Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nvidia/earth2studio-create-datasource
Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores.
Passed 15 of 20 test cases with the skill, and 4 of 20 without it.
and 15 more in the full report
12 fixed4 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am writing the test file for a newly created data source named `cmip6`. Where should I create the test file in the repository structure and what command should I run to execute only this test file and stop on the first failure?
| Checked | Without skill | With skill |
|---|---|---|
| Places the test file at test/data/test_cmip6.py | Missed | Passed |
| Uses uv run pytest test/data/test_cmip6.py -x to execute the test | Missed | Passed |
The instructions your model reads when the skill loads.
End-to-end workflow for implementing a new Earth2Studio data source wrapper that connects a remote data store (S3, GCS, Azure, HTTP, HuggingFace) to Earth2Studio's async data fetching infrastructure — from analysis through implementation, testing, validation, and PR submission.
uv (uv run python must work)origin) and upstream (upstream) remotesUse the directory containing pyproject.toml. For Harbor evals, write to
/workspace/output/ preserving paths. Never read evals/targets/.
Python Environment: Always use
uv run pythonor the local.venv. Never use the system Python directly.
Follow every step in order.
[CONFIRM] gates: Only Step 1 (Source Type) and Step 12 (Sanity-Check Plots) require explicit user approval. All other
[CONFIRM]markers are advisory — present decisions inline and proceed without blocking.Deliverables first: Write the source file and test file (Steps 6–7) before extended exploration, documentation, registration, CHANGELOG, or PR work. Skip Steps 8–14 when the user asks for implementation only.
Before you finish: Run verification commands in the repo root so results appear in the session log:
test cases passed, vs 4 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.