physicsnemo-discover

Name: physicsnemo-discover
Author: NVIDIA

1.7kinstalls297forks

How to install physicsnemo-discover?

nvidia/skills/physicsnemo-discover

$npx -y skills add nvidia/skills --skill physicsnemo-discover

Installs into the current project.

Summary

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

Files · 1

View on GitHub

SKILL.md

1	# PhysicsNeMo Discoverability
2
3	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.
4
5	## Core principle
6
7	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.
8
9	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.
10
11	## What a correct answer satisfies
12
13	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`.
14
15	- 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.
16	- 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.
17	- 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.
18	- 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."*
19	- 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.
20
21	## Discovery
22
23	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.
24
25	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.
26
27	## Output format
28
29	```
30	## Problem shape
31	Data shape: <resolved>. Task: <resolved>. Axes: model × datapipe × training strategy × config.
32
33	## Candidate model families (for your data shape)
34	Multiple families typically apply. Treat this as a menu, not a ranking.
35	- <family> at <absolute __init__.py path> — <one-line from docstring/exports>. Instantiated by: <example path if any>.
36	- <family> at <path> — <one-line>. Instantiated by: <example path if any>.
37
38	## Datapipe(s) for your data format
39	Datapipe choice is independent of model choice.
40	- <class / subpackage> at <absolute path> — <one-line>. Reused by: <examples if known>.
41	- For c

People who liked this also viewed

6 picks

Type

physicsnemo-discover

1.7kinstalls297forks

View on GitHub

How to install physicsnemo-discover?

nvidia/skills/physicsnemo-discover

$npx -y skills add nvidia/skills --skill physicsnemo-discover

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# PhysicsNeMo Discoverability
2
3	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.
4
5	## Core principle
6
7	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.
8
9	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.
10
11	## What a correct answer satisfies
12
13	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`.
14
15	- 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.
16	- 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.
17	- 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.
18	- 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."*
19	- 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.
20
21	## Discovery
22
23	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.
24
25	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.
26
27	## Output format
28
29	```
30	## Problem shape
31	Data shape: <resolved>. Task: <resolved>. Axes: model × datapipe × training strategy × config.
32
33	## Candidate model families (for your data shape)
34	Multiple families typically apply. Treat this as a menu, not a ranking.
35	- <family> at <absolute __init__.py path> — <one-line from docstring/exports>. Instantiated by: <example path if any>.
36	- <family> at <path> — <one-line>. Instantiated by: <example path if any>.
37
38	## Datapipe(s) for your data format
39	Datapipe choice is independent of model choice.
40	- <class / subpackage> at <absolute path> — <one-line>. Reused by: <examples if known>.
41	- For c

People who liked this also viewed

6 picks

Type