[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73YBNHMHFDFP83MAVGQQ92N":3,"skill-same:01M73YBNHMHFDFP83MAVGQQ92N":135},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":36,"commitSha":37,"skillDirectory":38,"forksCount":14,"repositoryHtmlUrl":39,"repositoryHomepageUrl":40,"ownerHtmlUrl":41,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":42,"install":43,"resources":56},"01M73YBNHMHFDFP83MAVGQQ92N","earth2studio-create-datasource",null,"Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores. Do NOT use for fetching data with existing sources, model inference, or installation tasks.","pattanation\u002FNorvik","pattanation","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235419268?v=4","01M71M5THHYYB15ME8R2E4FCZG","Patta","01M71M5TJM1NDM992M8PDKYR2K",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fearth2studio-create-datasource\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: earth2studio-create-datasource\nversion: 0.16.0\nlicense: Apache-2.0\nmetadata:\n  author: NVIDIA Earth-2 Team \u003Cagent-skills@nvidia.com>\n  tags:\n    - earth2studio\n    - earth2\n    - python\n    - data-source\n    - forecast-source\n    - integration\ndescription: >\n  Create and validate Earth2Studio data source wrappers (DataSource,\n  ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores.\n  Do NOT use for fetching data with existing sources, model inference, or\n  installation tasks.\nargument-hint: URL or description of remote data store (optional)\n---\n\n# Create and Validate Data Source\n\n## Purpose\n\nEnd-to-end workflow for implementing a new Earth2Studio data source wrapper\nthat connects a remote data store (S3, GCS, Azure, HTTP, HuggingFace) to\nEarth2Studio's async data fetching infrastructure — from analysis through\nimplementation, testing, validation, and PR submission.\n\n## Prerequisites\n\n- Earth2Studio dev environment with `uv` (`uv run python` must work)\n- Git configured with fork (`origin`) and upstream (`upstream`) remotes\n- Access to the target remote data store (credentials if private)\n- Python 3.10+\n\n## Workspace\n\nUse the directory containing `pyproject.toml`. For Harbor evals, write to\n`\u002Fworkspace\u002Foutput\u002F` preserving paths. Never read `evals\u002Ftargets\u002F`.\n\n## Instructions\n\n> **Python Environment:** Always use `uv run python` or the local `.venv`.\n> Never use the system Python directly.\n\nFollow every step in order.\n\n> **[CONFIRM] gates:** Only Step 1 (Source Type) and Step 12 (Sanity-Check\n> Plots) require explicit user approval. All other `[CONFIRM]` markers are\n> advisory — present decisions inline and proceed without blocking.\n>\n> **Deliverables first:** Write the source file and test file (Steps 6–7)\n> before extended exploration, documentation, registration, CHANGELOG, or PR\n> work. Skip Steps 8–14 when the user asks for implementation only.\n>\n> **Before you finish:** Run verification commands in the repo root so results\n> appear in the session log:\n>\n> ```bash\n> uv run pytest test\u002Fdata\u002Ftest_\u003Csource>.py -x\n> make format && make lint\n> ```\n>\n> **Be concise:** Avoid long architecture reports; summarize decisions in a\n> few sentences and move on to file writes.\n>\n> **Hangs or User Feedback** If agent becomes stuck or user provides a\n> correction during this skills use, conservatively review relevant part of\n> the skill and improve. Be concise.\n>\n> **One source type per invocation.** Invoke again for companion types.