NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage.
$ npx skills add NVIDIA/skills --skill rag-blueprint -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install NVIDIA/skills rag-blueprint --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/rag-blueprint .claude/skills/rag-blueprint && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "rag-blueprint" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/rag-blueprint into .claude/skills/rag-blueprint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rag-blueprint", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/NVIDIA/skills/tree/main/skills/rag-blueprintType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add NVIDIA/skills --skill rag-blueprint -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install NVIDIA/skills rag-blueprint --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/rag-blueprint .agents/skills/rag-blueprint && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "rag-blueprint" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/rag-blueprint into .agents/skills/rag-blueprint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rag-blueprint", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add NVIDIA/skills --skill rag-blueprint -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install NVIDIA/skills rag-blueprint --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/rag-blueprint .cursor/skills/rag-blueprint && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "rag-blueprint" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/rag-blueprint into .cursor/skills/rag-blueprint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rag-blueprint", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/NVIDIA/skills.git --path skills/rag-blueprint--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add NVIDIA/skills --skill rag-blueprint -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install NVIDIA/skills rag-blueprint --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/rag-blueprint .gemini/skills/rag-blueprint && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "rag-blueprint" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/rag-blueprint into .gemini/skills/rag-blueprint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rag-blueprint", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install NVIDIA/skills rag-blueprintInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add NVIDIA/skills --skill rag-blueprint -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/rag-blueprint .github/skills/rag-blueprint && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "rag-blueprint" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/rag-blueprint into .github/skills/rag-blueprint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rag-blueprint", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add NVIDIA/skills --skill rag-blueprint -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install NVIDIA/skills rag-blueprint --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/rag-blueprint .opencode/skills/rag-blueprint && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "rag-blueprint" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/rag-blueprint into .opencode/skills/rag-blueprint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rag-blueprint", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
rag-blueprintNVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage.
RAG Blueprint is an agent skill from NVIDIA/skills, published by the product's own GitHub organization. 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).
Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 41 other files, including reference files (for example `BENCHMARK.md`, `eval/h100.json` and `eval/nvidia_hosted.json`). Compatibility notes: NVIDIA RAG Blueprint repository checkout; Docker/Compose or Kubernetes/Helm for deployments; Python 3.11+ for library workflows; NVIDIA GPU tooling for…
It sits in AI & LLM Engineering, covering Retrieval-augmented generation, Summarization and Observability. It works with NVIDIA AI Platform, CUDA and Docker. The repository describes itself as: Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end. The licence is Apache-2.0.
4 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 0e0d506. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
Bash(echo *)Bash(nvidia-smi *)Bash(curl --version *)Bash(docker ps *)Bash(docker info *)Bash(docker --version *)Bash(docker version *)Bash(docker logs *)Bash(docker inspect *)Bash(docker stats *)…and 36 more on the same allowed-tools line.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
dockerkubectlcurlhelmFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use docker, kubectl, curl and helm, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
NGC_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
NVIDIA RAG Blueprint repository checkout; Docker/Compose or Kubernetes/Helm for deployments; Python 3.11+ for library workflows; NVIDIA GPU tooling for self-hosted NIM services.
From compatibility in the SKILL.md frontmatter.
RAG Blueprint loads about 2.8k tokens when it runs, and up to ~29k if it reads all its reference files. Until then it costs about 96 tokens; SKILL.md has 879 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
r) | Any | Self-hosted | `deploy/compose/.env` |ployment. Config file is `deploy/compose/.env`. Correct?"Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from NVIDIA/skills at commit 0e0d506, republished under its Apache-2.0 licence (© NVIDIA). 879 words, ~2,834 tokens.
.claude/skills/rag-blueprint/SKILL.md (or your agent's skills folder). This skill also uses 38 other files; get the full folder from GitHub.Use this skill for NVIDIA RAG Blueprint operations: deployment, configuration, troubleshooting, shutdown, and feature management across Docker, Helm, and library deployments.
Determine what the user wants and route immediately:
| User Intent | Action |
|---|---|
| Deploy, install, set up, start RAG | Read and follow references/deploy.md |
| Configure, enable, change, toggle a feature | Use the Configure section below |
| Troubleshoot, debug, fix, error, unhealthy | Read and follow references/troubleshoot.md |
| Stop, shutdown, tear down, clean up | Read and follow references/shutdown.md |
If the intent is ambiguous, infer from context (e.g., "RAG isn't working" → troubleshoot; "get RAG running" → deploy). Only ask if genuinely unclear.
