skills.rest
tylerjrbuell
tylerjrbuellCOMMUNITY
Explore all skills by this author →
GitHub

provider-streaming

Standardize streaming patterns for LLM providers with tool-enabled complete and stream methods.

21|4|Updated Feb 19, 2026
Search Tags:#testing#consistency#streaming#adapter#protocols#llm-provider#tool_calls
One-click install
npx skills add https://github.com/tylerjrbuell/reactive-agents-ts --skill provider-streaming
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: provider-streaming
Source: https://github.com/tylerjrbuell/reactive-agents-ts/tree/main/.agents/skills/provider-streaming
Command: npx skills add https://github.com/tylerjrbuell/reactive-agents-ts --skill provider-streaming

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Standardizes streaming patterns for LLM providers to ensure reliable, tool-enabled interactions across diverse backends and tool schemas, reducing integration friction.

Core Features & Use Cases

  • Provides a canonical streaming workflow that guarantees tools are passed to both complete() and stream() calls.
  • Documents provider-specific quirks and rules (e.g., comparator behavior for Anthropic, Gemini, Ollama, OpenAI, LiteLLM) to avoid common streaming pitfalls.
  • Use Case: When integrating a new provider or debugging a streaming session, follow the provider-adapter guidance and validated tests to ensure correct event sequencing.

Quick Start

Implement a new provider's streaming by wiring the provider layer, ensure the stream() method accepts tools, and run the streaming tests to verify tool event ordering.

Frequently Asked Questions about provider-streaming

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I standardize streaming patterns for LLM providers to ensure reliable tool calls?▼

Standardize streaming patterns for LLM providers by applying a canonical workflow that guarantees tools are passed to both complete() and stream() methods, ensuring reliable tool-enabled interactions across diverse backends.

Why are streaming tool calls failing when integrating a new LLM provider?▼

Streaming tool calls fail when provider-specific quirks are ignored. Documenting comparator behavior for Anthropic, Gemini, Ollama, OpenAI, and LiteLLM avoids common streaming pitfalls and ensures correct event sequencing.

What is a canonical streaming workflow for LLM provider adapters?▼

A canonical streaming workflow for LLM provider adapters is a standardized process that passes tools to both complete() and stream() calls, satisfying integration requirements and handling provider-specific quirks for reliable interactions.

Does this approach support debugging streaming sessions across multiple LLM backends?▼

Yes, debugging streaming sessions across multiple backends is supported. You can follow provider-adapter guidance and validated tests to verify correct event sequencing and resolve tool call inconsistencies across diverse LLM providers.

What are the limitations of not using a standardized streaming pattern for LLM providers?▼

Without a standardized streaming pattern, you face integration friction from undocumented provider-specific quirks, causing unreliable tool-enabled interactions and incorrect event sequencing during streaming sessions across diverse backends.

Related Skills

Explore More Software Engineering Skills→
vercel-labsvercel-labs
159

ai

Abstract low-level LLM provider APIs and streaming logic for Python applications.

Official
Advanced
vocalbridgeaivocalbridgeai
7

debug

Stream real-time debug events from the Vocal Bridge voice agent.

Official
Intermediate
duwenjiduwenji

heterogeneous-agent

Diagnose LobeHub heterogeneous agent integration failures across CLI trace, adapter mapping, and persistence stages.

Community
Advanced
tylerjrbuelltylerjrbuell
21

provider-patterns

Configure per-provider behavior and adapter hooks for LLM interactions.

Community
Advanced