\n\n### Reference Files\n\nLoad these on demand during the relevant steps:\n\n| File | Content | Load at |\n|---|---|---|\n| `references\u002Fimplementation-guide.py` | Skeleton source with FILL comments | Steps 3–10 |\n| `references\u002Ftesting-guide.py` | Test skeleton with FILL comments | Step 11 |\n| `references\u002Fvalidation-guide.md` | Plot templates, PR body template, Greptile handling | Steps 12–14 (optional, for templates) |\n\n---\n\n### Workflow Overview\n\n```text\nStep 0: Obtain reference → Step 1: Determine type → Step 2: Dependencies\n→ Step 3: Add deps → Step 4: Create lexicon → Step 5: Update vocab\u002Fschema\n→ Step 6: Create skeleton → Step 7: Implement source → Step 8: Register\n→ Step 9: Documentation → Step 10: CHANGELOG → Step 11: Tests\n→ Step 12: Validate & plots (user confirms) → Step 13: PR + sanity comment\n→ Step 14: Greptile review\n```\n\n---\n\n### Step 0 — Obtain Remote Data Store Reference\n\nIf `$ARGUMENTS` is provided, use it (URL → WebFetch; file path → read).\n\nIf empty, ask:\n\n> Please provide a URL, API documentation link, or description of the\n> remote data store. This will be used to understand storage format,\n> access pattern, variable inventory, temporal\u002Fspatial resolution.\n\n---\n\n### Step 1 — Determine Source Type\n\n| Protocol | Returns | Has `lead_time`? | Use |\n|---|---|---|---|\n| **DataSource** | `xr.DataArray` | No | Gridded analysis\u002Freanalysis |\n| **ForecastSource** | `xr.DataArray` | Yes | Gridded forecast |\n| **DataFrameSource** | `pd.DataFrame` | No | Sparse\u002Fstation obs |\n| **ForecastFrameSource** | `pd.DataFrame` | Yes | Sparse forecast obs |\n\nKey factors: gridded vs sparse → DataArray vs DataFrame; analysis vs forecast → Source vs ForecastSource.\n\n#### [CONFIRM — Source Type]\n\nPresent recommended type with justification. Ask for confirmation.\n\n---\n\n### Step 2 — Examine Remote Store & Propose Dependencies\n\n**Analyze:** storage backend, file format, authentication, access pattern,\ntemporal\u002Fspatial resolution, variable inventory.\n\n**Prefer fsspec:**\n\n| Backend | Preferred | Avoid |\n|---|---|---|\n| AWS S3 | `s3fs` (core dep) | `boto3` directly |\n| GCS | `gcsfs` (core dep) | `google-cloud-storage` |\n| Azure | `adlfs` | `azure-storage-blob` |\n| HTTP | `fsspec` (core dep) | `requests` |\n| HuggingFace | `huggingface_hub` (core dep) | custom scripts |\n\nOnly fall back to dedicated libraries when fsspec cannot access the store.\n\nCheck `pyproject.toml` — only propose packages not already present.\nCore deps include: `s3fs`, `gcsfs`, `fsspec`, `zarr`, `netCDF4`, `h5py`,\n`pygrib`, `huggingface-hub`, `pandas`, `pyarrow`.\n\n#### [CONFIRM — Dependencies & Access Pattern]\n\nPresent: backend, fsspec filesystem, new packages (with license), auth method.\n\n---\n\n### Step 3 — Add Dependencies\n\n> **Load `references\u002Fimplementation-guide.py` from here through Step 10.**\n\nIf new packages needed:\n\n1. `uv add --extra data \u003Cpackage>`\n2. `uv lock`\n3. Add optional dependency imports using `OptionalDependencyFailure` pattern\n\n---\n\n### Step 4 — Create Lexicon Class\n\nCreate `earth2studio\u002Flexicon\u002F\u003Csource_name>.py` with:\n\n- `metaclass=LexiconType`\n- `VOCAB: dict[str, str]` mapping E2S names → remote keys\n- `get_item(cls, val)` returning `tuple[str, Callable]`\n- Use `::` separator for structured keys\n\nMap remote variables against `E2STUDIO_VOCAB` (282 entries in\n`earth2studio\u002Flexicon\u002Fbase.py`).\n\n#### [CONFIRM — Lexicon & Variable Mapping]\n\nPresent: class name, key format, full mapping table, modifiers, reference URL.\n\n---\n\n### Step 5 — Update E2STUDIO_VOCAB \u002F SCHEMA (if needed)\n\n- New vocab: surface = descriptive abbrev; pressure = `{name}{level}`\n- New schema fields: DataFrame sources only, check `E2STUDIO_SCHEMA`\n\n#### [CONFIRM — Vocabulary & Schema Updates]\n\nSkip if no updates needed.