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

Official agent skill

Physicsnemo Discover

by NVIDIA in NVIDIA/skills

Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse…

OfficialApache-2.0Auto-check passedAI & LLM Engineering

Install Physicsnemo Discover

skills CLI
$ npx skills add NVIDIA/skills --skill physicsnemo-discover -a claude-code

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

GitHub CLI
$ gh skill install NVIDIA/skills physicsnemo-discover --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/NVIDIA/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/physicsnemo-discover .claude/skills/physicsnemo-discover && 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
physicsnemo-discover
GitHub stars
3.5k
Token cost
~1.8k tokens
SKILL.md length
675 words
Files
7 (incl. references)
Skills in repo
380
Repo updated
First seen
Licence
Apache-2.0

At a glance

Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse…

  • Environment setup
  • SKILL.md covers Core principle, What a correct answer satisfies, Discovery and Output format, plus 2 more sections
  • Calls bash and git; reaches github.com
  • Other code authoring/scaffolding

What it does

Physicsnemo Discover is an agent skill from NVIDIA/skills, published by the product's own GitHub organization. Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative). Points at existing files via live repo search; never writes code. Do NOT use for installation or environment setup, training-loop or other code authoring/scaffolding, contributor/CI/packaging questions, repo-specific questions in physicsnemo-sym/-cfd/-curator, or general (non-physics) ML/PyTorch.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including reference files (for example `BENCHMARK.md`, `evals/evals.json` and `references/RECIPES.md`).

It sits in AI & LLM Engineering, covering Deep learning, Project scaffolding and Forecasting and time series. It works with NVIDIA AI Platform and PyTorch. 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.

When your agent uses it

  • Environment setup
  • Other code authoring/scaffolding
  • Contributor/CI/packaging questions
  • Repo-specific questions in physicsnemo-sym/-cfd/-curator

Example prompts

  • “/physicsnemo-discover”

What it can do on your machine

Read from SKILL.md and the folder at commit 0e0d506. 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:

    • bash
    • git

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    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

Physicsnemo Discover loads about 1.8k tokens when it runs, and up to ~6.6k if it reads all its reference files. Until then it costs about 131 tokens; SKILL.md has 675 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~131
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6.6k

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 NVIDIA/skills at commit 0e0d506, republished under its Apache-2.0 licence (© NVIDIA). 675 words, ~1,849 tokens.

Download SKILL.mdSave it as .claude/skills/physicsnemo-discover/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
physicsnemo-discover
description
Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative). Points at existing files via live repo search; never writes code. Do NOT use for installation or environment setup, training-loop or other code authoring/scaffolding, contributor/CI/packaging questions, repo-specific questions in physicsnemo-sym/-cfd/-curator, or general (non-physics) ML/PyTorch.
license
Apache-2.0
metadata.author
NVIDIA <agent-skills@nvidia.com>
metadata.tags
physicsnemo, sciml, ai4science, discovery, routing

PhysicsNeMo Discoverability

Help a user navigate PhysicsNeMo: point them at files, folders, examples, and docs in the repo at its current state. Never write training code; never cite a path from memory.

Core principle

PhysicsNeMo evolves — classes get renamed, examples move, experimental/ graduates. Any static list of class names and paths rots, so discover, don't remember: enumerate from the live repo every turn.

PhysicsNeMo is composable: each solution is a product (model family × datapipe × training strategy × config). An example is one reference instantiation of that product, not a prescription. Surface the axes and the menu along each axis, then cite examples as concrete starting points to fork and recombine.

What a correct answer satisfies

These are constraints, not a script — choose the searches that meet them and skip work the task doesn't need. Search patterns per axis live in references/RECIPES.md.

