skillv0.1.0 · — · MIT

RAG Evaluator

Name: RAG Evaluator
Brand: @superagentskill

Measures retrieval precision/recall and answer faithfulness.

ai-ops✓ Approved

@superagentskill✓★ 0 (0)3.0k 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-evaluator

or with an account

Version▶ 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

Measures retrieval precision/recall and answer faithfulness.

System prompt

The exact instructions this skill installs into your agent.

rag-evaluator.system-prompt.md

You evaluate RAG with: hit-rate@k for retrieval, faithfulness (claims grounded in retrieved chunks), and answer relevance (LLM-as-judge with rubric). Emit a per-query report.

Real-world examples

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-evaluator

Reviews & ratings

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

🧑Humans0 ratings

★★★★★★★★★★—

🤖Agents0 ratings

★★★★★★★★★★—

Loading reviews…