openshell-cli

NVIDIA/OpenShell AI & ML engineering

openshell-cli is a skill in NVIDIA/OpenShell, last changed 30 Oct 2026. It can touch credentials, run shell commands, reach the network and name web addresses — read the findings before installing.

From the author

Guide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration and refresh, profile management, policy iteration, settings, service exposure, BYOC workflows, and attached-provider inference. Covers basic through advanced multi-step workflows. Trigger keywords - openshell, sandbox create, sandbox exec, sandbox connect, logs, provider create, profile list, profile describe, provider refresh, policy set, policy get, settings, service expose, forward, port forward, BYOC, bring your own container, inference, use openshell, run openshell, CLI usage, manage sandbox, manage provider, gateway add, gateway select.

How much a skill can do, not whether it is risky.

Pattern check

Nothing flagged

That isn't proof the skill is harmless.

Commit 42671c2 · 1 Nov 2026

How the check works

Pattern check: nothing flagged

That isn't proof the skill is harmless.

Install

Each tab says whether it installs commit 42671c2, the one we checked, or the latest version.

OpenCode also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Goose also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Windsurf (Devin Desktop) also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Zed also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Roo Code also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Factory Droid also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Junie also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Amp also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

No install command here reaches Kiro. Copy the skill's folder into .kiro/skills/ in your project, or ~/.kiro/skills/ for all your projects. NVIDIA/OpenShell/skills/openshell-cli (opens in a new tab)

Antigravity also looks in .agents/skills/, so the Any agent steps reach it with This project. For All projects, see where Antigravity looks.

Cline also looks in .claude/skills/, so the Claude Code steps reach it with This project. For All projects, see where Cline looks.

No tab for your agent? Use Any agent for OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie and Amp. With This project, Any agent also reaches Antigravity and Claude Code reaches Cline. Kiro needs the folder copied by hand.

Pinned to commit 42671c2, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/NVIDIA/OpenShell.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 42671c2dd2c02b744850e0bda72b99d5509969c1 &&git -C "$tmp" sparse-checkout set -- skills/openshell-cli &&git -C "$tmp" checkout -q 42671c2dd2c02b744850e0bda72b99d5509969c1 &&mkdir -p .claude/skills &&mkdir .claude/skills/openshell-cli &&cp -R "$tmp"/skills/openshell-cli/. .claude/skills/openshell-cli/ &&rm -rf "$tmp"

If Claude Code was already running and this created the skills folder, run /reload-skills.

Claude Code docs

Pinned to commit 42671c2, the one we checked.

Skills in the Claude apps belong to your account rather than to a project.

Make openshell-cli.zip, with the skill folder at the top level:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/NVIDIA/OpenShell.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 42671c2dd2c02b744850e0bda72b99d5509969c1 &&git -C "$tmp" sparse-checkout set -- skills/openshell-cli &&git -C "$tmp" checkout -q 42671c2dd2c02b744850e0bda72b99d5509969c1 &&out="$(mktemp -d)" &&cp -R "$tmp"/skills/openshell-cli "$out"/openshell-cli &&(cd "$out" && zip -qr - openshell-cli) > openshell-cli.zip &&rm -rf "$tmp" "$out"

In Claude, open Customize > Skills, select +, then + Create skill > Upload a skill, and choose openshell-cli.zip.

On Free, Pro and Max plans, turn on Code execution and file creation (Create and edit files in newer settings) under Settings > Capabilities.

Claude apps docs

Pinned to commit 42671c2, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/NVIDIA/OpenShell.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 42671c2dd2c02b744850e0bda72b99d5509969c1 &&git -C "$tmp" sparse-checkout set -- skills/openshell-cli &&git -C "$tmp" checkout -q 42671c2dd2c02b744850e0bda72b99d5509969c1 &&mkdir -p .agents/skills &&mkdir .agents/skills/openshell-cli &&cp -R "$tmp"/skills/openshell-cli/. .agents/skills/openshell-cli/ &&rm -rf "$tmp"

Codex picks up new skills on its own; restart it if this one does not appear.