\n\n---\n\n### Step 6 — Create Skeleton Data Source File\n\nFollow canonical method ordering:\n\n1. Class constants\n2. SCHEMA\n3. `__init__`\n4. `_async_init`\n5. `__call__`\n6. `fetch`\n7. `_create_tasks`\n8. `fetch_wrapper`\n9. `fetch_array`\n10. `_validate_time`\n11. Helpers\n12. `cache` property\n13. `available` classmethod\n\nUse async task dataclass pattern for parallel execution.\n\n#### [CONFIRM — Skeleton]\n\nPresent: class name, file path, skeleton code, task dataclass.\n\n---\n\n### Step 7 — Implement the Data Source & Tests\n\n> **The test file is a co-equal deliverable.** Create `test\u002Fdata\u002Ftest_\u003Cfilename>.py`\n> alongside the source. Add `test_\u003Csource>_call_mock` for async sources.\n\n**Sync sources:** Use `prep_data_inputs`\u002F`prep_forecast_inputs`, direct `__call__`.\n\n**Async sources:** See `references\u002Fimplementation-guide.py` for required patterns:\n`_sync_async`, `managed_session`, `gather_with_concurrency`, `async_retry`,\npure async I\u002FO, `try\u002Ffinally` cleanup. Constructor params: `cache=True`,\n`verbose=True`, `async_timeout=600`, `async_workers=16`, `retries=3`.\nDataFrame sources add `time_tolerance`.\n\n---\n\n### Step 8 — Register the Source\n\n- `earth2studio\u002Fdata\u002F__init__.py` — alphabetical import\n- `earth2studio\u002Flexicon\u002F__init__.py` — alphabetical import\n- Verify `pyproject.toml` deps\n\n---\n\n### Step 9 — Update Documentation\n\n- Add to correct RST file (`datasources_analysis.rst` \u002F `_forecast.rst` \u002F `_dataframe.rst`)\n- Class docstring: Parameters, Warning (download size), Note (reference URLs), Badges (last)\n- All public methods: NumPy-style docstrings\n\n---\n\n### Step 10 — Update CHANGELOG.md\n\nAdd entry under the current unreleased version. See\n`references\u002Fimplementation-guide.py` REGISTRATION CHECKLIST for the format.\n\nOne line per source. Do NOT add separate lexicon entries.\n\n---\n\n### Step 11 — Verify Style & Expand Tests\n\nRun `make format && make lint && make license`. Load `references\u002Ftesting-guide.py`\nfor test skeletons. Required tests: `test_\u003Csource>_fetch` (slow), `_cache` (slow),\n`_call_mock`, `_exceptions`, `_available`. Target 90%+ coverage with `--slow`.\n\n#### [CONFIRM — Tests]\n\nPresent test file, functions, coverage.\n\n---\n\n### Step 12 — Validate Variables & Sanity-Check\n\n1. Validate all lexicon vars against real data (run script, do NOT commit)\n2. Remove variables with \u003C 10% valid data\n3. Create sanity-check plot (gridded or sparse template)\n4. Tell user the plot path and ask for visual confirmation\n\n#### [CONFIRM — Sanity-Check Plots]\n\nUser MUST visually inspect plots. Do not proceed without confirmation.\n\n---\n\n### Step 13 — Branch, Commit & Open PR\n\n1. Create branch `feat\u002Fdata-source-\u003Cname>`\n2. Commit (do NOT add sanity-check script\u002Fimages)\n3. Push to fork\n4. `gh pr create --repo NVIDIA\u002Fearth2studio`\n5. **Immediately post sanity-check validation as PR comment** with:\n   - Variable coverage table (name, count, range, unit)\n   - Data validation summary (regions, storms\u002Fstations, time range)\n   - Key findings (physically reasonable values, conversions verified)\n   - Full validation script in `\u003Cdetails>` block\n   - Image placeholder: `\u003C!-- Drag and drop sanity-check image here -->`\n\n#### [CONFIRM — Ready to Submit]\n\nVerify all steps complete before creating PR.\n\n---\n\n### Step 14 — Automated Code Review\n\n1. Poll for Greptile review (5 min timeout)\n2. Categorize feedback (bug\u002Fstyle\u002Fperf\u002Fdocs\u002Fsuggestion\u002Ffalse-positive)\n3. Present triage table to user\n4. Implement accepted fixes\n5. Respond to PR comments\n6. Push\n\n#### [CONFIRM — Review Triage]\n\nUser approves which comments to address.