NVIDIA/skills is a catalogue of portable instruction sets that teach coding agents how to use NVIDIA software for robotics, simulation, CUDA, retrieval-augmented generation, and related workflows. Developers install these skills in agents such as Claude Code or Codex, while the catalogue mirrors skills maintained in separate NVIDIA product repositories.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add NVIDIA/skills --skill earth2studio-create-prognosticgit clone --depth 1 https://github.com/NVIDIA/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nvidia/skills/earth2studio-create-prognostic)<a href="https://agentmods.dev/skills/nvidia/skills/earth2studio-create-prognostic"><img src="https://agentmods.dev/badge/skills/nvidia/skills/earth2studio-create-prognostic.svg" alt="Measured on agentmods" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 31 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00036 | $0.02623 |
| Opus 5 | $0.00018 | $0.01311 |
| Sonnet 5 | $0.00007 | $0.00525 |
| Haiku 4.5 | $0.00004 | $0.00262 |
Grade A, and why
earth2studio-create-prognostic scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quick Start Checklist
Do these steps IN ORDER. Do not skip any step.
- Read this SKILL.md completely first
- Get reference script (Step 0)
- Create
earth2studio/models/px/<name>.pywith triple inheritance - Create
test/models/px/test_<name>.pywith mock tests - Run:
uv run pytest test/models/px/test_<name>.py -v - Add/update model extra, install docs, API docs, and changelog (Steps 1-2, 9)
- Run:
make format && make lint
⚠️ CRITICAL: Always use
uv runfor Python commands:
- ✅
uv run pytest .../uv run python ...- ❌
pytest .../python ...(missing dependencies)Stuck or wrong output: Do not keep retrying the same fix. Follow Self-Improvement to patch this skill before continuing.
Purpose
Implement a prognostic model wrapper connecting third-party ML weather models to Earth2Studio. Prognostic models time-integrate forward—given initial state, they predict future states by stepping through time (e.g., 6-hour increments).
Workspace
| Context | Location |
|---|---|
| Harbor eval | Write to /workspace/output/earth2studio/models/px/... |
Harbor + --copy-repo |
Full checkout at /workspace/repo |
| Local clone | Directory with pyproject.toml |
Never read evals/targets/ — grader references only.
Reference Files
Load on demand during the matching step:
| File | Content | Load at |
|---|---|---|
references/skeleton-template.py |
Full model skeleton with FILL comments | Steps 3–6 |
references/method-templates.py |
Canonical method implementations | Steps 4–6 |
references/testing-guide.py |
Test skeleton and mock patterns | Step 7 |
references/validation-guide.md |
Comparison scripts, PR, code review | Steps 10–11 |
Workflow Steps
Step 0 — Get Reference Script
If $ARGUMENTS provided, use it. Otherwise ask:
Please provide a reference inference script URL/path.
Step 1 — Analyze & Propose Dependencies
What ships with it
17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- BENCHMARK.md 4.3 KB
- evals/config.yml 1.1 KB
- evals/environment/Dockerfile 1.4 KB
- evals/environment/setup/bootstrap.sh 1.2 KB runs code
- evals/evals.json 2.4 KB
- evals/targets/eval_1_target.py 6.6 KB runs code
- evals/targets/eval_2_target.py 8.3 KB runs code
- evals/targets/test/eval_1_test_target.py 5.6 KB runs code
- evals/targets/test/eval_2_test_target.py 6.4 KB runs code
- references/method-templates.py 13 KB runs code
- references/pr-body-template.md 2.4 KB
- references/pr-comment-template.md 2.2 KB
- references/skeleton-template.py 15 KB runs code
- references/testing-guide.py 14 KB runs code
- references/validation-guide.md 4.8 KB
- skill-card.md 2.4 KB
- skill.oms.sig 7.1 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 301 lines · 36 tokens per session scan A 811fafca9495
earth2studio-create-prognostic is a skill published in the GitHub repository NVIDIA/skills (3,223 stars, last pushed today), licensed Apache-2.0. It adds 36 tokens to every session and 2,623 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
clinical-case-report
Structured medical case presentation for clinical rounds, conferences, and documentation. Generates SOAP-format or narrative case reports with physiologically accurate vitals, labs, and evidence-based plans. Use when the brief mentions "case report", "case presentation", "SOAP note", "clinical case", "ward rounds"…
qec-construct
Verifier-in-the-loop CONSTRUCTION of quantum error-correcting codes with transversal non-Clifford gates (CCZ/T). Applies whenever the project goal is a new or better code/construction — INCLUDING search-phrased goals ("find codes beating X"), where the construct-loop (propose algebraic rule → qverify → debug) is the…
paper-figures
Extract figures from downloaded papers and include them in survey/review reports. Use when the report covers other groups' work and benefits from their architecture diagrams, experimental plots, or system schematics. Your brain prompt supplies the absolute path to the extract-figures script as {{EXTRACTFIGURES}} — use…
arxiv-summarizer-orchestrator
End-to-end orchestration skill for periodic arXiv collection and reporting using three sub-skills: arxiv-search-collector, arxiv-paper-processor, and arxiv-batch-reporter. Supports manual language control across all markdown outputs and Stage-B processing strategy (subagentparallel default max 5, or serial).
ai-scaling-laws
Sizes models and token budgets using Kaplan/Chinchilla scaling laws. Use when reasoning about compute-optimal N and D, tokens-per-parameter ratios, or over-training tradeoffs.
swmm-calibration
Calibration and validation scaffold for EPA SWMM. Use when an agent needs to (1) compare simulated vs observed flow, (2) evaluate candidate parameter sets, (3) rank explicit candidates by an objective, (4) run a bounded random / LHS / adaptive search for the best-fitting parameters, (5) run a publication-grade SCE-UA…