Codex docs

Pinned to commit 42671c2, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/NVIDIA/OpenShell.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 42671c2dd2c02b744850e0bda72b99d5509969c1 &&git -C "$tmp" sparse-checkout set -- skills/openshell-cli &&git -C "$tmp" checkout -q 42671c2dd2c02b744850e0bda72b99d5509969c1 &&mkdir -p .cursor/skills &&mkdir .cursor/skills/openshell-cli &&cp -R "$tmp"/skills/openshell-cli/. .cursor/skills/openshell-cli/ &&rm -rf "$tmp"

Cursor docs

Pinned to commit 42671c2, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/NVIDIA/OpenShell.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 42671c2dd2c02b744850e0bda72b99d5509969c1 &&git -C "$tmp" sparse-checkout set -- skills/openshell-cli &&git -C "$tmp" checkout -q 42671c2dd2c02b744850e0bda72b99d5509969c1 &&mkdir -p .github/skills &&mkdir .github/skills/openshell-cli &&cp -R "$tmp"/skills/openshell-cli/. .github/skills/openshell-cli/ &&rm -rf "$tmp"

In a running Copilot CLI session, run /skills reload.

Or install it with gh skill, which also installs the commit we checked. Needs GitHub CLI 2.90 or later.

gh skill install NVIDIA/OpenShell skills/openshell-cli/SKILL.md@42671c2dd2c02b744850e0bda72b99d5509969c1 --agent github-copilot --scope project

Copilot & VS Code docs

Pinned to commit 42671c2, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/NVIDIA/OpenShell.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 42671c2dd2c02b744850e0bda72b99d5509969c1 &&git -C "$tmp" sparse-checkout set -- skills/openshell-cli &&git -C "$tmp" checkout -q 42671c2dd2c02b744850e0bda72b99d5509969c1 &&mkdir -p .gemini/skills &&mkdir .gemini/skills/openshell-cli &&cp -R "$tmp"/skills/openshell-cli/. .gemini/skills/openshell-cli/ &&rm -rf "$tmp"

In a running session, run /skills reload.

Or use Gemini CLI’s own installer. Installs the latest version, not the one we checked.

gemini skills install https://github.com/NVIDIA/OpenShell.git --path skills/openshell-cli --scope workspace

Gemini CLI docs

Pinned to commit 42671c2, the one we checked.

OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie, Amp and Antigravity read .agents/skills in a project.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/NVIDIA/OpenShell.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 42671c2dd2c02b744850e0bda72b99d5509969c1 &&git -C "$tmp" sparse-checkout set -- skills/openshell-cli &&git -C "$tmp" checkout -q 42671c2dd2c02b744850e0bda72b99d5509969c1 &&mkdir -p .agents/skills &&mkdir .agents/skills/openshell-cli &&cp -R "$tmp"/skills/openshell-cli/. .agents/skills/openshell-cli/ &&rm -rf "$tmp"

Or use the skills CLI from skills.sh. Installs the latest version, not the one we checked. The skills CLI reports installs to skills.sh unless you set DISABLE_TELEMETRY=1.

npx skills@1.7.4 add NVIDIA/OpenShell --skill openshell-cli

Agent Skills docs

Read SKILL.md first

Apache 2.0

Licence

20.9k

Repo stars

Folder last changed

Publisher

Files

Checked

1 Nov 2026

What it can touch

From the files and frontmatter at commit 42671c2. This is how much a skill can do, not whether it is risky.