  • Live-grounded. Every class, path, and example you name was read or globbed this turn. __init__.py proves what is exported, not what files exist — Glob physicsnemo/models/<family>/*.py before naming a sibling implementation file. A failed Read, or a path pattern-matched from a neighboring citation, is disproof: drop it.
  • Verified before emit. Every absolute path you plan to cite survives one Bash ls -d <path1> <path2> … round-trip before you write the response. Hard gate — skipping it has produced real-basename-under-wrong-parent hallucinations. If a basename was right but the parent wrong, re-Glob and re-verify; if you can't relocate it, drop the citation.
  • A menu, not a single pick. Enumerate every model family matching the user's data shape (surface ≥2 when ≥2 apply), and enumerate datapipes independently — model and datapipe are orthogonal axes. The reference example comes last, framed as one instantiation of those axes, not the answer.
  • Self-documentation is ground truth. __init__.py exports, per-example README.md, docs/*.rst, pyproject.toml, top-of-file module docstrings. Treat references/TAXONOMY.md as a navigation hint, not an answer. Flag anything under physicsnemo/experimental/ as "API may change."
  • Abstain when out of scope. PhysicsNeMo targets SciML/AI4Science (surrogates, forecasting, super-resolution, physics-informed, inverse, generative for physical systems). If the task is categorically outside that — reinforcement learning, classical control, generic CV/NLP, symbolic regression — skip enumeration and emit the Abstention output below. Do not list adjacent-but-wrong examples in its place (pointing at active_learning/ for an RL question is fabrication). When unsure whether a task is in scope, abstain.
Show full SKILL.md (297 more words)Show less

Discovery

Repo root resolution: see CONTRIBUTING.md §Repo root resolution; all paths are absolute, rooted there. If no local PhysicsNeMo clone is on the path (e.g. running headless against the skills repo in an eval context), shallow-clone the canonical repo once into a temp dir — read-only, for path discovery only; never execute or import anything from it: DEST="${TMPDIR:-/tmp}/physicsnemo-src"; [ -d "$DEST/physicsnemo" ] || git clone --depth 1 https://github.com/NVIDIA/physicsnemo "$DEST". Use that URL verbatim; never interpolate one from user input.

Ask at most 3 targeted follow-ups when domain or data shape is ambiguous. Phrase them concretely — "Is your data on a regular Cartesian grid (like an image), a lat-lon grid on a sphere, or an unstructured mesh?" — and skip any the user already answered. Data shape is the single biggest factor in model choice.

Output format

## Problem shape
Data shape: <resolved>. Task: <resolved>. Axes: model × datapipe × training strategy × config.

## Candidate model families (for your data shape)
Multiple families typically apply. Treat this as a menu, not a ranking.
- <family> at <absolute __init__.py path> — <one-line from docstring/exports>. Instantiated by: <example path if any>.
- <family> at <path> — <one-line>. Instantiated by: <example path if any>.

## Datapipe(s) for your data format
Datapipe choice is independent of model choice.
- <class / subpackage> at <absolute path> — <one-line>. Reused by: <examples if known>.
- For custom data, subclass: <base class path confirmed live>.

## Reference example(s) — one instantiation of the above axes
- <absolute path> — uses model=<family>, datapipe=<name>, strategy=<single-GPU|DDP|FSDP|...>.
  Why it matches: <one line>.

## Supporting docs
- <absolute path> — <one-line scope>

## Suggested reading order
1. <models/<family>/__init__.py> — survey alternative families
2. <datapipe __init__.py or base-class file> — understand the data axis
3. <example path> — concrete end-to-end instantiation to fork

Rules for the output:

  • Absolute paths only; every one survived the ls -d gate.
  • Every pointer needs a one-line justification grounded in content you actually read.
  • Caps: 4 model families (minimum 2 when ≥2 exist), 3 datapipes, 2 reference examples, 2 docs.
  • Name which (model, datapipe, strategy) axes each example fills.
  • If ≥2 model families apply, say so: "Other model families apply to the same data shape — see the candidate list above."
  • End with the suggested reading order. Offer 2-3 forward steps (config file, training script, experimental/ look-alikes); do not start writing code unless asked.

