# Install the "RAG Architect with LlamaIndex" skill

You are installing an AgenticMarket skill into this workspace. Follow these steps exactly.

## 1. Detect your environment and choose the destination file
- Andromity: `.andromity/skills/rag-llamaindex/SKILL.md` (or user scope `~/.andromity/skills/rag-llamaindex/SKILL.md`)
- Antigravity / Gemini CLI: `.agent/skills/rag-llamaindex/SKILL.md`
- Cursor: `.cursor/rules/rag-llamaindex.mdc`
- Claude Code: append to `CLAUDE.md` (or `.claude/skills/rag-llamaindex.md`)
- Windsurf: append to `.windsurfrules`
- Cline / Roo Code: `.clinerules/rag-llamaindex.md`
- GitHub Copilot: append to `.github/copilot-instructions.md`
- ChatGPT / web only: paste the content into Custom Instructions
- Any other agent: save to `.agent/skills/rag-llamaindex/SKILL.md`

## 2. Create the destination file
- Preserve every existing file and configuration entry.
- Create parent folders as needed.
- Never overwrite unrelated content.

## 3. Write exactly this content

```markdown
---
name: rag-llamaindex
description: "Architect Retrieval-Augmented Generation (RAG) pipelines, hierarchical chunking, vector indexing, and cross-encoder re-ranking."
author: community
license: mit
version: 1.0.0
---
# RAG Architecture with LlamaIndex

Building high-accuracy RAG systems:
- Split documents using semantic sentence windowing or hierarchical chunking.
- Implement hybrid search (BM25 keyword + vector semantic embeddings).
- Re-rank top-k retrieved candidates using a cross-encoder model before sending to generator.
```

## 4. Verify
- Confirm the file exists and is readable.
- Report the destination path and confirm the "RAG Architect with LlamaIndex" skill is installed and active.

Skill metadata:
- Slug: rag-llamaindex
- Category: ai-agents
- License: mit
- Source: AgenticMarket