Touches credentials
It reads, asks for or contains keys, tokens, passwords or similar secrets.
SKILL.md:410 (opens in a new tab)
Runs shell commands
Its instructions or files give the agent commands to run on your computer.
Reaches the network
It sends or fetches data over the internet, for example with curl, an HTTP library or a package install.
Names web addresses
It mentions outside web addresses the agent may visit. We list them but don't follow them.
Outside links we did not follow

Pattern check

Pattern check: nothing flagged · commit 42671c2 · 1 Nov 2026

We checked every text file in this skill, at commit 42671c2 on 1 Nov 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check works Report an incorrect finding

Outside links we did not follow

https://docs.nvidia.com/openshell/latest/about/installation.md
https://docs.nvidia.com/openshell/latest/how-it-works/gateways/overview
https://docs.nvidia.com/openshell/latest/how-it-works/sandboxes/overview
https://docs.nvidia.com/openshell/latest/how-it-works/providers/overview
https://docs.nvidia.com/openshell/latest/how-it-works/providers/profiles
https://docs.nvidia.com/openshell/latest/how-it-works/policies/overview
https://docs.nvidia.com/openshell/latest/how-it-works/inference
https://docs.nvidia.com/openshell/latest/how-it-works/sandboxes/overview.md
https://docs.nvidia.com/openshell/latest/kubernetes/high-availability#activate-sandbox-updates
https://docs.nvidia.com/openshell/latest/how-it-works/sandboxes/overview#update-the-image-of-a-stopped-sandbox

Show 2 more

https://docs.nvidia.com/openshell/latest/sdk/api-errors
https://docs.nvidia.com/openshell/latest/observability/ocsf-json-export

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

Agent Skills specPasses with warnings
The open format from agentskills.io, held to what the strictest agents enforce, so one folder loads everywhere.
- Warning
  The body is 1068 lines; the spec suggests under 500. B1
  Fix: Move detailed sections into reference files and link to them from SKILL.md.
- Warning
  The body is about 14,119 tokens (approx.); the spec suggests under 5,000. B2
  Fix: Move detail into reference files that the agent reads only when needed.
- Note
  The first sentence of the description is 253 characters. Agents shorten long descriptions, so lead with the main job. D8
  Fix: Start with one short sentence that names the job.
- Note
  There is no license field, so readers can't tell whether they may reuse the skill. O2
  Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.
Claude CodePasses
Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.
- Note
  The first sentence of the description is 253 characters. Agents shorten long descriptions, so lead with the main job. D8
  Fix: Start with one short sentence that names the job.
- Note
  The body is 1068 lines; the spec suggests under 500. Claude Code's docs say the same. B1
  Fix: Move detailed sections into reference files and link to them from SKILL.md.
- Note
  The body is about 14,119 tokens (approx.); the spec suggests under 5,000. After compaction Claude Code keeps only the first 5,000 tokens of a skill. B2
  Fix: Move detail into reference files that the agent reads only when needed.
Claude apps & API uploadPasses
Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.
- Note
  The description is 674 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4
  Fix: If the claude.ai upload refuses it, trim the description to 200 characters.
- Note
  The body is 1068 lines; the spec suggests under 500. Anthropic's guidance says the same. B1
  Fix: Move detailed sections into reference files and link to them from SKILL.md.
- Note
  The body is about 14,119 tokens (approx.); the spec suggests under 5,000. Anthropic's guidance says the same. B2
  Fix: Move detail into reference files that the agent reads only when needed.
OpenAI (Codex & API)Passes
Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.
- Note
  The first sentence of the description is 253 characters. Agents shorten long descriptions, so lead with the main job. D8
  Fix: Start with one short sentence that names the job.
VS Code & CopilotPasses

