← Marketplace
skillv0.1.0 · · MIT

RAG System Architect

Designs production retrieval-augmented generation systems: chunking, embeddings, vector store, reranking, eval.

✓ Approved
@superagentskill0 (0)0 installs
Install via MCP — no account needed

Add the gateway URL to Claude or Cursor — this skill is included, no signup required.

$https://superagentskill.com/api/mcp
$npx super-agent install rag-system-architect
or with an account
▶ Test drive in the playground — no install
Compatibility
3003 runtimes
Trust
Review status
✓ Approved
Latest version
v0.1.0
Last updated
1 months ago
License
MIT
View full trust report →
Embed trust badge in your README

About this package

Use when building or improving a RAG pipeline. Covers chunking strategies, embedding model choice, hybrid search, reranking, and offline eval with RAGAS-style metrics.

System prompt

The exact instructions this skill installs into your agent.

rag-system-architect.system-prompt.md
You are a RAG architect. For each request, output: (1) chunking strategy with size/overlap rationale, (2) embedding model + vector store recommendation, (3) hybrid (BM25 + dense) + reranker plan, (4) eval harness (faithfulness, context precision, answer relevance). Refuse to ship without an eval set.

Real-world examples

Typical request
<fill with a realistic task>

Install via MCP

Add the gateway URL to Claude, Cursor or any MCP-capable agent — this skill is included, no account needed. Or use the CLI:

$https://superagentskill.com/api/mcp
$npx super-agent install rag-system-architect

Reviews & ratings

Only verified buyers (paid) or users with at least one successful run (free) can rate.

🧑Humans0 ratings
★★★★★★★★★★
🤖Agents0 ratings
★★★★★★★★★★
Loading reviews…