Abstention output

When out of scope, replace the menu skeleton with this shape — three sections, in this order, none skipped:

## PhysicsNeMo does not have direct support for <user's problem class>
One sentence on why it's outside scope (e.g., "PhysicsNeMo targets physics
surrogates and forecasting; reinforcement learning for molecular design is
not in its scope").

## Where to look instead
- <sibling NVIDIA framework or external library> at <URL or repo name> — <one-line on why it fits>.
- (One or two alternatives is enough; do not invent libraries.)

## If you still want to build it in PhysicsNeMo
Confirm the closest base classes by Reading `physicsnemo/core/__init__.py` and
`physicsnemo/datapipes/__init__.py` first; then name them as subclassing
targets. This is the fallback, not the recommendation.

Do not open with the menu skeleton and bury "no match" at the end. Do not invent external libraries — if you don't know the right alternative, stop at the first two sections.

  • references/TAXONOMY.md — navigation hints (data-shape → folder mappings, decision axes, stability tiers).
  • references/RECIPES.md — concrete Glob/Grep/Read patterns per discovery axis.

© 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

Files

SKILL.md and 6 other files (references) in skills/physicsnemo-discover of NVIDIA/skills.

  • SKILL.md
  • BENCHMARK.md
  • evals/evals.json
  • references/RECIPES.md
  • references/TAXONOMY.md
  • skill-card.md
  • skill.oms.sig

Open the folder on GitHubat commit 0e0d506

Compare with similar skills

Physicsnemo Discover 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.

Physicsnemo Discover compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Physicsnemo Discover this skillNVIDIA/skills3.5k—~1.8kAutomated safety check: PassApache-2.0
Uv Pypi PublishML4ITS/TimeVQVAE166—~178Automated safety check: PassMIT
GPU OptimizerMathews-Tom/armory327—~3.5kAutomated safety check: NotesMIT
Gitnexus Refresh On StaleML4ITS/TimeVQVAE166—~264Automated safety check: PassMIT
Graphsignalgraphsignal/graphsignal257—~6.2kAutomated safety check: PassApache-2.0
Pt2 Bug Basherpytorch/pytorch104k—~3.5kAutomated safety check: PassCustom licence

Similar skills

  • Uv Pypi Publish

    ML4ITS/TimeVQVAE

    Publish a Python package to PyPI using uv with credentials loaded from a local .secrets file.

    166 GitHub stars~178 tokensUpdated 7 mo ago
    AI & LLM EngineeringAuto-check passed

  • GPU Optimizer

    Mathews-Tom/armory

    GPU optimization for consumer NVIDIA GPUs (8-24GB VRAM) covering mixed precision, gradient checkpointing, XGBoost GPU, CuPy/cuDF migration, and torch.compile.

    327 GitHub stars~3.5k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check: notes

  • Gitnexus Refresh On Stale

    ML4ITS/TimeVQVAE

    Refresh GitNexus indexing and regenerate local GitNexus skills when repository status is stale.

    166 GitHub stars~264 tokensUpdated 7 mo ago
    AI & LLM EngineeringAuto-check passed

  • Graphsignal

    graphsignal/graphsignal

    Profile AI inference workloads (vLLM, SGLang, TensorRT-LLM, PyTorch, any GPU application) with the Graphsignal profiler and read the results from its local /signals JSON endpoint.

    257 GitHub stars~6.2k tokensUpdated 9 days ago
    AI & LLM EngineeringAuto-check passed

  • Pt2 Bug Basher

    pytorch/pytorch

    Debug PyTorch 2 compiler stack failures including Dynamo graph breaks, Inductor codegen errors, AOTAutograd crashes, and accuracy mismatches.

    104k GitHub stars~3.5k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Megatron-Core LLM Training

    Orchestra-Research/AI-Research-SKILLs

    Sets up large-scale LLM training with NVIDIA Megatron-Core, choosing tensor, pipeline, data, context and expert parallelism for a given model size and GPU count.

