IDE & Editors

Comprehensive guide for creating Model Context Protocol (MCP) servers. Use when building MCP servers, integrating external APIs, or creating tool interfaces for LLMs.

Comprehensive guide for building meshes in TX V4. Covers SDK-based worker architecture, agent design, prompt templates, message protocols, and HITL workflows. Use when creating new meshes, defining agent roles, or debugging multi-agent systems.

Guide for writing and improving Claude Code skills. Use when creating new skills, debugging why skills aren't activating, or improving skill descriptions and structure.

Provides Nette Utils helper classes. Use when working with arrays, strings, files, images, JSON, validators, DateTime, or other utility functions.

Use when implementing phases from a plan document, executing phased implementations, orchestrating sub-agents for phase work, or when /workflow-implement-phases command is invoked. Provides dependency analysis and parallel/sequential execution strategies.

Skill Promotion Workflow - Atomic promotion from staging to production

Set up GPU sandboxes for interpretability research. Use when writing setup.py scripts with Sandbox, SandboxConfig, ModelConfig, or create_notebook_session. Provides the exact API for Modal GPU environments - MUST read before writing any sandbox setup code.

AI image and video generation using ComfyUI node-based workflow system with Stable Diffusion, FLUX, and other diffusion models via local or distributed GPU compute (Salad Cloud)

Provide accurate current time by calling get_time tool.

Repository structure, build/test commands, coding style, and contribution rules for opal-frontend. Use when navigating the repo, running or debugging builds/lint/tests, following style conventions, or setting up local tooling.

Provides templates, standards, and best practices for writing clear, comprehensive technical documentation

Use when validating product assumptions before building, discovering unmet user needs, understanding customer problems and workflows, testing concepts or positioning, researching target markets, identifying jobs-to-be-done and hiring triggers, uncovering pain points and workarounds, or when users mention user research, customer interviews, surveys, discovery interviews, validation studies, or voice of customer.

Systematically design and validate specialist agents with evidence-based prompting, tooling contracts, and adversarial evaluation.

INVOKE when user says: 'brainstorm', 'design this', 'help me think through', 'what should we build'. Collaborative idea-to-spec workflow.

Expert prompt optimization system for building production-ready AI features. Use when users request help improving prompts, want to create system prompts, need prompt review/critique, ask for prompt optimization strategies, want to analyze prompt effectiveness, mention prompt engineering best practices, request prompt templates, or need guidance on structuring AI instructions. Also use when users provide prompts and want suggestions for improvement.

Generate interactive presentation slides using React + Tailwind. Triggers on keywords like "slides", "presentation", "PPT", "demo", "benchmark".

Generate highly detailed, Midjourney-style image prompts optimized for the FLUX 1.1 Pro model on Replicate. Transform basic user descriptions into rich, cinematic prompts with professional photography qualities, dramatic lighting, and editorial-quality aesthetics. Use when users request image generation, need prompt enhancement, or want Midjourney-quality outputs via FLUX 1.1 Pro.

Gemini media and multimodal workflows across image, audio, and video.

Chain streaming workflows with deterministic routing, backpressure controls, and evidence-backed checkpoints.

Generate research visuals (figures, diagrams) with constraints, evidence alignment, and confidence ceilings.