Skip to main content

Primitive Explorer · 847 primitives

Primitives

Every authoring primitive across the FrootAI catalog. Agents, skills, instructions, hooks, plugins, workflows — searchable + faceted. Each one is MIT-licensed and runnable today.

← Home

Filter

Type
WAF pillars (must include all)
Play usage

40 of 847 primitivesClear filters

  • 🤖 agentsused by 2

    fai-grpc-expert

    gRPC specialist — Protocol Buffers schema design, unary/streaming RPCs, interceptors for auth and tracing, load balancing, health checking, and high-performance AI microservice communication.

    agents/fai-grpc-expert.agent.md173 lines
    • performance-efficiency
    • reliability
    …
  • 🤖 agentsused by 2

    fai-kubernetes-expert

    Kubernetes specialist — pod scheduling, GPU resource management, network policies, Helm charts, GitOps with Flux/ArgoCD, and production-grade AI workload orchestration on AKS.

    agents/fai-kubernetes-expert.agent.md174 lines
    • reliability
    • performance-efficiency
    • security
    …
  • 🤖 agentsused by 2

    fai-llamaindex-expert

    LlamaIndex data framework specialist — document loaders, index types (VectorStore/Summary/Knowledge Graph), query engines, response synthesizers, and agent tool integration for RAG.

    agents/fai-llamaindex-expert.agent.md147 lines
    • performance-efficiency
    • reliability
    …
  • 🤖 agentsused by 2

    fai-production-patterns-expert

    Production AI patterns expert — hosting selection (Container Apps/AKS/Functions), APIM gateway patterns, streaming SSE, retry/circuit-breaker, health checks, and multi-region deployment for production AI workloads.

    agents/fai-production-patterns-expert.agent.md175 lines
    • reliability
    • performance-efficiency
    • cost-optimization
    • operational-excellence
    …
  • 🤖 agentsused by 2

    fai-python-expert

    Python development specialist — Python 3.12+, async/await patterns, Pydantic v2, FastAPI, pytest, type hints, Azure SDK, and production-grade AI application patterns.

    agents/fai-python-expert.agent.md147 lines
    • security
    • reliability
    • performance-efficiency
    …
  • 🤖 agentsused by 2

    fai-python-mcp-expert

    Python MCP server specialist — FastMCP framework, @mcp.tool() decorators, async handlers, Pydantic input models, uv deployment, and Azure service integration for AI tools.

    agents/fai-python-mcp-expert.agent.md172 lines
    • security
    • reliability
    • performance-efficiency
    …
  • 🤖 agentsused by 2

    fai-rag-architect

    Enterprise RAG architecture specialist — designs end-to-end retrieval-augmented generation pipelines with Azure AI Search, OpenAI embeddings, chunking strategies, grounding, citation, evaluation, and production deployment.

    agents/fai-rag-architect.agent.md144 lines
    • security
    • reliability
    • cost-optimization
    • performance-efficiency
    …
  • 🤖 agentsused by 3

    fai-rag-expert

    RAG expert — advanced retrieval patterns (agentic, graph, multi-modal RAG), chunking strategies, hybrid search, re-ranking, evaluation metrics, and production RAG optimization.

    agents/fai-rag-expert.agent.md169 lines
    • reliability
    • performance-efficiency
    • cost-optimization
    …
  • 🤖 agentsused by 2

    fai-refactoring-expert

    Code refactoring specialist — extract method, reduce cyclomatic complexity, improve testability, SOLID principles, design pattern application, and safe behavior-preserving transformations.

    agents/fai-refactoring-expert.agent.md155 lines
    • reliability
    • performance-efficiency
    …
  • 🤖 agentsused by 2

    fai-rust-expert

    Rust specialist — ownership/borrowing, async with tokio, serde serialization, error handling with thiserror/anyhow, and high-performance AI infrastructure (inference proxies, MCP servers).

    agents/fai-rust-expert.agent.md159 lines
    • security
    • performance-efficiency
    • reliability
    …
  • 🤖 agentsused by 2

    fai-solutions-architect

    Cloud solutions architect — end-to-end AI solution design, Azure service selection, multi-service integration, cost estimation, WAF trade-off analysis, and architecture decision records.

    agents/fai-solutions-architect.agent.md147 lines
    • reliability
    • cost-optimization
    • performance-efficiency
    • security
    …
  • 🤖 agentsused by 2

    fai-streaming-expert

    Real-time streaming specialist — SSE for LLM token delivery, WebSocket for bidirectional chat, ReadableStream API, backpressure handling, and Azure Event Hubs stream processing for AI pipelines.

    agents/fai-streaming-expert.agent.md175 lines
    • performance-efficiency
    • reliability
    …
  • 🤖 agentsused by 2

    fai-swift-expert

    Swift specialist — structured concurrency (async/await, TaskGroup, actors), SwiftUI, Codable, and Apple platform AI integration with on-device Core ML and cloud Azure OpenAI.

    agents/fai-swift-expert.agent.md152 lines
    • performance-efficiency
    • reliability
    …
  • 🤖 agentsused by 2

    fai-typescript-expert

    TypeScript/Node.js specialist — strict mode, Zod validation, ESM modules, Vitest testing, Azure SDK integration, async patterns, and production-ready AI application development.

    agents/fai-typescript-expert.agent.md143 lines
    • security
    • reliability
    • performance-efficiency
    …
  • 🤖 agentsused by 2

    fai-typescript-mcp-expert

    TypeScript MCP server specialist — @modelcontextprotocol/sdk, McpServer class, Zod schema validation, async tool handlers, stdio/SSE transport, and npm distribution.

    agents/fai-typescript-mcp-expert.agent.md150 lines
    • security
    • reliability
    • performance-efficiency
    …
  • 🤖 agentsused by 2

    fai-vector-database-expert

    Vector database specialist — HNSW vs IVFFlat index selection, embedding storage with Qdrant/Pinecone/pgvector/Azure AI Search, similarity metrics, and performance tuning for RAG retrieval.

    agents/fai-vector-database-expert.agent.md158 lines
    • performance-efficiency
    • reliability
    …

Catalog synthesised from frootai/. Refresh with pnpm catalog:sync. Default page size: 24.