New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Nvwb

by brevdev in brevdev/workshop-build-an-agent

Manage NVIDIA AI Workbench projects, contexts, builds, and environments via the nvwb CLI.

Apache-2.0Auto-check passedDevelopment

Install Nvwb

skills CLI
$ npx skills add brevdev/workshop-build-an-agent --skill nvwb -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install brevdev/workshop-build-an-agent nvwb --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/brevdev/workshop-build-an-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/nvwb .claude/skills/nvwb && rm -rf skills-src

Use ~/.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/

Facts

Skill name
nvwb
GitHub stars
143
Token cost
~1.1k tokens
SKILL.md length
468 words
Files
7 (incl. references)
Skills in repo
11
Repo updated
First seen
Licence
Apache-2.0

At a glance

Manage NVIDIA AI Workbench projects, contexts, builds, and environments via the nvwb CLI.

  • Works in 6 steps: Read the build output carefully for the… → Common causes: bad package version in… → For deeper logs, check… → …
  • Wants to create
  • SKILL.md covers Core Concepts, Current State Detection, Build vs Runtime Isolation and Key Environment Variables, plus 3 more sections
  • Calls ssh

What it does

Nvwb is an agent skill from brevdev/workshop-build-an-agent. Manage NVIDIA AI Workbench projects, contexts, builds, and environments via the nvwb CLI. This skill should be used when the user wants to create, clone, build, manage, or configure AI Workbench projects, contexts, or environments.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `references/cli-reference.md`, `references/codex-in-container.md` and `references/nvwb-brev.md`).

It sits in Development. It works with NVIDIA AI Platform and Git. The licence is Apache-2.0.

When your agent uses it

  • Wants to create
  • Configure AI Workbench projects

Example prompts

  • “/nvwb”

Requirements

  • Docker

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Read the build output carefully for the error message
  2. Common causes: bad package version in requirements.txt, missing apt dependency, bash syntax error in build scripts
  3. For deeper logs, check project-runtime-info/ inside the context's workbench directory — this is on the machine running the Workbench…
  4. Fix the relevant config file
  5. Run nvwb build again
  6. For persistent issues, try nvwb build --full-build for a clean rebuild

What it can do on your machine

Read from SKILL.md and the folder at commit b5689a7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • ssh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use ssh, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Nvwb loads about 1.1k tokens when it runs, and up to ~13k if it reads all its reference files. Until then it costs about 59 tokens; SKILL.md has 468 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~13k

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.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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.

SKILL.md

The full file from brevdev/workshop-build-an-agent at commit b5689a7, republished under its Apache-2.0 licence (© brevdev). 468 words, ~1,115 tokens.

Download SKILL.mdSave it as .claude/skills/nvwb/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
nvwb
description
Manage NVIDIA AI Workbench projects, contexts, builds, and environments via the nvwb CLI. This skill should be used when the user wants to create, clone, build, manage, or configure AI Workbench projects, contexts, or environments.
disable-model-invocation
false
user-invocable
true

NVIDIA AI Workbench — Local Machine (Control Plane)

NVIDIA AI Workbench is a lightweight, containerized development platform for GPU-accelerated AI/ML workflows. Every project is a Git repo with a .project/spec.yaml that defines the container environment. It supports Docker and Podman as container runtimes.

The nvwb CLI always runs on the local machine — the user's laptop or desktop. From there it manages contexts, which may be local (container on the same machine) or remote (container on a server or cloud instance accessed via SSH). Codex using this skill is on the local machine.

The user wants help with: $ARGUMENTS

Core Concepts

  • Contexts — Locations/machines where projects run (local, remote SSH, Brev cloud)
  • Projects — Git repos with container configuration (.project/spec.yaml)
  • Applications — Services inside the container (JupyterLab, VS Code, custom webapps/processes)
  • Environment Variables — Runtime values set via CLI; sensitive ones (--is-sensitive) are masked in output. Values are never committed to Git. Projects may declare required secret variable names in spec.yaml under execution.secrets.

Current State Detection

Before taking action, check the current state:

bash
nvwb list contexts        # What locations are configured?
nvwb status               # Is a project open? Is the container running?
nvwb list projects        # What projects exist in the active context?

