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

provider-patterns

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

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill helps teams configure provider-specific behavior and adapter patterns to maximize reliability and performance across LLM providers.

Core Features & Use Cases

  • Provider-aware configuration: select providers, apply extended thinking, and set model options with automatic adaptation to streaming quirks.
  • 7-hook adapter system: taskFraming, toolGuidance, continuationHint, errorRecovery, synthesisPrompt, qualityCheck, and systemPromptPatch are automatically applied across providers.
  • Cross-provider orchestration: supports local Ollama, proxy routing via LiteLLM, and multi-provider setups for production agents.

Quick Start

Configure Reactive Agents to use a specific provider, model, and reasoning strategy, then enable provider-specific adapters to optimize performance across providers.

Frequently Asked Questions about provider-patterns

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

FAQPage Schema
How do I configure LLM routing for different providers like Anthropic and OpenAI?▼

LLM routing for different providers is configured by applying provider-specific adapter hooks and behavioral settings that automatically adapt to streaming quirks, extended thinking, and system prompts across Anthropic, OpenAI, Gemini, and Ollama.

What are adapter hooks and how do they optimize LLM interactions?▼

Adapter hooks are a 7-hook system—taskFraming, toolGuidance, continuationHint, errorRecovery, synthesisPrompt, qualityCheck, and systemPromptPatch—automatically applied across providers to optimize LLM task framing, tool guidance, and error recovery.

Can I use proxy routing with LiteLLM for local Ollama models?▼

Yes, cross-provider orchestration supports proxy routing via LiteLLM and local Ollama models, allowing you to configure multi-provider setups for production agents with automatic adaptation to local streaming considerations.

Does this approach support extended thinking scenarios across multiple LLM providers?▼

Extended thinking scenarios are supported across Anthropic, OpenAI, Gemini, and Ollama by enforcing provider-specific configurations and applying reasoning strategies alongside adapter hooks to optimize model performance.

What is the best way to handle provider-specific streaming quirks in LLM applications?▼

The best way to handle streaming quirks is to enable provider-specific adapters that automatically apply error recovery and continuation hints, ensuring reliable LLM interactions across local and cloud-based providers.

Related Skills

Explore More Software Engineering Skills→
arrowcirclearrowcircle
7

llm-db

Catalog and normalize provider and model metadata for deterministic LLM selection.

Community
Intermediate
vercel-labsvercel-labs
159

ai

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

Official
Advanced
seanchiuaiseanchiuai
14

ai-ml

Unify multi-provider LLM routing, embeddings, and RAG pipelines into configurable AI workflows.

Community
Advanced
kettleofketchupkettleofketchup

litellm

Deploy an OpenAI-compatible API gateway routing requests to 100+ LLM providers.

Community
Advanced