Requires a running RAG deployment. If services are not running, deploy first via references/deploy.md.
Match the user's request to a reference file, then read and follow it:
| Feature Keywords | Reference |
|---|---|
| VLM, VLM embeddings, image captioning | references/configure/vlm.md |
| NeMo Guardrails | references/configure/guardrails.md |
| Agentic RAG, planning/execution agent, agentic streaming, stage events | references/configure/agentic-rag.md |
| Query rewriting, decomposition, multi-turn | references/configure/query-and-conversation.md |
| Ingestion (text-only, audio, Nemotron Parse, OCR, batch CLI, NV-Ingest, volume mount, performance) | references/configure/ingestion.md |
| Search, retrieval, hybrid search, multi-collection, metadata, filters, Elasticsearch filters, reranker, topK, accuracy/performance | references/configure/search-and-retrieval.md |
| LLM/embedding/ranking model changes, vector DB, Milvus/Elasticsearch auth, service keys, model profiles, ports/GPU | references/configure/models-and-infrastructure.md |
Reasoning, thinking mode, reasoning_content, self-reflection, prompts, generation params (tokens, temperature, citations), per-request LLM params | references/configure/reasoning-and-generation.md |
| Summarization | references/configure/summarization.md |
| Observability (tracing, Zipkin, Grafana, Prometheus) | references/configure/observability.md |
| Multimodal query (image + text) | references/configure/multimodal-query.md |
| Data catalog (collection/document metadata) | references/configure/data-catalog.md |
| User interface (UI settings, reasoning panel, metadata filters) | references/configure/user-interface.md |
| API reference (endpoints, schemas) | references/configure/api-reference.md |
| Evaluation (RAGAS metrics) | references/configure/evaluation.md (and skill rag-eval) |
| MCP server & client, agent toolkit | references/configure/mcp.md |
| Migration (version upgrades) | references/configure/migration.md |
| Notebooks (setup and catalog) | references/configure/notebooks.md |
Match the user's request to a reference file from the table above.
Detect what's running:
echo "=== NIM ===" && docker ps --format '{{.Names}}' 2>/dev/null | grep -iE '(nim-llm|nemotron-(vlm-)?embedding|nemotron-ranking|nemotron-vlm|nemotron-3-nano-omni|page-elements|graphic-elements|table-structure|nemotron-ocr)' || echo "NO_LOCAL_NIMS"; echo "=== RAG ===" && docker ps --format '{{.Names}}' 2>/dev/null | grep -iE '(rag-server|ingestor-server|elasticsearch|milvus|seaweedfs|lancedb)' || echo "NO_DOCKER_RAG"; echo "=== K8S ===" && kubectl get pods -n rag 2>/dev/null | head -5 || echo "NO_K8S"; echo "=== LIBRARY ===" && ps aux 2>/dev/null | grep -E '(nvidia_rag|uvicorn.*rag)' | grep -v grep || echo "NO_LIBRARY"Use this table to determine platform, deployment type, and where config lives:
| Local NIMs running? | RAG services running? | Deployment Type | Config Location |
|---|---|---|---|
| Yes (Docker) | Any | Self-hosted | deploy/compose/.env |
| No | Yes (Docker) | NVIDIA-hosted | deploy/compose/nvdev.env |
| Yes (K8s pods) | Any | Self-hosted | values.yaml (NIM sections) |
| No | Yes (K8s pods) | NVIDIA-hosted | values.yaml (envVars) |
| — | Library processes | Library mode | notebooks/config.yaml |
| No | No | Not running | Deploy first via references/deploy.md |
Tell the user what you detected and ask to confirm. Example: "I see local NIM containers running (nim-llm-ms, nemotron-vlm-embedding-ms) — this is a self-hosted deployment. Config file is deploy/compose/.env. Correct?"
Check current feature state before changing anything — read the config location from step 3, then cross-check the live service:
docker exec rag-server env 2>/dev/null | grep -E "<VAR_NAME>"kubectl get pod -n rag -l app=rag-server -o jsonpath='{.items[0].spec.containers[0].env}' 2>/dev/nullIf the config file and live service disagree, tell the user the service has stale config and will need a restart.