\n\n---\n\n## Examples\n\n```text\nUser: Add a data source for the NOAA GFS analysis on S3\nAgent: [loads skill, proceeds through Steps 0–14]\n```\n\n---\n\n## Limitations\n\n- One source type per invocation\n- Requires network access for validation (Step 12)\n- SPDX license headers required in all files\n\n---\n\n## Reminders\n\n**DO:** `uv run python`, `loguru.logger`, alphabetical order in `__init__.py`\u002FRST\u002FCHANGELOG,\ncanonical method ordering, async utilities (`managed_session`, `gather_with_concurrency`,\n`async_retry`), pure async I\u002FO, reference URLs in docstrings, `try\u002Ffinally` cleanup.\n\n**AVOID:** `asyncio.to_thread`, bare `tqdm.gather`, xarray for loading, full file downloads.\n\n**NEVER:** `loop.set_default_executor()`, commit secrets, commit sanity-check scripts\u002Fimages.\n","# Create and Validate Data Source\n\n## Purpose\n\nEnd-to-end workflow for implementing a new Earth2Studio data source wrapper\nthat connects a remote data store (S3, GCS, Azure, HTTP, HuggingFace) to\nEarth2Studio's async data fetching infrastructure — from analysis through\nimplementation, testing, validation, and PR submission.\n\n## Prerequisites\n\n- Earth2Studio dev environment with `uv` (`uv run python` must work)\n- Git configured with fork (`origin`) and upstream (`upstream`) remotes\n- Access to the target remote data store (credentials if private)\n- Python 3.10+\n\n## Workspace\n\nUse the directory containing `pyproject.toml`. For Harbor evals, write to\n`\u002Fworkspace\u002Foutput\u002F` preserving paths. Never read `evals\u002Ftargets\u002F`.\n\n## Instructions\n\n> **Python Environment:** Always use `uv run python` or the local `.venv`.\n> Never use the system Python directly.\n\nFollow every step in order.\n\n> **[CONFIRM] gates:** Only Step 1 (Source Type) and Step 12 (Sanity-Check\n> Plots) require explicit user approval. All other `[CONFIRM]` markers are\n> advisory — present decisions inline and proceed without blocking.\n>\n> **Deliverables first:** Write the source file and test file (Steps 6–7)\n> before extended exploration, documentation, registration, CHANGELOG, or PR\n> work. Skip Steps 8–14 when the user asks for implementation only.\n>\n> **Before you finish:** Run verification commands in the repo root so results\n> appear in the session log:\n>\n> ```bash\n> uv run pytest test\u002Fdata\u002Ftest_\u003Csource>.py -x\n> make format && make lint\n> ```\n>\n> **Be concise:** Avoid long architecture reports; summarize decisions in a\n> few sentences and move on to file writes.\n>\n> **Hangs or User Feedback** If agent becomes stuck or user provides a\n> correction during this skills use, conservatively review relevant part of\n> the skill and improve. Be concise.\n>\n> **One source type per invocation.** Invoke again for companion types.\n\n### Reference Files\n\nLoad these on demand during the relevant steps:\n\n| File | Content | Load at |\n|---|---|---|\n| `references\u002Fimplementation-guide.py` | Skeleton source with FILL comments | Steps 3–10 |\n| `references\u002Ftesting-guide.py` | Test skeleton with FILL comments | Step 11 |\n| `references\u002Fvalidation-guide.md` | Plot templates, PR body template, Greptile handling | Steps 12–14 (optional, for templates) |\n\n---\n\n### Workflow Overview\n\n```text\nStep 0: Obtain reference → Step 1: Determine type → Step 2: Dependencies\n→ Step 3: Add deps → Step 4: Create lexicon → Step 5: Update vocab\u002Fschema\n→ Step 6: Create skeleton → Step 7: Implement source → Step 8: Register\n→ Step 9: Documentation → Step 10: CHANGELOG → Step 11: Tests\n→ Step 12: Validate & plots (user confirms) → Step 13: PR + sanity comment\n→ Step 14: Greptile review\n```\n\n---\n\n### Step 0 — Obtain Remote Data Store Reference\n\nIf `$ARGUMENTS` is provided, use it (URL → WebFetch; file path → read).