rag-blueprint

52 / 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

NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change, configure, troubleshoot, debug, fix, shutdown, stop, or tear down any RAG feature or service (Agentic RAG, VLM, guardrails, query rewriting, models, search, ingestion, observability, summarization, reasoning, and more).

Works with any agent that supports SKILL.md skills.

What this skill can do

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 3 places.

skills/rag-blueprint/SKILL.md, line 115echo "=== NIM ===" && docker ps --format '{{.Names}}' 2>/dev/null | grep -iE '(nim-llm|nemotron-(vlm-)?embedding|nemotron-ranking|nemotron-vlm|nemotron-3-nano-o
skills/rag-blueprint/SKILL.md, line 139nvidia-smi --query-gpu=index,name,memory.total,memory.used --format=csv,noheader 2>/dev/null || echo "NO_GPU"
skills/rag-blueprint/SKILL.md, line 190grep -E "^(export )?(ENABLE_|APP_)" <config-file> 2>/dev/null | sort

Connects to the internet

The author does not mention this.

Found in 14 places.

skills/rag-blueprint/SKILL.md, line 159- Docker: `docker ps --format "table {{.Names}}\t{{.Status}}" | head -20; curl -s http://localhost:8081/v1/health?check_dependencies=true 2>/dev/null | head -1`
skills/rag-blueprint/SKILL.md, line 161- Library: `curl -s http://localhost:8081/v1/health 2>/dev/null | head -1`
skills/rag-blueprint/eval/h100.json, line 32"`curl -sf -o /dev/null -w '%{http_code}' http://localhost:8081/v1/health` outputs 200",

Show 11 more

skills/rag-blueprint/eval/h100.json, line 33"`curl -sf -o /dev/null -w '%{http_code}' http://localhost:8082/v1/health` outputs 200",
skills/rag-blueprint/eval/nvidia_hosted.json, line 20"`curl -sf -o /dev/null -w '%{http_code}' http://localhost:8081/v1/health` outputs 200",
skills/rag-blueprint/eval/nvidia_hosted.json, line 21"`curl -sf -o /dev/null -w '%{http_code}' http://localhost:8082/v1/health` outputs 200",
skills/rag-blueprint/eval/nvidia_hosted.json, line 22"`curl -sf -o /dev/null -w '%{http_code}' http://localhost:8090` outputs 200 (frontend served on port 8090)",
skills/rag-blueprint/references/deploy.md, line 104echo "=== RAG Server ===" && curl -s http://localhost:8081/v1/health?check_dependencies=true 2>/dev/null || echo "RAG_SERVER_NOT_READY"; echo "=== Ingestor ==="
skills/rag-blueprint/references/deploy/docker.md, line 65sleep 5; echo "=== RAG ===" && curl -s http://localhost:8081/v1/health?check_dependencies=true 2>/dev/null || echo "RAG_NOT_READY"; echo "=== INGESTOR ===" && c
skills/rag-blueprint/references/deploy/helm.md, line 74kubectl port-forward -n rag service/rag-server 8081:8081 --address 0.0.0.0 & kubectl port-forward -n rag service/rag-frontend 3000:3000 --address 0.0.0.0 & slee
skills/rag-blueprint/references/troubleshoot.md, line 8echo "=== CONTAINERS ===" && docker ps --format "table {{.Names}}\t{{.Status}}\t{{.Ports}}" 2>/dev/null | grep -E "(rag|elasticsearch|milvus|seaweedfs|nim|inges
skills/rag-blueprint/references/troubleshoot.md, line 107- [ ] Vector database accessible (`curl http://localhost:9200/_cluster/health` for default Elasticsearch, or `curl http://localhost:9091/healthz` for Milvus)
skills/rag-blueprint/references/troubleshoot.md, line 108- [ ] Embedding service healthy (`curl http://localhost:9081/v1/health/ready` for default VLM embedding, or `curl http://localhost:9080/v1/health/ready` for `te
skills/rag-blueprint/references/troubleshoot.md, line 115- [ ] LLM service accessible (`curl http://localhost:8999/v1/health/ready`)

Downloads and installs other software

The author does not mention this.

Found in 3 places.

skills/rag-blueprint/references/configure/ingestion.md, line 39- Batch CLI: `pip install -r scripts/requirements.txt` first; idempotent (skips already-ingested files)
skills/rag-blueprint/references/deploy/library-lite.md, line 162. Create virtualenv and install: `pip install nvidia-rag[all]`
skills/rag-blueprint/references/deploy/library.md, line 47- `pip install` failure → try `uv pip install` or check Python version ≥3.11.

Reads your saved credentials, such as SSH keys or .env files

The author does not mention this.

Found in 1 place.

skills/rag-blueprint/references/deploy/docker.md, line 39grep -q "nvcr.io" ~/.docker/config.json 2>/dev/null && echo "ALREADY_LOGGED_IN" || echo "NOT_LOGGED_IN"

Changes files outside its own folder

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

Found in 1 place.

skills/rag-blueprint/references/shutdown.md, line 103rm -rf ~/.cache/model-cache/

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-blueprint' ] || [ -L ~/.agents/skills/'rag-blueprint' ]; then echo 'A skill folder named rag-blueprint 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 "$d" checkout --quiet '2630133f22e357f2005886567a39eddcc1b520e2' -- 'skills/rag-blueprint' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/rag-blueprint' ~/.agents/skills/'rag-blueprint' && 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-blueprint' ~/.claude/skills/'rag-blueprint' (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`	52
2026-11-08	`fce3cca`	52
2026-11-07	`fce3cca`	52