omniverse-cad-to-simready

Each tab says whether it installs commit d7e1e2c, the one we checked, or the latest version.

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/NVIDIA/skills.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin d7e1e2c728579ad38174443ef22382d0fb4615b5 &&
  git -C "$tmp" sparse-checkout set -- skills/omniverse-cad-to-simready &&
  git -C "$tmp" checkout -q d7e1e2c728579ad38174443ef22382d0fb4615b5 &&
  mkdir -p .claude/skills &&
  mkdir .claude/skills/omniverse-cad-to-simready &&
  cp -R "$tmp"/skills/omniverse-cad-to-simready/. .claude/skills/omniverse-cad-to-simready/ &&
  rm -rf "$tmp"

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/NVIDIA/skills.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin d7e1e2c728579ad38174443ef22382d0fb4615b5 &&
  git -C "$tmp" sparse-checkout set -- skills/omniverse-cad-to-simready &&
  git -C "$tmp" checkout -q d7e1e2c728579ad38174443ef22382d0fb4615b5 &&
  out="$(mktemp -d)" &&
  cp -R "$tmp"/skills/omniverse-cad-to-simready "$out"/omniverse-cad-to-simready &&
  (cd "$out" && zip -qr - omniverse-cad-to-simready) > omniverse-cad-to-simready.zip &&
  rm -rf "$tmp" "$out"

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/NVIDIA/skills.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin d7e1e2c728579ad38174443ef22382d0fb4615b5 &&
  git -C "$tmp" sparse-checkout set -- skills/omniverse-cad-to-simready &&
  git -C "$tmp" checkout -q d7e1e2c728579ad38174443ef22382d0fb4615b5 &&
  mkdir -p .agents/skills &&
  mkdir .agents/skills/omniverse-cad-to-simready &&
  cp -R "$tmp"/skills/omniverse-cad-to-simready/. .agents/skills/omniverse-cad-to-simready/ &&
  rm -rf "$tmp"

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/NVIDIA/skills.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin d7e1e2c728579ad38174443ef22382d0fb4615b5 &&
  git -C "$tmp" sparse-checkout set -- skills/omniverse-cad-to-simready &&
  git -C "$tmp" checkout -q d7e1e2c728579ad38174443ef22382d0fb4615b5 &&
  mkdir -p .cursor/skills &&
  mkdir .cursor/skills/omniverse-cad-to-simready &&
  cp -R "$tmp"/skills/omniverse-cad-to-simready/. .cursor/skills/omniverse-cad-to-simready/ &&
  rm -rf "$tmp"

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/NVIDIA/skills.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin d7e1e2c728579ad38174443ef22382d0fb4615b5 &&
  git -C "$tmp" sparse-checkout set -- skills/omniverse-cad-to-simready &&
  git -C "$tmp" checkout -q d7e1e2c728579ad38174443ef22382d0fb4615b5 &&
  mkdir -p .github/skills &&
  mkdir .github/skills/omniverse-cad-to-simready &&
  cp -R "$tmp"/skills/omniverse-cad-to-simready/. .github/skills/omniverse-cad-to-simready/ &&
  rm -rf "$tmp"

gh skill install NVIDIA/skills skills/omniverse-cad-to-simready/SKILL.md@d7e1e2c728579ad38174443ef22382d0fb4615b5 --agent github-copilot --scope project

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/NVIDIA/skills.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin d7e1e2c728579ad38174443ef22382d0fb4615b5 &&
  git -C "$tmp" sparse-checkout set -- skills/omniverse-cad-to-simready &&
  git -C "$tmp" checkout -q d7e1e2c728579ad38174443ef22382d0fb4615b5 &&
  mkdir -p .gemini/skills &&
  mkdir .gemini/skills/omniverse-cad-to-simready &&
  cp -R "$tmp"/skills/omniverse-cad-to-simready/. .gemini/skills/omniverse-cad-to-simready/ &&
  rm -rf "$tmp"

gemini skills install https://github.com/NVIDIA/skills.git --path skills/omniverse-cad-to-simready --scope workspace