Build vs Runtime Isolation

Build-time (changes require nvwb build):

  • apt.txt — system packages
  • requirements.txt — pip packages
  • preBuild.bash / postBuild.bash — custom build scripts
  • Package manager entries in spec.yaml

Runtime (changes require container restart: nvwb close + nvwb open):

  • variables.env — environment variables
  • Mount configuration changes
  • App definitions in spec.yaml

No action needed:

  • Code in layout directories (code/, data/, models/) — live-mounted at /project/

Key Environment Variables

VariableAvailableDescription
$NVWB_UIDBuild-timeUser ID for file ownership in build scripts
$NVWB_GIDBuild-timeGroup ID for file ownership in build scripts
$PROXY_PREFIXRuntimeURL prefix for proxied web apps
Show full SKILL.md (218 more words)Show less

Error Handling

When a build fails:

  1. Read the build output carefully for the error message
  2. Common causes: bad package version in requirements.txt, missing apt dependency, bash syntax error in build scripts
  3. For deeper logs, check project-runtime-info/ inside the context's workbench directory — this is on the machine running the Workbench service, not necessarily the local machine. Find the right path first:
    bash
    cat ~/.nvwb/contexts.json   # workbenchDir field for each context
    • Local context: ~/.nvwb/project-runtime-info/
    • Remote context (SSH or Brev): <workbenchDir>/project-runtime-info/ on the remote — access via ssh <context-name> "ls <workbenchDir>/project-runtime-info/"
  4. Fix the relevant config file
  5. Run nvwb build again
  6. For persistent issues, try nvwb build --full-build for a clean rebuild

When to Rebuild vs Restart vs Do Nothing

ChangeAction
Edit code filesNothing
Edit apt.txt, requirements.txt, build scriptsnvwb build
Edit variables.envnvwb close then nvwb open
Change mounts or app config in spec.yamlnvwb close then nvwb open
Change compose servicesnvwb compose down then nvwb compose up

References

See the reference files for detailed information:

  • references/cli-reference.md — Complete CLI command reference
  • references/spec-reference.md — spec.yaml structure and fields
  • references/project-structure.md — Project file layout and roles
  • references/workflows.md — Multi-step workflow recipes
  • references/nvwb-brev.md — Brev cloud GPU integration: stoppability, interactive vs manual bootstrap, org management, Brev CLI reference
  • references/codex-in-container.md — Running Codex inside the container, credential persistence, and the host↔container bridge pattern

© brevdev, 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

Files

SKILL.md and 6 other files (references) in .agents/skills/nvwb of brevdev/workshop-build-an-agent.

  • SKILL.md
  • references/cli-reference.md
  • references/codex-in-container.md
  • references/nvwb-brev.md
  • references/project-structure.md
  • references/spec-reference.md
  • references/workflows.md

Open the folder on GitHubat commit b5689a7

Compare with similar skills

Nvwb 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.

Nvwb compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Nvwb this skillbrevdev/workshop-build-an-agent143—~1.1kAutomated safety check: PassApache-2.0
Backend Gap ReportAMD-AGI/Primus130—~3.4kAutomated safety check: PassCustom licence
Respond To IssueNVIDIA/Megatron-LM18k—~913Automated safety check: PassCustom licence
Jetson Promote ImageNVIDIA/skills3.5k—~5kAutomated safety check: NotesApache-2.0
Finishing a Development Branchobra/superpowers296k5 repos~1.9kAutomated safety check: PassMIT
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Backend Gap Report

    AMD-AGI/Primus

    Compare a Primus backend against an upstream repository or reference, verify git state, dependencies, directory changes, and integration coupling, then generate comparison reports, dashboard…

    130 GitHub stars~3.4k tokensUpdated today
    DevelopmentAuto-check passed

  • Respond To Issue

    NVIDIA/Megatron-LM

    Official

    Research and draft a response to a GitHub issue or question from an external contributor.

    18k GitHub stars~913 tokensUpdated today
    DevelopmentAuto-check passed

  • Jetson Promote Image

    NVIDIA/skills

    Official

    A skill your agent uses to promote overlay files and built artifacts into the staged BSP image.

