before using any Notion MCP tools.

Interpretive guidance for generating OpenSCAD code for Gridfinity desktop/drawer organizers. Provides pattern selection frameworks, dimensional constraints, and stacking system integration specific to the Gridfinity ecosystem. Use when generating OpenSCAD files for Gridfinity bins, baseplates, or accessories.