Use when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests external models ("blockrun", "use grok", "use gpt", "dall-e", "deepseek"). For Antigravity users, also use when credits are exhausted, stuck in refactoring loops, or need a second opinion on Gemini's code.
Consult Google Gemini CLI for second opinions on architecture, debugging, and security audits. Use Gemini's 1M+ context window for comprehensive code analysis. Compare Flash (fast) vs Pro (thorough) vs 3-Pro-Preview (cutting-edge). Use when: need second opinion on architectural decisions, stuck debugging after 2+ attempts, writing security- sensitive code, planning refactors (5+ files), approaching 70%+ context capacity, unfamiliar with tech stack, need peer review, or want Flash vs Pro vs 3-Pro-Preview comparison. Keywords: gemini-cli, google gemini, gemini command line, second opinion, model comparison, gemini-2.5-flash, gemini-2.5-pro, gemini-3-pro-preview, architectural decisions, debugging assistant, code review gemini, security audit gemini, 1M context window, AI pair programming, gemini consultation, flash vs pro, AI-to-AI prompting, peer review, codebase analysis, gemini CLI tool, shell gemini, command line AI assistant, gemini architecture advice, gemini debug help, gemini security scan, gemini cod
Create and manage AI agent skills following best practices. Use when creating new skills, optimizing context, designing multi-agent systems, or implementing progressive disclosure patterns.
Type-safe development patterns for JARVIS AI Assistant
Guides creation of high-quality Agent Skills with domain expertise, anti-pattern detection, and progressive disclosure best practices. Activate on keywords: create skill, review skill, skill quality, skill best practices, skill anti-patterns, improve skill, skill audit. NOT for general coding advice, slash commands, MCP development, or non-skill Claude Code features.
Expert skill for integrating local Large Language Models using llama.cpp and Ollama. Covers secure model loading, inference optimization, prompt handling, and protection against LLM-specific vulnerabilities including prompt injection, model theft, and denial of service attacks.
Expert in drone systems, computer vision, and autonomous navigation. Specializes in flight control, SLAM, object detection, sensor fusion, and path planning. Activate on "drone", "UAV", "SLAM", "visual odometry", "PID control", "MAVLink", "Pixhawk", "path planning", "A*", "RRT", "EKF", "sensor fusion", "optical flow", "ByteTrack". NOT for domain-specific inspection tasks like fire detection, roof damage assessment, or thermal analysis (use drone-inspection-specialist), GPU shader optimization (use metal-shader-expert), or general image classification without drone context (use clip-aware-embeddings).
Create and manage Teachable online courses with browser automation and AI content generation. Use when building courses, setting up curriculum, generating content with CCG, or automating Teachable admin tasks.
Extracts key learnings from conversations, debugging sessions, and failed attempts. Use at session end or after solving complex problems to capture insights. Stores discoveries in memory (via amplihack.memory.discoveries), suggests PATTERNS.md updates, and recommends new agent creation. Ensures knowledge persists across sessions via Kuzu memory backend.
Expert bot developer specializing in Discord, Telegram, Slack automation with deep knowledge of rate limiting, state machines, event sourcing, moderation systems, and conversational AI integration. Activate on 'Discord bot', 'Telegram bot', 'Slack bot', 'chat automation', 'moderation system'. NOT for web APIs (use backend-architect), general automation scripts (use python-pro), or frontend chat widgets (use frontend-developer).
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations. Use PROACTIVELY for LLM features, chatbots, AI agents, or AI-powered applications.
Handle mental health crisis situations in AI coaching safely. Use when implementing crisis detection, safety protocols, emergency escalation, or suicide prevention features. Activates for crisis keywords, safety planning, hotline integration, and risk assessment.
Sets up and configures Convex agents for chat-based AI interactions. Use this when initializing agent instances, creating conversation threads, and generating basic text or structured responses from LLMs. Essential foundation for any Convex agent implementation.
Expert speech-language pathologist specializing in AI-powered speech therapy, phoneme analysis, articulation visualization, voice disorders, fluency intervention, and assistive communication technology. Activate on 'speech therapy', 'articulation', 'phoneme analysis', 'voice disorder', 'fluency', 'stuttering', 'AAC', 'pronunciation', 'speech recognition', 'mellifluo.us'. NOT for general audio processing, music production, or voice acting coaching without clinical context.
Detects fabricated content, false citations, and unverifiable claims in agent outputs. Uses source verification and consistency checking. Activate on 'detect hallucination', 'fact check', 'verify claims', 'check accuracy', 'find fabrications'. NOT for validation (use dag-output-validator) or confidence scoring (use dag-confidence-scorer).
Comprehensive knowledge of Microsoft Agent Framework for building production AI agents and workflows. Auto-activates for agent building, workflow design, AutoGen migration, and enterprise AI tasks.
AgentDB Reinforcement Learning Training operates on 3 fundamental principles:
Autonomous context extraction and structuring for converting unstructured information from multiple sources into AI-interpretable structured formats.
Orchestrates multi-step agent operations with durable execution, automatic retries, and recovery from failures. Use this for complex workflows that need to survive server restarts or coordinate multiple agents.
