rag-perf

79 / 100 · Review before installing

Check before installing. Some of what it can do is expected: a coding skill usually runs build and test commands.

By NVIDIA/skills (GitHub) · coding · 3,933 stars · scanned at commit 2630133

Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for accuracy / RAGAS scoring (use rag-eval) or for deploying / repairing services (use rag-blueprint).

Works with any agent that supports SKILL.md skills.

What this skill can do

Downloads and installs other software

The author does not mention this.

Found in 3 places.

skills/rag-perf/SKILL.md, line 54- A reachable RAG server (default `http://localhost:8081`). For the aiperf phase, the bundled `nvidia_rag` endpoint plugin must be installed — `pip install -e .
skills/rag-perf/SKILL.md, line 139| CI: `ModuleNotFoundError: No module named 'ruamel'` from `tests/unit/test_rag_perf/` | rag-perf package missing from CI venv | Add `uv pip install -e ./script
skills/rag-perf/SKILL.md, line 150- **`--endpoint-type nvidia_rag`** comes from the bundled plugin at `scripts/rag-perf/rag_perf/plugin/nvidia_rag.py`. It teaches aiperf about the RAG `/v1/gener

Runs commands on your computer

This is disclosed by the author in the skill's SKILL.md or README. Expected for a coding skill.

Found in 5 places.

skills/rag-perf/SKILL.md, line 69uv run --project scripts/rag-perf rag-perf -c scripts/rag-perf/configs/single_run.yaml
skills/rag-perf/SKILL.md, line 86uv run --project scripts/rag-perf rag-perf -c scripts/rag-perf/configs/quick_profile.yaml
skills/rag-perf/SKILL.md, line 94uv run --project scripts/rag-perf rag-perf -c scripts/rag-perf/configs/single_run.yaml

Show 2 more

skills/rag-perf/SKILL.md, line 102uv run --project scripts/rag-perf rag-perf -c scripts/rag-perf/configs/sweep.yaml
skills/rag-perf/SKILL.md, line 110uv sync --project scripts/rag-perf --extra dev # one-time, installs pytest-asyncio

Connects to the internet

This is disclosed by the author in the skill's SKILL.md or README.

Found in 4 places.

skills/rag-perf/SKILL.md, line 137| `Citation count (mean): 0` and `Citation relevance score: N/A` for a non-empty deployment | Collection mismatch between `rag.collection_names` and what's actu
skills/rag-perf/references/output-and-analysis.md, line 206- **`Citation count (mean): 0` everywhere** — collection mismatch. Suggest verifying with `curl http://<ingestor>:8082/v1/collections`.
skills/rag-perf/references/output-and-analysis.md, line 239| `Citation count (mean): 0` everywhere | Collection mismatch (placeholder `<collection_name>` left in config, or wrong collection name); verify with `curl http

Show 1 more

skills/rag-perf/references/synthetic-generation.md, line 155. Fans out concurrent LLM calls (bounded by `synthetic.generation_concurrency`, default 8) using `asyncio.gather` over `asyncio.to_thread` wrappers around the

Safer alternatives

Low-risk skills in the same category (coding) that look related. Check that one does what you need.

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'rag-perf' ] || [ -L ~/.agents/skills/'rag-perf' ]; then echo 'A skill folder named rag-perf already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/NVIDIA/skills' "$d" && git -C "$d" checkout --quiet '2630133f22e357f2005886567a39eddcc1b520e2' -- 'skills/rag-perf' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/rag-perf' ~/.agents/skills/'rag-perf' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'rag-perf' ~/.claude/skills/'rag-perf' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for NVIDIA/skills shows the score of its lowest-scoring skill.

SkillTrust badge for NVIDIA/skills

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/NVIDIA/skills.svg)](https://zalavijaysinh.github.io/skilltrust/repos/NVIDIA/skills/)

Score history

Date	Version	Score
2026-11-11	`2630133`	79
2026-11-08	`fce3cca`	79
2026-11-07	`fce3cca`	79