If the feature needs extra GPUs, check availability against hardware restrictions (see below):
nvidia-smi --query-gpu=index,name,memory.total,memory.used --format=csv,noheader 2>/dev/null || echo "NO_GPU"Read the reference file and apply changes:
source <env-file> && docker compose -f deploy/compose/<compose-file> up -d| Service | Compose File |
|---|---|
| rag-server | docker-compose-rag-server.yaml |
| ingestor-server | docker-compose-ingestor-server.yaml |
| Elasticsearch, Milvus, etcd, SeaweedFS | vectordb.yaml |
| NIM containers (LLM, embedding, ranking, VLM, OCR, parse, audio, extraction) | nims.yaml |
| guardrails | docker-compose-nemo-guardrails.yaml |
| observability (Grafana, Prometheus, Zipkin) | observability.yaml |
values.yaml, then upgrade: helm upgrade rag <chart> -n rag -f values.yamlnotebooks/config.yaml, then restart the Python processVerify:
docker ps --format "table {{.Names}}\t{{.Status}}" | head -20; curl -s http://localhost:8081/v1/health?check_dependencies=true 2>/dev/null | head -1kubectl get pods -n rag; kubectl rollout status deployment/rag-server -n rag --timeout=120scurl -s http://localhost:8081/v1/health 2>/dev/null | head -1If restart fails, read references/troubleshoot.md. If multiple features requested, repeat from step 1 for each.
references/deploy.md.references/configure/vlm.md.references/troubleshoot.md.references/shutdown.md.NGC_API_KEY must be supplied by the user environment.| Error / signal | What to do |
|---|---|
| Services are not running | Follow references/deploy.md before configuring features. |
| Restart or health check fails | Follow references/troubleshoot.md. |
| User requests teardown | Follow references/shutdown.md and confirm destructive cleanup. |
Run steps 2–3 above, then read the identified config file to list what's currently enabled:
grep -E "^(export )?(ENABLE_|APP_)" <config-file> 2>/dev/null | sortSummarize what's running and enabled, then ask which feature to change.
Read docs/support-matrix.md for current GPU requirements per deployment mode.
Read docs/service-port-gpu-reference.md for port mappings and GPU assignments.
| GPU | Feature Restrictions |
|---|---|
| B200 | No VLM, No Guardrails, No Nemotron Parse. May need multi-GPU LLM (LLM_MS_GPU_ID). |
| RTX PRO 6000 | No Nemotron Parse. No Audio on Helm. |
© NVIDIA, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 38 other files (references) in skills/rag-blueprint of NVIDIA/skills.
Open the folder on GitHubat commit 0e0d506
RAG Blueprint next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| RAG Blueprint this skillNVIDIA/skills | 3.5k | — | ~2.8k | Automated safety check: Notes | Apache-2.0 | |
| Vss Deploy Detection Tracking 3DNVIDIA-AI-Blueprints/video-search-and-summarization | 1.9k | — | ~5.1k | Automated safety check: Notes | Apache-2.0 | |
| Nemotron Customizer AirgapNVIDIA-NeMo/Nemotron | 2.1k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| Cv DeployLMIXR/CV_Deployment_skill | 126 | — | ~547 | Automated safety check: Pass | None | |
| Vllm Deploy Dockervllm-project/vllm-skills | 103 | — | ~2.5k | Automated safety check: Notes | Apache-2.0 | |
| Setup Workshopbrevdev/workshop-build-an-agent | 143 | — | ~2.3k | Automated safety check: Notes | Apache-2.0 |
NVIDIA-AI-Blueprints/video-search-and-summarization
A skill your agent uses when deploying or operating standalone RTVI-CV-3D / MV3DT multi-camera 3D tracking for calibrated MP4/file inputs and live RTSP streams: missing-calibration handoff to AMC…
NVIDIA-NeMo/Nemotron
Prepare, validate, build, and use Nemotron Customizer airgap image bundles for offline clusters.
LMIXR/CV_Deployment_skill
基于 helpfile 工程经验，协助 agent 配置 CV 主机和边缘设备环境、编译视觉与推理依赖、接入摄像头视频并打包部署服务。适用于 Ubuntu、CentOS、Windows、macOS、Jetson、树莓派和 RK3399 的 CV 工程实施与故障排查，以及相关移动端配套工具；模型训练和纯算法设计不属于本技能主线。
vllm-project/vllm-skills
Deploy vLLM using Docker (pre-built images or build-from-source) with NVIDIA GPU support and run the OpenAI-compatible server.
brevdev/workshop-build-an-agent
This skill should be used when the user wants to set up, install, deploy, bootstrap, or "spin up" the Build-an-Agent workshop (a.k.a.
brevdev/workshop-build-an-agent
Set up the NVIDIA "Build an Agent" DevX workshop as a working JupyterLab environment from INSIDE a locked-down OpenShell/NemoClaw sandbox, and hand the user the token URL + access commands.
