Primitives

fai-specification-writer

Specification writer — generates AI-ready technical specifications with requirements, evaluation criteria, WAF alignment, API contracts, data models, and acceptance criteria.

• operational-excellence

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.

• performance-efficiency
• reliability

fai-swarm-supervisor

Multi-agent swarm supervisor — routes tasks to specialist agents, manages turn limits and token budgets, handles agent coordination, conflict resolution, and synthesizes multi-perspective results.

• reliability
• cost-optimization

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.

• performance-efficiency
• reliability

fai-tdd-green

TDD Green phase specialist — writes the minimal implementation to make failing tests pass, no more and no less. Follows the Red-Green-Refactor cycle.

• reliability

fai-tdd-red

TDD Red phase specialist — writes failing tests from requirements before any implementation. Covers happy path, error cases, edge cases, and AI-specific test scenarios.

• reliability

fai-tdd-refactor

TDD Refactor phase specialist — improves code quality while keeping ALL tests green. Applies extract method, reduce complexity, improve naming, and design pattern introduction.

• reliability
• performance-efficiency

fai-teams-expert

Microsoft Teams integration specialist — Adaptive Cards, Bot Framework SDK, Graph API for channels/chats/meetings, AI-powered meeting summarization, and action item extraction.

• operational-excellence
• security

fai-tech-debt-analyst

Tech debt analyst — identifies, quantifies, and prioritizes technical debt with cost-of-delay analysis, remediation plans, and sprint allocation recommendations.

• operational-excellence
• reliability

fai-temporal-expert

Temporal workflow orchestration specialist — durable execution, saga patterns, long-running AI workflows, activity retry policies, timeouts, and distributed task scheduling.

• reliability
• operational-excellence

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.

• security
• reliability
• performance-efficiency

fai-typescript-mcp-expert

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

• security
• reliability
• performance-efficiency

fai-ux-designer

AI UX designer — conversation design patterns, chatbot interaction flows, AI disclosure/transparency, loading states for streaming, confidence display, and accessibility for AI interfaces.

• responsible-ai
• performance-efficiency

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.

• performance-efficiency
• reliability

fai-vercel-expert

Vercel specialist — AI SDK (streaming useChat/useCompletion), Edge Functions, Next.js deployment, KV/Blob/Postgres storage, and serverless AI application patterns.

• performance-efficiency
• operational-excellence

fai-wandb-expert

Weights & Biases specialist — experiment tracking, model versioning, hyperparameter sweeps, prompt tracing, evaluation dashboards, and LLM fine-tuning monitoring.

• operational-excellence
• performance-efficiency

fai-wasm-expert

WebAssembly specialist — WASI preview 2, Component Model, edge AI inference with Spin/Fermyon, Wasmtime runtime, and portable, sandboxed AI model execution.

• performance-efficiency
• security

fai-cost-tracker

Triggers on Stop (1 script)

fai-governance-audit

Triggers on UserPromptSubmit, SessionStart, Stop (3 scripts)

fai-license-checker

Triggers on Stop (1 script)

fai-output-validator

Triggers on Stop (1 script)

fai-pii-redactor

Triggers on Stop (1 script)

fai-secrets-scanner

Triggers on Stop (1 script)

fai-session-logger

Triggers on SessionStart, Stop, UserPromptSubmit (3 scripts)