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/NVIDIA/skills.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin d7e1e2c728579ad38174443ef22382d0fb4615b5 &&
  git -C "$tmp" sparse-checkout set -- skills/omniverse-cad-to-simready &&
  git -C "$tmp" checkout -q d7e1e2c728579ad38174443ef22382d0fb4615b5 &&
  mkdir -p .agents/skills &&
  mkdir .agents/skills/omniverse-cad-to-simready &&
  cp -R "$tmp"/skills/omniverse-cad-to-simready/. .agents/skills/omniverse-cad-to-simready/ &&
  rm -rf "$tmp"

npx skills@1.7.4 add NVIDIA/skills --skill omniverse-cad-to-simready

From the files and frontmatter at commit d7e1e2c. This is how much a skill can do, not whether it is risky.

What it can touch: Shell, network or credentials

• 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.

• Bundles scripts

  The folder holds code files the agent may run.

  references/assemble-package-source/scripts/check_dependencies.py · references/content-agents/references/material-agent-client/scripts/check_dependencies.py · references/content-agents/references/physics-agent-client/scripts/check_dependencies.py and 23 more

• Pre-approves tools

  Its allowed-tools field lists tools the agent may use without asking you first, in agents that honour it.

  SKILL.md:9

• Touches credentials

  It reads, asks for or contains keys, tokens, passwords or similar secrets.

  references/convert-to-usd/references/usd-convert-cad/scripts/run.py:287 · shared/preflight_manifest.py:226

• Downloads software

  It fetches programs or packages from the internet, or from a package source other than the default.

  references/preflight/README.md:261 · references/preflight/scripts/preflight.py:209

Pattern check: 3 items to review · commit d7e1e2c · 27 Oct 2026

• R34 · HighBroad tools pre-approved in allowed-tools

  SKILL.md:9 (opens in a new tab)

  allowed-tools: Read Write Bash WebFetch Env

• R01 · HighDownload piped into a shell

  references/preflight/README.md:261 (opens in a new tab)

  `curl -LsSf https://astral.sh/uv/install.sh | sh`.

• R01 · HighDownload piped into a shell

  references/preflight/scripts/preflight.py:209 (opens in a new tab)

  UV_INSTALL_HINT = "Install uv with: curl -LsSf https://astral.sh/uv/install.sh | sh"

We checked every text file in this skill, at commit d7e1e2c on 27 Oct 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 worksReport an incorrect finding

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 specFails

  The open format from agentskills.io, held to what the strictest agents enforce, so one folder loads everywhere.

  • Error

    compatibility is 501 characters; the limit is 500. O3

    Fix: Write compatibility as plain text of 500 characters or fewer, or delete it.

  • Warning

    The frontmatter uses [ ] or { } values. Most agents accept them, but the spec's validator (skills-ref) rejects the file. F4

    Fix: Write lists as "- item" lines and maps as indented key: value lines, without anchors or tags.

  • Warning

    Fields outside the spec: version, tools and permissions. Uploads to the Claude apps and API, and the spec's validator, reject the file; most agents ignore these fields. O1

    Fix: Delete them for a portable skill, or keep them if you only target the agents that read them.

  • Warning

    metadata values should be text; tags (a list) and languages (a list) are not. The spec's validator turns them into text; other readers may not. O4

    Fix: Quote each value, for example version: "1.0".

  • Note

    Anthropic's packaging script leaves these out: evals/. F8

    Fix: Delete them, or list them in .gitignore.

  • Note

    Reference files that SKILL.md doesn't link: BENCHMARK.md, references/deploy-content-agents/references/deploy-material-agent-docker.md, references/deploy-content-agents/references/deploy-ovrtx-docker.md, references/deploy-content-agents/references/deploy-physics-agent-docker.md, references/deploy-content-agents/references/deploy-texture-agent-docker.md and 1 more. Anthropic suggests linking every reference file directly from SKILL.md. B4

    Fix: Link each one from SKILL.md and say when to read it.

  • Note

    Reference files over 100 lines with no table of contents at the top: BENCHMARK.md (115 lines), references/commands.md (109 lines) and references/workflow.md (267 lines). B5

    Fix: Add a short list of the sections at the top of each.

