Loading...
Loading...
Found 2,220 Skills
Guides engineering of multi-agent systems—agent roles and specialization, orchestration topologies (supervisor, peer-to-peer, hierarchical, blackboard), task decomposition and routing, inter-agent messaging (A2A-style patterns), shared vs partitioned state, fan-out/fan-in and DAG workflows, synchronization and consensus, conflict resolution, fault tolerance and retries across agents, cost/latency/token budgets, cross-agent observability, testing multi-agent flows, and deployment (queues, durable workflows). Framework-agnostic; high-level LangGraph, Deep Agents, and agenthub—not single-agent loops (agentic-ai-developer), ML training (ai-engineer), strategy-only whiteboard (enterprise-strategist), or PM planning (technical-program-manager). Use for multi-agent system, multi-agent engineer, agent orchestration, supervisor agent, agent topology, fan-out fan-in, agent handoff protocol, multi-agent workflow, agent coordination, blackboard pattern, hierarchical agents, A2A, agent DAG, multi-agent architecture.
Generate a fully working React + Vite app that explains a codebase's workflows, data types, and architecture through interactive visuals — click-to-step animated walkthroughs with auto-play, sequence diagrams, animated packet tracers, message inspectors that toggle between named-field view and raw JSON, and collapsible code peeks with file:line citations. Splits the repo into 4–6 domain clusters and dispatches one content agent per cluster to write the pages in parallel. The skill bundles its own reference pages (under references/examples/) so it works in any repo. Use this skill whenever the user asks for interactive docs, animated explainers, an "agent team" for docs, one page per domain, wants to visualize a system's request flow or wire protocol, or any visual documentation site. Requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 in .claude/settings.json.
Technology-agnostic guidance for modular systems: bounded contexts, clear boundaries, composability, state isolation, explicit contracts, failure containment, scaffolding workflows, split/merge criteria, sub-units inside a context, and compliance review signals. Use when designing or reviewing module structure, service boundaries, package layout, cross-cutting dependencies, "how should we split this?", modularity assessments, coupling between domains, greenfield context design, or architecture discussions without assuming a specific framework, language, or repository layout. Do NOT use for executing the full Patterns 1–5 repo decomposition pipeline or per-pattern inventories (use modular-decomposition), phased extraction roadmaps as the main deliverable (use decomposition-planning-roadmap), or end-to-end legacy migration strategy (use legacy-migration-planner).
Service hierarchy, 7 foundational patterns, cross-platform input. Client-server architecture, module patterns, framework options.
Designs user experiences and interfaces grounded in research. Use when creating user journeys, wireframes, prototypes, or improving usability. Use for information architecture, interaction design, accessibility audits, design system creation, and developer handoff.
End-to-end retail ETL pipeline using PySpark, SQL Server, and Medallion Architecture (Bronze/Silver/Gold layers) for data warehousing
Infrastructure-as-code specialist for multi-cloud provisioning using Terraform across any provider (AWS, GCP, Azure, Oracle Cloud). Use for terraform plan/apply, state management, compute, databases, storage, networking, IAM, OIDC, cost optimization, policy-as-code, ISO/IEC 42001 AI controls, ISO 22301 continuity, and ISO/IEC/IEEE 42010 architecture documentation.
OneFormer for universal image segmentation. Unifies panoptic, instance, and semantic segmentation with a single architecture using task-conditioned queries. Use when training, evaluating, exporting, quantizing, or running inference for a TAO OneFormer model. Trigger phrases include "train OneFormer", "universal segmentation", "task-conditioned segmentation", "panoptic / instance / semantic in one model".
Monocular depth estimation using Metric Depth Anything v2 or Relative Depth Anything architectures. Predicts per-pixel depth from single RGB images. Use when training, evaluating, exporting, or running inference for a TAO monocular depth model. Trigger phrases include "train monocular depth", "DepthAnything v2", "metric depth from single image", "monocular depth estimation".
Expert GraphQL developer specializing in type-safe API development, schema design, resolver optimization, and federation architecture. Use when building GraphQL APIs, implementing Apollo Server, optimizing query performance, or designing federated microservices.
Enterprise-grade architecture combining DDD bounded contexts with Feature-Sliced Design. Use for large-scale monorepos with multiple domains, microservices, event-driven communication, and scalable frontend modules.
Monorepo architecture patterns with Turborepo, pnpm workspaces, and shared packages. Use when setting up multi-package repositories, shared libraries, or micro-frontend architectures.