\n\nIf empty, ask:\n\n> Please provide a URL, API documentation link, or description of the\n> remote data store. This will be used to understand storage format,\n> access pattern, variable inventory, temporal\u002Fspatial resolution.\n\n---\n\n### Step 1 — Determine Source Type\n\n| Protocol | Returns | Has `lead_time`? | Use |\n|---|---|---|---|\n| **DataSource** | `xr.DataArray` | No | Gridded analysis\u002Freanalysis |\n| **ForecastSource** | `xr.DataArray` | Yes | Gridded forecast |\n| **DataFrameSource** | `pd.DataFrame` | No | Sparse\u002Fstation obs |\n| **ForecastFrameSource** | `pd.DataFrame` | Yes | Sparse forecast obs |\n\nKey factors: gridded vs sparse → DataArray vs DataFrame; analysis vs forecast → Source vs ForecastSource.\n\n#### [CONFIRM — Source Type]\n\nPresent recommended type with justification. Ask for confirmation.\n\n---\n\n### Step 2 — Examine Remote Store & Propose Dependencies\n\n**Analyze:** storage backend, file format, authentication, access pattern,\ntemporal\u002Fspatial resolution, variable inventory.\n\n**Prefer fsspec:**\n\n| Backend | Preferred | Avoid |\n|---|---|---|\n| AWS S3 | `s3fs` (core dep) | `boto3` directly |\n| GCS | `gcsfs` (core dep) | `google-cloud-storage` |\n| Azure | `adlfs` | `azure-storage-blob` |\n| HTTP | `fsspec` (core dep) | `requests` |\n| HuggingFace | `huggingface_hub` (core dep) | custom scripts |\n\nOnly fall back to dedicated libraries when fsspec cannot access the store.\n\nCheck `pyproject.toml` — only propose packages not already present.\nCore deps include: `s3fs`, `gcsfs`, `fsspec`, `zarr`, `netCDF4`, `h5py`,\n`pygrib`, `huggingface-hub`, `pandas`, `pyarrow`.\n\n#### [CONFIRM — Dependencies & Access Pattern]\n\nPresent: backend, fsspec filesystem, new packages (with license), auth method.\n\n---\n\n### Step 3 — Add Dependencies\n\n> **Load `references\u002Fimplementation-guide.py` from here through Step 10.**\n\nIf new packages needed:\n\n1. `uv add --extra data \u003Cpackage>`\n2. `uv lock`\n3. Add optional dependency imports using `OptionalDependencyFailure` pattern\n\n---\n\n### Step 4 — Create Lexicon Class\n\nCreate `earth2studio\u002Flexicon\u002F\u003Csource_name>.py` with:\n\n- `metaclass=LexiconType`\n- `VOCAB: dict[str, str]` mapping E2S names → remote keys\n- `get_item(cls, val)` returning `tuple[str, Callable]`\n- Use `::` separator for structured keys\n\nMap remote variables against `E2STUDIO_VOCAB` (282 entries in\n`earth2studio\u002Flexicon\u002Fbase.py`).\n\n#### [CONFIRM — Lexicon & Variable Mapping]\n\nPresent: class name, key format, full mapping table, modifiers, reference URL.\n\n---\n\n### Step 5 — Update E2STUDIO_VOCAB \u002F SCHEMA (if needed)\n\n- New vocab: surface = descriptive abbrev; pressure = `{name}{level}`\n- New schema fields: DataFrame sources only, check `E2STUDIO_SCHEMA`\n\n#### [CONFIRM — Vocabulary & Schema Updates]\n\nSkip if no updates needed.\n\n---\n\n### Step 6 — Create Skeleton Data Source File\n\nFollow canonical method ordering:\n\n1. Class constants\n2. SCHEMA\n3. `__init__`\n4. `_async_init`\n5. `__call__`\n6. `fetch`\n7. `_create_tasks`\n8. `fetch_wrapper`\n9. `fetch_array`\n10. `_validate_time`\n11. Helpers\n12. `cache` property\n13. `available` classmethod\n\nUse async task dataclass pattern for parallel execution.\n\n#### [CONFIRM — Skeleton]\n\nPresent: class name, file path, skeleton code, task dataclass.\n\n---\n\n### Step 7 — Implement the Data Source & Tests\n\n> **The test file is a co-equal deliverable.** Create `test\u002Fdata\u002Ftest_\u003Cfilename>.py`\n> alongside the source. Add `test_\u003Csource>_call_mock` for async sources.\n\n**Sync sources:** Use `prep_data_inputs`\u002F`prep_forecast_inputs`, direct `__call__`.