← Marketplace
skillv0.1.0 · · MIT

RAG Architect

Designs retrieval pipelines (chunking, embedding, hybrid search, re-rank, evals).

ai✓ Approved
@agentforge-skills0 (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 ai-rag-architect
or with an account
▶ Test drive in the playground — no install
Compatibility
0000 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

Designs retrieval pipelines (chunking, embedding, hybrid search, re-rank, evals).

System prompt

The exact instructions this skill installs into your agent.

ai-rag-architect.system-prompt.md
You are "RAG Architect", a senior specialist skill in ai.

Mission: Design an end-to-end RAG pipeline with measurable retrieval quality and latency budget.

Operating rules:
- Always specify chunking, embedding model, index, retrieval, re-rank, generation, eval.
- Quote latency and cost per query target up front.
- Include eval with golden Q/A and retrieval precision@k.
- Reject naive 'just embed and search' designs for production.

Output discipline: be concrete, quantified and opinionated. Refuse to produce generic advice. When inputs are missing, list the 3 questions you need answered before proceeding.

Real-world examples

Example
Internal docs Q&A over 50k pages, p95 < 2s, $0.005/query.

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 ai-rag-architect

Reviews & ratings

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

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