SKILL.md

Read SKILL.md on GitHub

Files

1 file

Path	Size
SKILL.md (opens in a new tab)	56 KB

More from NVIDIA/OpenShell

Skill	What it can touch	Pattern check	Licence	Updated
debug-inferenceDebug inference clients that use an attached provider and its native endpoint, including hosted APIs and host-local Ollama, vLLM, SGLang, TRT-LLM, LM Studio, or NIM. Use for provider attachment, endpoint policy, credential substitution, topology, and migration from the removed managed inference endpoint. Trigger keywords - debug inference, managed inference endpoint, local inference, ollama, lm studio, vllm, sglang, trtllm, NIM, inference failing, model server unreachable, credential_endpoint_mismatch, host.openshell.internal. Runs shell commands +1 more Pattern check: Nothing flaggedApache 2.0Updated 25 Sept 2026	Runs shell commands Names web addresses	Pattern check: Nothing flagged	Apache 2.0	25 Sept 2026
gator-gateValidate and monitor OpenShell GitHub issues and PRs using the gator:* state machine. Use when asked to triage issues/PRs for project validity, gate PRs, run gator, validate submissions, or monitor PRs toward merge readiness. Runs shell commands +2 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Runs shell commands Reaches the network +1 more	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
generate-sandbox-policyGenerate sandbox security policies from plain-language requirements and optional REST API documentation. Produces L4 or fine-grained L7 network policies and ordered network middleware configuration. Use for API access rules, middleware host selection, failure behavior, or built-in and operator-run middleware attachment. Trigger keywords - generate policy, create policy, update policy, change policy, sandbox policy, network policy, API policy, security policy, allow API, restrict API, network middleware, supervisor middleware. Reaches the network +1 more Pattern check: Nothing flaggedApache 2.0Updated 26 Oct 2026	Reaches the network Names web addresses	Pattern check: Nothing flagged	Apache 2.0	26 Oct 2026
openshell-policy-advisorUse when an OpenShell sandbox returns policy_denied, mentions policy.local, or needs a narrow network policy proposal. Names web addresses Pattern check: Nothing flaggedApache 2.0Updated 15 Jun 2026	Names web addresses	Pattern check: Nothing flagged	Apache 2.0	15 Jun 2026

Other AI & ML engineering skills

Same category, most repo stars first.

Skill	What it can touch	Pattern check	Licence	Updated
agent-architecture-auditFull-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack. affaan-m/ECC Runs shell commands Pattern check: Nothing flaggedMITUpdated 11 Aug 2026	Runs shell commands	Pattern check: Nothing flagged	MIT	11 Aug 2026
agent-evalHead-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression. affaan-m/ECC Runs shell commands +1 more Pattern check: Nothing flaggedMITUpdated 11 Aug 2026	Runs shell commands Names web addresses	Pattern check: Nothing flagged	MIT	11 Aug 2026
claude-apiReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-`, `us.anthropic.`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai\|langchain_openai\|google.generativeai\|genai\|mistralai\|cohere\|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). anthropics/skills Touches credentials +6 more Pattern check: 1 item to reviewApache 2.0Updated 9 Oct 2026	Touches credentials Downloads software +5 more	Pattern check: 1 item to review	Apache 2.0	9 Oct 2026
mcp-builderGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). anthropics/skills Touches credentials +4 more Pattern check: Nothing flaggedApache 2.0Updated 28 Oct 2026	Touches credentials Runs shell commands +3 more	Pattern check: Nothing flagged	Apache 2.0	28 Oct 2026
benchmark-modelsCross-model benchmark for gstack skills. (gstack) garrytan/gstack Touches credentials +2 more Pattern check: 1 item to reviewMITUpdated 30 Oct 2026	Touches credentials Runs shell commands +1 more	Pattern check: 1 item to review	MIT	30 Oct 2026
eval-planPreregister a paid eval (bars, arms, decoys, stop rules), dry-run it at zero cost, then run a three-item priced pilot whose spend table gates approval. (gstack) garrytan/gstack Runs shell commands +1 more Pattern check: 1 item to reviewMITUpdated 1 Nov 2026	Runs shell commands Pre-approves tools	Pattern check: 1 item to review	MIT	1 Nov 2026

At a glance

What it can touch

Pattern check

Install

Claude Code

Claude apps

Codex

Cursor

Copilot & VS Code

Gemini CLI

Any agent

What it can touch

Pattern check

Outside links we did not follow

Format check

SKILL.md

Files

More from NVIDIA/OpenShell

Other AI & ML engineering skills