Rag System Architect
- 1 installs
- Updated April 19, 2026
- adryanmoldokkr32-pixel/bionicbot-devops-ai-skills
rag-system-architect is a Claude Code skill that designs retrieval-augmented generation systems for answering questions over private data.
About
rag-system-architect designs Retrieval-Augmented Generation systems that answer questions from a private set of documents. A developer uses it to plan a data ingestion pipeline (chunking, embedding), pick a retrieval strategy (semantic, keyword, or hybrid), and design the context-injection step in the LLM prompt. It also covers source attribution and tuning the retrieval window to prevent hallucinations.
- Designs RAG systems that answer from a private document set
- Covers chunking, embedding, retrieval strategy, and context injection
- Adds source attribution and retrieval tuning to reduce hallucinations
Rag System Architect by the numbers
- 1 all-time installs (skills.sh)
- Ranked #14,098 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Jul 7, 2026 (Skillselion catalog sync)
rag-system-architect capabilities & compatibility
- Capabilities
- rag design · retrieval strategy · embedding pipeline
- Use cases
- research · web search
What rag-system-architect says it does
Design Retrieval-Augmented Generation systems for private data.
Implement a retrieval strategy (Semantic search, Keyword search, Hybrid).
npx skills add https://github.com/adryanmoldokkr32-pixel/bionicbot-devops-ai-skills --skill rag-system-architectAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 1 |
|---|---|
| Last updated | April 19, 2026 |
| Repository | adryanmoldokkr32-pixel/bionicbot-devops-ai-skills ↗ |
How do you build a RAG system that answers only from private documents without hallucinating?
Design a RAG pipeline that answers questions grounded in a private document collection with source citations.
Who is it for?
Developers building a RAG bot or private-document Q&A pipeline who need an ingestion and retrieval design.
Skip if: Tasks where a task-specific model already works and no private-document retrieval is needed.
When should I use this skill?
The user wants to build or improve a RAG system over their own documents or data.
What you get
A RAG design with chunking, embeddings, a retrieval strategy, context injection, and source attribution.
- A RAG ingestion and retrieval design
- Context-injection and source-attribution plan
By the numbers
- 5-step design process (ingestion, retrieval, context injection, attribution, tuning)
Files
RAG System Architect
This skill focuses on teaching AI to answer questions based exclusively on a private set of documents or data.
Instructions
1. Design the data ingestion pipeline (Chunking, Embedding). 2. Implement a retrieval strategy (Semantic search, Keyword search, Hybrid). 3. Design the 'Context Injection' step in the LLM prompt. 4. Implement source attribution to cite specific documents. 5. Optimize the retrieval window to prevent hallucinations.
Examples
- "Build a RAG system that answers questions based on my company's PDFs."
- "Improve the accuracy of my RAG bot by adjusting the chunk size."
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10FAQ
What retrieval strategies does it cover?
It covers semantic search, keyword search, and hybrid retrieval.
How does it reduce hallucinations?
It optimizes the retrieval window and adds source attribution to cite specific documents.