• 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

    Anthropic's packaging script leaves these out: evals/. F8

    Fix: Delete them, or list them in .gitignore.

  • Note

    Claude Code ignores fields it doesn't know: version, tools and permissions. O1

    Fix: Check the spelling against Claude Code's field list, or delete them.

  • Note

    compatibility is 501 characters; the limit is 500. Claude Code accepts up to 500 characters and doesn't act on the field. O3

    Fix: Write compatibility as plain text of 500 characters or fewer, or delete it.

  • Note

    Reference files that SKILL.md doesn't link: BENCHMARK.md, references/deploy-content-agents/references/deploy-material-agent-docker.md, references/deploy-content-agents/references/deploy-ovrtx-docker.md, references/deploy-content-agents/references/deploy-physics-agent-docker.md, references/deploy-content-agents/references/deploy-texture-agent-docker.md and 1 more. Anthropic suggests linking every reference file directly from SKILL.md. B4

    Fix: Link each one from SKILL.md and say when to read it.

  • Note

    Reference files over 100 lines with no table of contents at the top: BENCHMARK.md (115 lines), references/commands.md (109 lines) and references/workflow.md (267 lines). B5

    Fix: Add a short list of the sections at the top of each.

• Claude apps & API uploadFails

  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.

  • Error

    Upload and packaging fail on fields outside the spec: version, tools and permissions. O1

    Fix: Delete them, and keep your own data under metadata as text values.

  • Error

    compatibility is 501 characters; the limit is 500. Anthropic's validator rejects it. O3

    Fix: Write compatibility as plain text of 500 characters or fewer, or delete it.

  • Note

    Anthropic's packaging script leaves these out: evals/. F8

    Fix: Delete them, or list them in .gitignore.

  • Note

    The description is 422 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

    metadata values should be text; tags (a list) and languages (a list) are not. The spec defines metadata as text to text. O4

    Fix: Quote each value, for example version: "1.0".

  • Note

    Reference files that SKILL.md doesn't link: BENCHMARK.md, references/deploy-content-agents/references/deploy-material-agent-docker.md, references/deploy-content-agents/references/deploy-ovrtx-docker.md, references/deploy-content-agents/references/deploy-physics-agent-docker.md, references/deploy-content-agents/references/deploy-texture-agent-docker.md and 1 more. Anthropic suggests linking every reference file directly from SKILL.md. B4

    Fix: Link each one from SKILL.md and say when to read it.

  • Note

    Reference files over 100 lines with no table of contents at the top: BENCHMARK.md (115 lines), references/commands.md (109 lines) and references/workflow.md (267 lines). B5

    Fix: Add a short list of the sections at the top of each.

• OpenAI (Codex & API)Fails

  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.

  • Error

    compatibility is 501 characters; the limit is 500. OpenAI's upload follows the spec. O3

    Fix: Write compatibility as plain text of 500 characters or fewer, or delete it.

  • Warning

    Fields outside the spec: version, tools and permissions. Codex ignores them; OpenAI doesn't say whether its upload accepts them. O1

    Fix: Delete them, or move your own data under metadata as text values.

  • Warning

    metadata values should be text; tags (a list) and languages (a list) are not. OpenAI's upload follows the spec's text-to-text rule. O4

    Fix: Quote each value, for example version: "1.0".

  • Note

    Anthropic's packaging script leaves these out: evals/. F8

    Fix: Delete them, or list them in .gitignore.

• VS Code & CopilotPasses

  VS Code reads skills one folder below .github/skills, .claude/skills or .agents/skills and falls back to the folder name when the name is missing or differs; GitHub's Copilot docs require the exact name SKILL.md.

  • Note

    Anthropic's packaging script leaves these out: evals/. F8

    Fix: Delete them, or list them in .gitignore.

  • Note

    VS Code ignores fields it doesn't support: version, tools and permissions. O1

    Fix: Delete them unless another agent you target reads them.

  • Note

    compatibility is 501 characters; the limit is 500. O3

    Fix: Write compatibility as plain text of 500 characters or fewer, or delete it.

131 files