\n\n**Async sources:** See `references\u002Fimplementation-guide.py` for required patterns:\n`_sync_async`, `managed_session`, `gather_with_concurrency`, `async_retry`,\npure async I\u002FO, `try\u002Ffinally` cleanup. Constructor params: `cache=True`,\n`verbose=True`, `async_timeout=600`, `async_workers=16`, `retries=3`.\nDataFrame sources add `time_tolerance`.\n\n---\n\n### Step 8 — Register the Source\n\n- `earth2studio\u002Fdata\u002F__init__.py` — alphabetical import\n- `earth2studio\u002Flexicon\u002F__init__.py` — alphabetical import\n- Verify `pyproject.toml` deps\n\n---\n\n### Step 9 — Update Documentation\n\n- Add to correct RST file (`datasources_analysis.rst` \u002F `_forecast.rst` \u002F `_dataframe.rst`)\n- Class docstring: Parameters, Warning (download size), Note (reference URLs), Badges (last)\n- All public methods: NumPy-style docstrings\n\n---\n\n### Step 10 — Update CHANGELOG.md\n\nAdd entry under the current unreleased version. See\n`references\u002Fimplementation-guide.py` REGISTRATION CHECKLIST for the format.\n\nOne line per source. Do NOT add separate lexicon entries.\n\n---\n\n### Step 11 — Verify Style & Expand Tests\n\nRun `make format && make lint && make license`. Load `references\u002Ftesting-guide.py`\nfor test skeletons. Required tests: `test_\u003Csource>_fetch` (slow), `_cache` (slow),\n`_call_mock`, `_exceptions`, `_available`. Target 90%+ coverage with `--slow`.\n\n#### [CONFIRM — Tests]\n\nPresent test file, functions, coverage.\n\n---\n\n### Step 12 — Validate Variables & Sanity-Check\n\n1. Validate all lexicon vars against real data (run script, do NOT commit)\n2. Remove variables with \u003C 10% valid data\n3. Create sanity-check plot (gridded or sparse template)\n4. Tell user the plot path and ask for visual confirmation\n\n#### [CONFIRM — Sanity-Check Plots]\n\nUser MUST visually inspect plots. Do not proceed without confirmation.\n\n---\n\n### Step 13 — Branch, Commit & Open PR\n\n1. Create branch `feat\u002Fdata-source-\u003Cname>`\n2. Commit (do NOT add sanity-check script\u002Fimages)\n3. Push to fork\n4. `gh pr create --repo NVIDIA\u002Fearth2studio`\n5. **Immediately post sanity-check validation as PR comment** with:\n   - Variable coverage table (name, count, range, unit)\n   - Data validation summary (regions, storms\u002Fstations, time range)\n   - Key findings (physically reasonable values, conversions verified)\n   - Full validation script in `\u003Cdetails>` block\n   - Image placeholder: `\u003C!-- Drag and drop sanity-check image here -->`\n\n#### [CONFIRM — Ready to Submit]\n\nVerify all steps complete before creating PR.\n\n---\n\n### Step 14 — Automated Code Review\n\n1. Poll for Greptile review (5 min timeout)\n2. Categorize feedback (bug\u002Fstyle\u002Fperf\u002Fdocs\u002Fsuggestion\u002Ffalse-positive)\n3. Present triage table to user\n4. Implement accepted fixes\n5. Respond to PR comments\n6. Push\n\n#### [CONFIRM — Review Triage]\n\nUser approves which comments to address.\n\n---\n\n## Examples\n\n```text\nUser: Add a data source for the NOAA GFS analysis on S3\nAgent: [loads skill, proceeds through Steps 0–14]\n```\n\n---\n\n## Limitations\n\n- One source type per invocation\n- Requires network access for validation (Step 12)\n- SPDX license headers required in all files\n\n---\n\n## Reminders\n\n**DO:** `uv run python`, `loguru.logger`, alphabetical order in `__init__.py`\u002FRST\u002FCHANGELOG,\ncanonical method ordering, async utilities (`managed_session`, `gather_with_concurrency`,\n`async_retry`), pure async I\u002FO, reference URLs in docstrings, `try\u002Ffinally` cleanup.\n\n**AVOID:** `asyncio.to_thread`, bare `tqdm.gather`, xarray for loading, full file downloads.\n\n**NEVER:** `loop.set_default_executor()`, commit secrets, commit sanity-check scripts\u002Fimages.