skills.rest
seanchiuai
seanchiuaiCOMMUNITY
Explore all skills by this author →
𝕏@seanchiuaiGitHub

ai-ml

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

14|2|Updated Mar 13, 2026
Search Tags:#embeddings#ai#llm#rag#agents#observability#ml
One-click install
npx skills add https://github.com/seanchiuai/openclaude --skill ai-ml-seanchiuai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-ml
Source: https://github.com/seanchiuai/openclaude/tree/main/.claude/skills/ai-ml
Command: npx skills add https://github.com/seanchiuai/openclaude --skill ai-ml-seanchiuai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AI/ML integrations bring together multiple LLM providers, embeddings, RAG pipelines, autonomous agents, Langfuse prompt management, image generation, and observability into a unified workflow. This enables teams to experiment with provider diversity, ground outputs with embeddings, orchestrate tool-calling loops, and monitor prompts across systems.

Core Features & Use Cases

  • Multi-provider LLM routing across OpenAI, Anthropic, and Google models for resilience and cost efficiency.
  • RAG and embeddings pipeline: local prompts, vector stores, and citation-aware retrieval to ground answers.
  • Autonomous agents & tooling: agent runtimes that orchestrate tasks, tool calls, and memory with observability instrumentation.
  • Observability & prompt management: Langfuse integration for traces, metrics, and prompt observation.
  • Use Case: Build an experiment that selects a model, fetches embeddings, runs a retrieval cycle, and generates a supporting image prompt.
  • Note: Do not use for voice-specific features or frontend UI tasks.

Quick Start

Configure a sample multi-provider AI workflow with models, embeddings, RAG, and a basic agent experiment.

Frequently Asked Questions about ai-ml

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

FAQPage Schema
How do I route prompts across multiple LLM providers like OpenAI, Anthropic, and Google?▼

Multi-provider LLM routing unifies OpenAI, Anthropic, and Google models into a single configurable workflow, enabling resilient and cost-efficient AI operations through provider adapters and robust error handling.

How does RAG pipeline with embeddings work for grounding LLM outputs?▼

RAG pipelines with embeddings ground LLM outputs by integrating local prompts, vector stores, and citation-aware retrieval, ensuring responses are contextually anchored and verifiable.

Can I use Langfuse for observability and prompt management in multi-provider AI workflows?▼

Langfuse integration provides observability and prompt management for multi-provider AI workflows by capturing traces, metrics, and prompt observations across Claude, OpenAI, and Google models.

What are the limitations of this multi-provider AI workflow orchestration?▼

This multi-provider AI workflow orchestration is not designed for voice-specific features or frontend UI tasks, focusing strictly on backend LLM routing, embeddings, RAG pipelines, and agent orchestration.

Related Skills

Explore More Software Engineering Skills→
AndVl1AndVl1
4

koog

Build Kotlin AI agents with tool calling and multi-provider LLM support.

Community
Advanced
ddnettersddnetters
2

langfuse-observability

Query Langfuse REST API for LLM traces, generations, costs, and metrics.

Community
Intermediate
JCETools-PetraJCETools-Petra
16

ai-llm-engineering

Design RAG pipelines with chunking, embedding, retrieval, and evaluation metrics.

Community
Advanced
vercelvercel
246

ai-gateway

Route AI model calls through a unified gateway with OIDC authentication.

Official
Advanced