skills.rest
stars-end
stars-endOFFICIAL
Explore all skills by this author →
GitHub

context-llm-pipeline

Coordinate RAG pipelines and LLM interactions for document ingestion, retrieval, and reasoning.

Updated Aug 23, 2026
Search Tags:#embeddings#llm#rag#orchestration#vector-search
One-click install
npx skills add https://github.com/stars-end/affordabot --skill context-llm-pipeline
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: context-llm-pipeline
Source: https://github.com/stars-end/affordabot/tree/main/.claude/skills/context-llm-pipeline
Command: npx skills add https://github.com/stars-end/affordabot --skill context-llm-pipeline

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Core AI logic including RAG flows, LLM service orchestration, and vector retrieval to enable scalable AI-assisted workflows.

Core Features & Use Cases

  • Flows: Ingestion, scraping, and template review pipelines.
  • Services: Orchestrator, pipeline, and analyzer for LLM interactions.
  • Shared Packages: llm-common utilities for consistency.
  • Usage: Build end-to-end RAG pipelines with multiple data sources and vector stores.

Quick Start

Use this skill when building or debugging RAG workflows. For example, invoke ingestion_flow or scraping_flow to process new documents.

Frequently Asked Questions about context-llm-pipeline

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

FAQPage Schema
How do I build a RAG pipeline that retrieves and reasons over documents?▼

RAG pipelines coordinate document ingestion, vector storage, and LLM retrieval to enable end-to-end reasoning. Use ingestion_flow to process documents into a vector store, then invoke the orchestrator service to retrieve relevant context and pass it to the LLM for reasoning tasks.

What's the best way to orchestrate multiple LLM interactions in a workflow?▼

LLM orchestration coordinates sequential and parallel LLM calls across ingestion, retrieval, and analysis stages. The orchestrator service manages flow execution, prompt engineering, and vector search integration to synchronize multiple AI tasks and dependencies.

Can I use vector search with my existing document ingestion pipeline?▼

Yes. Vector search integrates with ingestion pipelines to index documents as embeddings and enable fast semantic retrieval. The pipeline automatically embeds documents during ingestion and the orchestrator queries the vector store to surface relevant context for LLM processing.

How do I handle scraping, ingestion, and template review in a single workflow?▼

Use specialized flows for each stage: scraping_flow extracts raw content, ingestion_flow processes it into retrievable documents, and template review pipelines validate output. Chain flows through the orchestrator to create end-to-end AI-assisted workflows.

What happens when vector retrieval doesn't return relevant documents?▼

Check embedding quality, vector store configuration, and query formulation. The analyzer service can diagnose retrieval gaps and the orchestrator supports prompt refinement and multi-stage retrieval strategies to improve relevance across different data sources.

Do I need to manage vector store configuration separately from my ingestion setup?▼

The pipeline abstracts vector store management within the orchestration layer, but you configure embedding models and retrieval parameters as part of flow setup. The llm-common utilities provide consistent configuration across ingestion and retrieval stages.

Related Skills

Explore More Software Engineering Skills→
dotlab-hqdotlab-hq

langchain-rag

Build RAG pipelines that ingest, chunk, embed, and retrieve documents for LLMs.

Official
Intermediate
nahisahonahisaho
3

scientific-gwas-catalog

Retrieve GWAS Catalog associations, traits, and study metadata via the NHGRI-EBI REST API.

Community
Intermediate
leonardoteodorooleonardoteodoroo

rag-implementation

Builds minimal RAG pipelines combining vector stores and document retrieval for grounded answers.

Community
Advanced
zhuangbiaoweizhuangbiaowei
2

llamaindex

Build LLM applications with RAG using data connectors and vector indices.

Community
Advanced