    3.5k GitHub stars~5k tokensUpdated today
    AI & LLM EngineeringAuto-check: notes

  • Finishing a Development Branch

    obra/superpowers

    Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    296k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed

  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed

  • Codebase Knowledge Graph Q&A

    Egonex-AI/Understand-Anything

    Answers questions about a codebase by searching a prebuilt knowledge graph of its files, functions, classes and dependencies, not by rereading every source file.

    85k GitHub starsUsed in 1 repo~1.2k tokens
    DevelopmentAuto-check passed

More from brevdev/workshop-build-an-agent

All 11 skills in this repo

  • Setup Workshop

    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.

    143 GitHub stars~2.3k tokensUpdated today
    Auto-check: notes

  • Setup Workshop Nemoclaw

    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.

    143 GitHub stars~5.2k tokensUpdated today
    Auto-check passed

  • Module 1

    brevdev/workshop-build-an-agent

    This skill should be used when a learner is working through Module 1 ("Build an Agent") of the Build-an-Agent workshop and wants help understanding the concepts, notebooks, or code — e.g.

    143 GitHub stars~2.7k tokensUpdated today
    Auto-check passed

  • Module 1

    brevdev/workshop-build-an-agent

    This skill should be used when a learner is working through Module 1 ("Build an Agent") of the Build-an-Agent workshop and wants help understanding the concepts, notebooks, or code — e.g.

    143 GitHub stars~2.7k tokensUpdated today
    Auto-check passed

  • Workshop

    brevdev/workshop-build-an-agent

    This skill should be used when a learner wants to navigate or understand the Build-an-Agent workshop as a whole — e.g.

    143 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Workshop

    brevdev/workshop-build-an-agent

    This skill should be used when a learner wants to navigate or understand the Build-an-Agent workshop as a whole — e.g.

    143 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Nvwb

What does Nvwb do?

Manage NVIDIA AI Workbench projects, contexts, builds, and environments via the nvwb CLI. Nvwb is an agent skill from brevdev/workshop-build-an-agent. Manage NVIDIA AI Workbench projects, contexts, builds, and environments via the nvwb CLI.

When should I use Nvwb?

Nvwb fits situations like: wants to create; configure AI Workbench projects.

How do I install Nvwb in Claude Code?

Run `npx skills add brevdev/workshop-build-an-agent --skill nvwb -a claude-code`. Or copy the skill folder (.agents/skills/nvwb in brevdev/workshop-build-an-agent) into .claude/skills/nvwb in your project. Claude Code loads it when a task matches its description.

How do I install Nvwb in Codex?

Run `npx skills add brevdev/workshop-build-an-agent --skill nvwb -a codex`. Or copy the skill folder (.agents/skills/nvwb in brevdev/workshop-build-an-agent) into .agents/skills/nvwb in your project. Codex loads it when a task matches its description.

Can I use Nvwb in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add brevdev/workshop-build-an-agent --skill nvwb -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nvwb, .gemini/skills/nvwb, .github/skills/nvwb and .opencode/skills/nvwb in your project.

What does Nvwb need to run?

Going by SKILL.md and its folder, Nvwb needs the command-line tools its instructions call (ssh). Our summary lists: Docker.

Does Nvwb access the network?

SKILL.md contains no URLs. Its commands use ssh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Nvwb safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Nvwb use?

Nvwb is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Nvwb use?

About 1.1k tokens (SKILL.md is roughly 4.5k 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 12k tokens, read only when the agent opens those files.

What are the alternatives to Nvwb?

Skills that share tags, products or a category with Nvwb: Backend Gap Report (AMD-AGI/Primus, 130 stars), Respond To Issue (NVIDIA/Megatron-LM, 18k stars), Jetson Promote Image (NVIDIA/skills, 3.5k stars) and Finishing a Development Branch (obra/superpowers, 296k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Nvwb?

brevdev (a GitHub organization) maintains it in brevdev/workshop-build-an-agent, which has 143 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 6, 2026.

Source: brevdev/workshop-build-an-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.