llm-streaming-response-handler

SKILL.md

Expert in building production-grade streaming interfaces for LLM responses that feel instant and responsive.

| OpenAI | SSE | data: {"choices":[{"delta":{"content":"token"}}]} | | Anthropic | SSE | data: {"type":"contentblockdelta","delta":{"text":"token"}} | | Claude (API) | SSE | data: {"delta":{"text":"token"}} | | Vercel AI SDK | SSE | Normalized across providers |

Problem: Stream fails mid-response, user sees partial text with no indication of failure.

Build production LLM streaming UIs with Server-Sent Events, real-time token display, cancellation, error recovery. Handles OpenAI/Anthropic/Claude streaming APIs. Use for chatbots, AI assistants, real-time text generation. Activate on "LLM streaming", "SSE", "token stream", "chat UI", "real-time AI". NOT for batch processing, non-streaming APIs, or WebSocket bidirectional chat. Source: erichowens/some_claude_skills.

View raw