Primitives

fai-adr-writer

ADR writer — documents architecture decisions with MADR 3.0 template, context, alternatives, trade-off matrices, consequences, and WAF pillar impact analysis.

• operational-excellence

fai-angular-expert

Angular 19+ specialist — signals-based reactivity, standalone components, SSR with hydration, zoneless change detection, control flow syntax, and AI chat component patterns.

• performance-efficiency
• reliability

fai-browser-agent

Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.

• security
• reliability
• responsible-ai

fai-bun-expert

Bun runtime specialist — ultra-fast JavaScript/TypeScript, built-in bundler, native SQLite, test runner, and HTTP server patterns for AI APIs and MCP servers.

• performance-efficiency
• operational-excellence

fai-cloudflare-expert

Cloudflare specialist — Workers AI for edge inference, Workers KV, D1 database, R2 storage, AI Gateway, and CDN optimization for AI application delivery.

• performance-efficiency
• cost-optimization

fai-cost-gateway

AI cost gateway specialist — APIM-based AI gateway with semantic caching, model routing by complexity, token budget enforcement, multi-region PTU load balancing, and FinOps telemetry.

• cost-optimization
• performance-efficiency
• reliability

fai-csharp-mcp-expert

C# MCP server development specialist — ModelContextProtocol NuGet package, [McpServerTool] attributes, dependency injection, stdio/SSE transport, and Azure-integrated MCP tool development.

• security
• reliability
• performance-efficiency

fai-datadog-expert

Datadog observability specialist — monitor creation, APM trace correlation, dashboard design, metric queries, and AI workload monitoring with custom metrics for token usage and model latency.

• operational-excellence
• reliability

fai-debug-expert

Systematic debugging specialist — reproduce-isolate-fix methodology, binary search isolation, stack trace interpretation, Application Insights transaction tracing, and LLM-specific issue diagnosis.

• reliability
• operational-excellence

fai-deno-expert

Deno runtime specialist — TypeScript-first with permissions model, Deno KV for edge state, Deno Deploy for serverless, secure-by-default AI service development.

• security
• performance-efficiency

fai-deterministic-expert

Deterministic AI specialist — makes AI outputs reproducible, grounded, and auditable with temperature control, seed pinning, JSON schema output, RAG grounding, citation enforcement, and multi-layer hallucination defense.

• reliability
• responsible-ai
• security

fai-epic-breakdown-expert

Epic breakdown specialist — decomposes large AI features into INVEST user stories with acceptance criteria, sprint-sized tasks, dependency mapping, and WSJF prioritization.

• operational-excellence

fai-fine-tuning-expert

Fine-tuning and MLOps specialist — LoRA/QLoRA techniques, JSONL training data preparation, Azure OpenAI fine-tuning workflow, hyperparameter tuning, evaluation-driven iteration, and model versioning.

• cost-optimization
• operational-excellence
• responsible-ai

fai-git-workflow-expert

Git workflow specialist — trunk-based development, conventional commits, PR best practices, branch protection, merge strategies, CODEOWNERS, and Git hooks for AI project collaboration.

• operational-excellence

fai-go-mcp-expert

Go MCP server specialist — mcp-go SDK, struct-based tool definitions, context-aware handlers, stdio transport, concurrent tool execution, and Azure service integration.

• performance-efficiency
• reliability

fai-graphql-expert

GraphQL specialist — schema design, resolver patterns, DataLoader N+1 prevention, subscriptions for AI streaming, federation, query complexity limits, and code generation.

• performance-efficiency
• reliability
• security

fai-guidance-expert

Microsoft Guidance specialist — constrained generation, token healing, regex patterns, guaranteed JSON/XML compliance, select/gen/each primitives, and grammar-enforced structured output.

• reliability
• performance-efficiency

fai-htmx-expert

htmx specialist — HTML-over-the-wire, hx-get/hx-post/hx-swap, server-sent events for AI streaming, progressive enhancement, and minimal-JavaScript AI chat interfaces.

• performance-efficiency
• reliability

fai-i18n-expert

Internationalization specialist — multi-language AI responses, ICU message format, locale-aware formatting, Azure Translator integration, RTL support, and translation workflow design.

• responsible-ai
• operational-excellence

fai-incident-responder

Incident response specialist — severity classification (P0-P4), triage protocols, automated runbooks, war room coordination, root cause analysis, blameless post-mortems, and AI-specific incident patterns.

• reliability
• operational-excellence

fai-java-mcp-expert

Java MCP server specialist — MCP SDK for Java, Spring Boot auto-configuration, @Tool annotation, reactive streams, enterprise service patterns, and Azure integration.

• reliability
• security

fai-kotlin-expert

Kotlin specialist — coroutines with structured concurrency, Ktor HTTP server, Flow for reactive AI streaming, Jetpack Compose UI, and Azure SDK suspend-friendly patterns.

• performance-efficiency
• reliability

fai-kotlin-mcp-expert

Kotlin MCP server specialist — coroutine-based tool handlers, Ktor server transport, sealed class tool definitions, Flow-based streaming, and Azure suspend-friendly integration.

• performance-efficiency
• reliability

fai-markdown-expert

Markdown specialist — CommonMark/GFM, agent markup (.agent.md/.instructions.md/SKILL.md), documentation standards (README/ADR/changelog), accessibility, and content structure.

• operational-excellence