NVIDIA/skills
A skill your agent uses when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice.
NVIDIA/skills
Generates, validates, compares and explains HOLOLINK_def.svh macro files for the HSB IP, using bundled Python scripts and asking before it writes anything.
NVIDIA/skills
Runs and validates an end-to-end Mission Control demo in a locally installed Isaac Sim, with a Nova Carter robot driven through a Python server.
NVIDIA/skills
Orchestrates defect image generation for PCBA, metal surface and glass inspection with NVIDIA Cosmos AnomalyGen on OSMO, from cold-start Day 0 to real-photo Day 1 labeling.
NVIDIA/skills
Orchestrates video data augmentation and auto-labeling workflows on OSMO, from flow selection and preflight checks to submission, monitoring and output download.
NVIDIA/skills
Runs NVIDIA TAO Data Services KPI analysis on object detection results, comparing predictions to ground truth and writing per-class precision, recall and AP to a CSV.
Works with
Categories
NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. RAG Blueprint is an agent skill from NVIDIA/skills, published by the product's own GitHub organization. NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage.
RAG Blueprint fits situations like: tasks that involve Retrieval-augmented generation; tasks that involve Summarization; tasks that involve Observability.
Run `npx skills add NVIDIA/skills --skill rag-blueprint -a claude-code`. Or copy the skill folder (skills/rag-blueprint in NVIDIA/skills) into .claude/skills/rag-blueprint in your project. Claude Code loads it when a task matches its description.
Run `npx skills add NVIDIA/skills --skill rag-blueprint -a codex`. Or copy the skill folder (skills/rag-blueprint in NVIDIA/skills) into .agents/skills/rag-blueprint in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NVIDIA/skills --skill rag-blueprint -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/rag-blueprint, .gemini/skills/rag-blueprint, .github/skills/rag-blueprint and .opencode/skills/rag-blueprint in your project.
Going by SKILL.md and its folder, RAG Blueprint needs the command-line tools its instructions call (docker, kubectl, curl and helm) and credentials named NGC_API_KEY. Our summary lists: Python 3; Docker; A credential in NGC_API_KEY. Its frontmatter pre-approves these tools: Bash(echo *), Bash(nvidia-smi *), Bash(curl --version *), Bash(docker ps *), Bash(docker info *), Bash(docker --version *), Bash(docker version *), Bash(docker logs *), Bash(docker inspect *), Bash(docker stats *), Bash(docker compose ps *), Bash(docker compose logs *), Bash(docker compose config *), Bash(docker compose version *), Bash(kubectl get *), Bash(kubectl describe *), Bash(kubectl version *), Bash(kubectl logs *), Bash(kubectl api-resources *), Bash(kubectl rollout status *), Bash(helm version *), Bash(helm list *), Bash(helm status *), Bash(oc get *), Bash(oc describe *), Bash(oc logs *), Bash(oc whoami *), Bash(oc version *), Bash(git rev-parse *), Bash(git describe *), Bash(git status *), Bash(python3 --version *), Bash(pip3 show *), Bash(df *), Bash(du *), Bash(cat /proc/*), Bash(cat /etc/os-release *), Bash(ss *), Bash(netstat *), Bash(ls *), Bash(grep *), Bash(lsof *), Bash(ps aux *), Read, Grep, Glob. Compatibility (from SKILL.md): NVIDIA RAG Blueprint repository checkout; Docker/Compose or Kubernetes/Helm for deployments; Python 3.11+ for library workflows; NVIDIA GPU tooling for self-hosted NIM services..
SKILL.md contains no URLs. Its commands use docker and curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
RAG Blueprint is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 26k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with RAG Blueprint: Vss Deploy Detection Tracking 3D (NVIDIA-AI-Blueprints/video-search-and-summarization, 1.9k stars), Nemotron Customizer Airgap (NVIDIA-NeMo/Nemotron, 2.1k stars), Cv Deploy (LMIXR/CV_Deployment_skill, 126 stars) and Vllm Deploy Docker (vllm-project/vllm-skills, 103 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
NVIDIA (a GitHub organization, an official publisher) maintains it in NVIDIA/skills, which has 3,534 GitHub stars. The repository holds 380 skills in this directory. The repository was last updated on October 7, 2026.
Source: NVIDIA/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
