Найдите подходящую возможность для вашего агента.
Use when planning new features or need structured requirements - creates feature structure, elicits EARS requirements through systematic questioning, proposes architectural approaches with trade-offs. Activates when user mentions "new feature", "requirements", "specs", "design", "architecture", or uses /dev-workflow:spec commands (create, requirements, design).
Route tasks to small model by default, escalate to large model only on low confidence detection, achieving 87% faster learning and 10-30x cost reduction while maintaining accuracy. Use for cost optimization, confidence-based delegation, routine vs complex task routing, and resource efficiency. Triggers on "optimize cost", "model routing", "confidence threshold", "small model first", "escalate on uncertainty".
Karrot app automation with AI Vision - bypass Play Integrity and LIAPP detection, login, and interaction workflows with Claude Vision API integration
Use when "CrewAI", "multi-agent systems", "agent orchestration", "AI crews", or asking about "autonomous agents", "agent collaboration", "role-based agents", "agent workflows", "AI team coordination"
Automatically retrieve relevant information from the organization's CustomGPT.ai knowledge base when answering questions about documented topics, policies, procedures, or technical specifications.
Analyze and improve the AI agent workforce system, ensuring compatibility across environments (CLI, IDE, GitHub) and leveraging emerging technologies.
Execute Gray Swan AI Arena indirect prompt injection (IPI) and machine-in-the-middle (MITM) challenges with optimized payloads, reconnaissance workflows, and evidence collection for CTF competition success
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
CLI for Limitless.ai Pendant with lifelog management, FalkorDBLite semantic graph, vector embeddings, and DAG pipelines. Use for personal memory queries, semantic search across lifelogs/chats/persons/topics, entity extraction, and knowledge graph operations. Triggers include "lifelog", "pendant", "limitless", "personal memory", "semantic search", "graph query", "extraction".
Builds FastAPI projects from beginner to professional level, including project structure, database integration, authentication, testing, and deployment. Use when creating new FastAPI projects, adding features, or improving project structure.
Manage user signup/signin and collect software/hardware background to enable personalized content in the Physical AI & Humanoid Robotics textbook.
Comprehensive guide to sandboxing AI agents including code execution isolation, resource limits, security boundaries, and safe tool execution
Multi-model orchestration for ARIA. Activate when dispatching tasks to different LLM providers (OpenAI, local models, cloud providers) or when optimizing cost/latency tradeoffs.
Delegate asynchronous coding tasks to Jules (Google's AI coding agent) to maximize efficiency. Use for code reviews, refactoring, adding tests, bug fixes, and documentation. Proactively suggest Jules delegation when appropriate. Invoke when user asks to interact with Jules, create sessions, check task status, or when tasks are suitable for async delegation.
Implement Zettelkasten-inspired knowledge management for building and maintaining context libraries with automated cross-referencing. Use when organizing executive knowledge, building context libraries, or implementing knowledge compounding systems.