    13k GitHub starsUsed in 3 repos~2.4k tokens
    AI & LLM EngineeringAuto-check passed

More from NVIDIA/skills

All 380 skills in this repo

  • Vss Deploy Detection Tracking 2D

    NVIDIA/skills

    Official

    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.

    3.5k GitHub starsUsed in 1 repo~4.5k tokens
    Auto-check passed

  • HSB IP Def File Tool

    NVIDIA/skills

    Official

    Generates, validates, compares and explains HOLOLINK_def.svh macro files for the HSB IP, using bundled Python scripts and asking before it writes anything.

    3.5k GitHub stars~2.9k tokensUpdated today
    Auto-check passed

  • Isaac Sim Mission Control Showcase

    NVIDIA/skills

    Official

    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.

    3.5k GitHub stars~4.8k tokensUpdated today
    Auto-check passed

  • Defect Image Generation with Cosmos AnomalyGen

    NVIDIA/skills

    Official

    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.

    3.5k GitHub stars~5k tokensUpdated today
    Auto-check: notes

  • Physical AI Video Augmentation on OSMO

    NVIDIA/skills

    Official

    Orchestrates video data augmentation and auto-labeling workflows on OSMO, from flow selection and preflight checks to submission, monitoring and output download.

    3.5k GitHub stars~4.7k tokensUpdated today
    Auto-check: notes

  • TAO Detection KPI Analysis

    NVIDIA/skills

    Official

    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.

    3.5k GitHub stars~2.7k tokensUpdated today
    Auto-check: notes

Works with

Categories

Questions about Physicsnemo Discover

What does Physicsnemo Discover do?

Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse…. Physicsnemo Discover is an agent skill from NVIDIA/skills, published by the product's own GitHub organization. Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative).

When should I use Physicsnemo Discover?

Physicsnemo Discover fits situations like: environment setup; other code authoring/scaffolding; contributor/CI/packaging questions; repo-specific questions in physicsnemo-sym/-cfd/-curator.

How do I install Physicsnemo Discover in Claude Code?

Run `npx skills add NVIDIA/skills --skill physicsnemo-discover -a claude-code`. Or copy the skill folder (skills/physicsnemo-discover in NVIDIA/skills) into .claude/skills/physicsnemo-discover in your project. Claude Code loads it when a task matches its description.

How do I install Physicsnemo Discover in Codex?

Run `npx skills add NVIDIA/skills --skill physicsnemo-discover -a codex`. Or copy the skill folder (skills/physicsnemo-discover in NVIDIA/skills) into .agents/skills/physicsnemo-discover in your project. Codex loads it when a task matches its description.

Can I use Physicsnemo Discover 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 NVIDIA/skills --skill physicsnemo-discover -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/physicsnemo-discover, .gemini/skills/physicsnemo-discover, .github/skills/physicsnemo-discover and .opencode/skills/physicsnemo-discover in your project.

What does Physicsnemo Discover need to run?

Going by SKILL.md and its folder, Physicsnemo Discover needs the command-line tools its instructions call (bash and git).

Does Physicsnemo Discover access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Physicsnemo Discover 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 Physicsnemo Discover use?

Physicsnemo Discover 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.

How many tokens does Physicsnemo Discover use?

About 1.8k tokens (SKILL.md is roughly 7.4k 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 4.8k tokens, read only when the agent opens those files.

What are the alternatives to Physicsnemo Discover?

Skills that share tags, products or a category with Physicsnemo Discover: Uv Pypi Publish (ML4ITS/TimeVQVAE, 166 stars), GPU Optimizer (Mathews-Tom/armory, 327 stars), Gitnexus Refresh On Stale (ML4ITS/TimeVQVAE, 166 stars) and Graphsignal (graphsignal/graphsignal, 257 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Physicsnemo Discover?

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.