Content & Media

Send BSV transactions using @bsv/sdk. Build, sign, and broadcast transactions to the BSV blockchain.

Default testing standard for all implementation work - ensures code actually works through mandatory execution validation before confirming to user. Applies automatically whenever writing, modifying, debugging, or implementing any code (scripts, APIs, UI, configs, data operations, logic changes). This is the baseline expectation, not an optional extra - every implementation must be verified through actual execution, not assumed correct.

Guia implementação de breadcrumb de navegação hierárquica seguindo padrões de acessibilidade WCAG e design system do Ultrathink

Implement ng-alain theming system with layout configuration, responsive design, menu management, and settings drawer for ng-lin project

Create and modify combat system components for SHINOBI WAY game following the dual-system architecture (CombatCalculationSystem + CombatWorkflowSystem). Use when user wants to add new combat mechanics, damage formulas, status effects, mitigation logic, turn phases, or refactor existing combat code. Guides through proper separation of pure calculations vs state management.

PyTorch CUDA environment and performance guidance, with emphasis on CUDA 13 toolkit/driver requirements, PyTorch wheel compatibility, and runtime checks. Use when configuring PyTorch on NVIDIA GPUs, debugging CUDA setup, or migrating to CUDA 13; triggers: pytorch cuda, cuda 13, driver version, nvcc, torch.version.cuda, tf32, streams.

Optimizes token usage and context management for large tasks, cleanup operations, multi-step workflows, code audits, and complex agent operations. Automatically triggers when handling cleanup commands, large codebase analysis, multi-file operations, or tasks requiring multiple subagents. Enforces efficient context usage while maintaining quality results.

Use when building or working with Mastra agents - establishes best practices for agent development, tool creation, and workflow orchestration

Google Gemini AI integration for Claude Code. Supports multimodal analysis, long context processing, fast inference with Gemini 2.5 Flash/Pro models, and Nano Banana image generation/editing extension. Activated when users mention "Gemini", need image analysis, image generation, or require large context processing.

HestAI workflow phase execution including D0→D1→D2→D3→B0→B1→B2→B3→B4→B5 sequence, agent assignments per phase, phase transition validation, and deliverable requirements. Use when starting new phase, determining next steps, or validating phase completion.

Use when creating or editing marimo reactive Python notebooks. Covers cell structure, UI elements (mo.ui), reactivity, SQL integration, markdown, and deployment as apps. Triggers on .py notebook creation, marimo edit/run commands, reactive notebook development, or interactive data exploration. Extends python-development skill.

Use when you have a spec or requirements for a multi-step task, before touching code

Clerk modern authentication specialist covering WebAuthn, passkeys, passwordless, and beautiful UI components. Use when implementing modern auth with great UX.

Claude Code plugin creation guide. Use when creating new plugins, adding commands/skills/hooks/MCP servers to plugins, or setting up marketplace distribution. Triggers on "create plugin", "add command", "add skill", "add hook", "plugin structure".

Expert UX evaluation and usability guidance for Carbon ACX interfaces using heuristic evaluation, cognitive walkthroughs, user journey mapping, and flow analysis.

Apply the complete CURV Tools design system to all visual outputs - dashboards, reports, HTML artifacts, and data visualizations. Includes exact colors from production tools (rgb(3, 12, 27) dark background, rgb(157, 78, 221) purple accent), glassmorphic effects, gradient borders, header/footer templates, and animation patterns used in GL Decoder and SQPR Analyser.

Use when the user asks to "refactor shell script", "fix bash style", "apply Google style guide to shell", "review shell script style", "format bash script", or when writing, reviewing, or refactoring shell/bash scripts. Provides Google Shell Style Guide rules for formatting, quoting, naming, control flow, and common anti-patterns.

Background jobs with PgBoss for Wasp applications. Use when implementing async tasks, scheduled jobs, email queues, or background processing. Requires PostgreSQL database.

Advanced reasoning with search strategies (beam search, MCTS). WHEN: Complex problem-solving requiring exploration of multiple solution paths, optimization problems, decision trees, when you need scored/ranked reasoning paths. WHEN NOT: Simple linear reasoning (use sequential_thinking), trivial problems, when branching isn't needed.

Generate DHEP Behavioral Insights & Evaluation (BIE) proposals with engagementtriage, activity classification, and single-design proposal generation. Supportscausal evaluation, HEOR, digital strategy, AI governance, and training programs.