# Context LLM Pipeline

> RAG pipeline, embeddings, LLM interactions, and flow orchestration.

- Skill: `majiayu000/context-llm-pipeline` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds add majiayu000/context-llm-pipeline`
- Raw SKILL.md: https://api.skillmd.com/api/skills/majiayu000/context-llm-pipeline/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: DevOps & Infra
- Author: majiayu000 (https://skillmd.com/u/majiayu000)
- Updated: 2026-09-09
- Page: https://skillmd.com/skills/majiayu000/context-llm-pipeline

---


# LLM Pipeline Context

## Overview
Core AI logic including RAG flows, LLM service orchestration, and vector retrieval.

## Active Files

### Orchestration (Flows)
- `backend/flows/ingestion_flow.py` - Document ingestion
- `backend/flows/scraping_flow.py` - Scrape orchestration
- `backend/flows/template_review_flow.py` - LLM review flow

### Services
- `backend/services/llm/orchestrator.py` - Main LLM handler
- `backend/services/llm/pipeline.py` - Pipeline logic
- `backend/services/llm/analyzer.py` - Analysis logic
- `backend/services/research/zai.py` - ZAI research integration
- `backend/services/search_pipeline_service.py` - Search pipeline

### Shared Packages
- `packages/llm-common/` - Shared types and utilities (Submodule)

## Usage
Use this skill when working on RAG, prompt engineering, or vector search logic.