Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/PracticalSwan/agent-skillsnpx agentmods add skills/practicalswan/agent-skills/rag-evalWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/practicalswan/agent-skills/rag-eval)<a href="https://agentmods.dev/skills/practicalswan/agent-skills/rag-eval"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/rag-eval/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/practicalswan/agent-skills/rag-eval"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/rag-eval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 124 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00030 | $0.02601 |
| Opus 5.5 | $0.00012 | $0.01040 |
| Sonnet 5.5 | $0.00006 | $0.00520 |
| Haiku 4.5 | $0.00003 | $0.00260 |
Grade A, and why
rag-eval scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
On-disk RAG evaluation (corpus/ + train.json)
Purpose
Guide agents through NVIDIA RAG Blueprint filesystem benchmarks: preparing corpus/ and train.json, running scripts/eval/evaluate_rag.py, tuning retrieval and generation flags for quality comparisons, interpreting RAGAS JSON outputs, and triaging failures (HTTP/stream errors, empty contexts, collection mismatch, judge API).
For latency, throughput, and load testing, use the rag-perf skill (scripts/rag-perf, docs/performance-benchmarking.md) — not this skill.
When not to use
Do not use this skill for: deploying or repairing services (use rag-blueprint); evaluating APIs without the corpus/ + train.json layout; general ML experimentation unrelated to this evaluator; production monitoring/alerting; or latency/throughput benchmarking (use rag-perf).
Prerequisites
- Repo cloned; run commands from repo root (imports and paths assume this).
- Python 3.11+ and uv; eval deps:
uv sync --project scripts/eval. - Reachable RAG server and ingestor (defaults often
localhost:8081/8082). NVIDIA_API_KEYfor RAGAS (see credential hygiene); optionalRAG_EVAL_JUDGE_MODEL.- Dataset roots passed to
--dataset-pathseach containcorpus/andtrain.json.
Instructions
- Prepare data — Ensure each dataset directory matches the layout and
train.jsonrules inreferences/dataset-and-conversion.md. When sources arrive as public links (sites or dataset pages), materialize documents undercorpus/—prefer PDF for multimodal content so images stay embedded; convert CSV/JSONL/etc. using the patterns there. - Run eval —
uv run --project scripts/eval python scripts/eval/evaluate_rag.pywith--dataset-paths,--host, and--port. Seereferences/benchmark-execution.mdfor command examples, outputs, and errors. Usereferences/evaluate-rag-cli.mdfor flag-level detail. - Tune quality — Adjust
--top_k/--vdb_top_k, reranker and query-rewriting toggles, and generation overrides (--temperature,--top-p,--max-tokens) as documented inreferences/benchmark-execution.mdwhen comparing retrieval/generation configs for RAGAS scores. - Analyze results — Use
references/result-analysis.mdfor scripts; scanrag_*_evaluation_summary.jsonfor headline RAGAS metrics. - Triage errors — Use the error signal table and the Troubleshooting section below.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · -1 lines b067da130471
- 1mo ago Changed 44bd0302b241
- 1mo ago First seen · 155 lines · 30 tokens per session scan A 6fc714dace5f
rag-eval is a skill published in the GitHub repository PracticalSwan/agent-skills (21 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 2,601 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
rag-evaluator
Evaluate RAG pipeline quality across faithfulness, relevance, and hallucination metrics. Use when user asks to test, benchmark, or improve a RAG system, or when RAG outputs look wrong.
rag-evaluation
Use this skill to evaluate the quality of a RAG pipeline on faithfulness, answer relevancy, context precision, context recall, and hallucination rate. Activates after a RAG system is implemented or when retrieval quality is in question. Produces a structured evaluation report with measurable results.
generate-rag-dataset
Generate a synthetic evaluation dataset from your RAG knowledge base. Creates diverse Q&A pairs with expected answers and relevant context, ready for LangWatch experiments and platform import. Use when you need test data for your RAG pipeline.
rag-eval
Use when the user has a RAG (Retrieval-Augmented Generation) system and wants to evaluate its quality — separating retrieval issues from generation issues. Also use when the user mentions RAG evaluation, faithfulness checking, hallucination detection in RAG, retrieval quality, chunking optimization, or "is my RAG…
nemo-evaluator-sdk
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
rag-retrieval-audit
Diagnose missing evidence in a RAG pipeline with labeled queries, chunk/trace inspection, Recall@K/MRR/nDCG, and stage-isolated failure taxonomy. Use when retrieval looks fine but answers fail, or when index/chunk/filter/rerank changes need before/after proof.