Skip to content
Get packs

LlamaIndex RAG Builder

Guides the agent to build document Q&A and RAG pipelines with LlamaIndex (ingest, index, query, agents).

Source Download skill
Repository
Orchestra-Research/AI-Research-SKILLs
Stars
14,195
Licence
MIT
Files
4 files

What it does

This skill gives the agent a reference guide to LlamaIndex, an open-source Python framework for connecting language models to your own documents. Once installed, the agent can write code that loads files or web pages, splits them into searchable pieces, builds an index, and answers questions over that material. It also covers building simple agents that call tools and chatbots that remember earlier turns.

Great for

  • Python developers building document Q&A or internal knowledge-base chatbots
  • Data teams prototyping retrieval-augmented generation (RAG) over private files
  • Anyone who wants the agent to write LlamaIndex code correctly without re-reading the docs

Skip it if

  • Non-programmers expecting a ready-made app: this skill writes code, it does not provide a finished product
  • Projects needing a different stack; the skill itself suggests LangChain, Haystack, or Chroma for other needs
  • Sensitive documents sent to third-party APIs without review: the examples call OpenAI and other hosted model services, so your data may leave your machine

Try asking

  • “Write a Python script that loads all PDFs in ./docs and answers questions about them with LlamaIndex”
  • “Build a chatbot over our company wiki pages that remembers the conversation”
  • “Create a LlamaIndex agent with a calculator tool and a document search tool”
  • “Save a vector index to disk and reload it later without re-embedding”
Step-by-step guide: how to use LlamaIndex RAG BuilderInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 4 original files, the MIT licence and an attribution note.

    llamaindex.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip llamaindex.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip llamaindex.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Name the data source and format explicitly (folder of PDFs, GitHub repo, web URLs) so the agent picks the right reader
  • Ask the agent to check the current LlamaIndex version, since the skill references v0.14.7 and APIs change quickly
  • Keep API keys in environment variables rather than pasting them into code or chat

What's inside

  • references/agents.md
  • references/data_connectors.md
  • references/query_engines.md
  • SKILL.md

Redistributed unmodified from Orchestra-Research/AI-Research-SKILLs under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.