public-qa-chatbot

What problem does it solve?

Public-facing chatbot widgets deployed without guardrails quickly exhaust API quotas, leak internal data, or deliver poor user experiences during long conversations. This Skill distills production-tested patterns for rate limiting, security hardening, cost control, observability, and chat scroll behavior so you can serve anonymous visitors safely.

Core Features & Use Cases

• Rate Limiting & Security: Multi-layer rate limits, origin validation, input size caps, and BYOK fallbacks protect against abuse and quota exhaustion.
• Cost Optimization: Semantic caching, cheap model selection, and short output limits keep LLM costs predictable for FAQ-style bots.
• Agentic Retrieval: Optional virtual filesystem tools let the model browse documentation with ls, cat, and grep-style commands instead of relying solely on top-k RAG.
• UX Patterns: Draggable windows, streaming responses, TanStack Virtual chat lists, bottom command shelves, and theme-aware styling create polished widget experiences.

Quick Start

Use the public-qa-chatbot skill to build an unauthenticated public Q&A chatbot widget with rate limiting, semantic caching, and virtualized chat scrolling for your conference or documentation site.