Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

or, when no additional packages are required: · nvidia | DecimalAI

codingby nvidia

or, when no additional packages are required:

nvidia/earth2studio-create-prognostic

Source nvidia/skills ↗License Apache-2.0

Create Earth2Studio prognostic (time-stepping forecast) model wrappers.

SkillScore83Maintained

Automatic

AI Engineer pack

Last verified 8/12/2026

What it changes

Passed 17 of 21 test cases with the skill, and 9 of 21 without it.

Without skill42%

With skill83%

Checks it passed that the model alone missed

Imports logger from loguru for logging.
Prefixes the mock test class name with Phoo.
Prefixes pytest invocation commands with uv run.

and 10 more in the full report

10 fixed10 passed either way4 still failing0 broke

Pass-rate lift: +42 pp
Tokens: +101%
Agent turns: 0%
Response time: -56%

Model gemini-3.6-flashMeasured 8/12/2026v120 of 24 cases passed with skill · 21 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/nvidia-earth2studio-create-prognostic/SKILL.md https://app.decimal.ai/s/nvidia-earth2studio-create-prognostic/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add nvidia-earth2studio-create-prognostic, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/nvidia-earth2studio-create-prognostic/ and pins it in .decimal/skills.lock

decimalai skills add nvidia-earth2studio-create-prognostic

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/nvidia-earth2studio-create-prognostic/SKILL.md https://app.decimal.ai/s/nvidia-earth2studio-create-prognostic/SKILL.md

Raw file: /s/nvidia-earth2studio-create-prognostic/SKILL.md ↗ · machine-readable summary at /s/nvidia-earth2studio-create-prognostic.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 10

Prompt

In `test/models/px/test_storm_v2.py`, we wrote a full-weight test `test_storm_v2_package` decorated with `@pytest.mark.package`. What command should be used to run this package test specifically?

What was checked, without and with the skill
Checked	Without skill	With skill
Passes the --package option to pytest when running real-weight tests.	Missed	Passed

case-18 · gemini-3.6-flash · 8/12/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md287 lines7 files

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>.py with triple inheritance
Create test/models/px/test_<name>.py with 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 run for 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 |

Track record

Benchmark

17 / 21

test cases passed, vs 9 / 21 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

nvidia / skills

skills/earth2studio-create-prognostic/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1Bundled 6 files

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

nvidia/earth2studio-create-diagnosticCreate Earth2Studio diagnostic model wrappers for single-step data transformations, including simple derived diagnostics, packaged AutoModel diagnostics, and generative or diffusion diagnostics. Do NOT use for prognostic time-stepping models, data sources, or installation.Close match+68 pp pass-rate lift

More skills from the same source and nearby in the registry, with their headline benchmark lift.