\n",{"name":5,"license":15,"version":24,"metadata":25,"description":34,"argument-hint":35},"0.16.0",{"tags":26,"author":33},[27,28,29,30,31,32],"earth2studio","earth2","python","data-source","forecast-source","integration","NVIDIA Earth-2 Team \u003Cagent-skills@nvidia.com>","Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores. Do NOT use for fetching data with existing sources, model inference, or installation tasks.\n","URL or description of remote data store (optional)","claude\u002Finstall-gsd-build-foQdV","d86cd127f527124b5fd0fd0bc679a4d79b7d01d7",".agents\u002Fskills\u002Fearth2studio-create-datasource","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik","https:\u002F\u002Fnorvik-orpin.vercel.app","https:\u002F\u002Fgithub.com\u002Fpattanation","2026-07-17 11:17:04",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add pattanation\u002FNorvik --skill earth2studio-create-datasource",{"tool":49,"command":50},"bunx","bunx skills add pattanation\u002FNorvik --skill earth2studio-create-datasource",{"tool":52,"command":53},"pnpm","pnpm dlx skills add pattanation\u002FNorvik --skill earth2studio-create-datasource","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fearth2studio-create-datasource\u002FSKILL.md",true,[57,63,67,73,79,83,87,91,95,99,103,107,111,115,119,123,127,131],{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"BENCHMARK.md","REFERENCE","参考文档",2496,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fearth2studio-create-datasource\u002FBENCHMARK.md",{"path":64,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":65,"sourceHtmlUrl":66},"evals\u002Fconfig.yml",1175,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fearth2studio-create-datasource\u002Fevals\u002Fconfig.yml",{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"evals\u002Fenvironment\u002FDockerfile","OTHER","其他",867,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fearth2studio-create-datasource\u002Fevals\u002Fenvironment\u002FDockerfile",{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"evals\u002Fenvironment\u002Fsetup\u002Fbootstrap.sh","SCRIPT","脚本",934,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fearth2studio-create-datasource\u002Fevals\u002Fenvironment\u002Fsetup\u002Fbootstrap.sh",{"path":80,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":81,"sourceHtmlUrl":82},"evals\u002Fevals.json",6215,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fearth2studio-create-datasource\u002Fevals\u002Fevals.json",{"path":84,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":85,"sourceHtmlUrl":86},"evals\u002Ftargets\u002Feval_1_target.py",2524,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fearth2studio-create-datasource\u002Fevals\u002Ftargets\u002Feval_1_target.py",{"path":88,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":89,"sourceHtmlUrl":90},"evals\u002Ftargets\u002Feval_2_target.py",2920,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fearth2studio-create-datasource\u002Fevals\u002Ftargets\u002Feval_2_target.py",{"path":92,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":93,"sourceHtmlUrl":94},"evals\u002Ftargets\u002Feval_3_target.py",3897,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fearth2studio-create-datasource\u002Fevals\u002Ftargets\u002Feval_3_target.py",{"path":96,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":97,"sourceHtmlUrl":98},"evals\u002Ftargets\u002Feval_4_target.py",11808,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fearth2studio-create-datasource\u002Fevals\u002Ftargets\u002Feval_4_target.py",{"path":100,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":101,"sourceHtmlUrl":102},"evals\u002Ftargets\u002Ftest\u002Feval_1_test_target.py",2441,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fearth2studio-create-datasource\u002Fevals\u002Ftargets\u002Ftest\u002Feval_1_test_target.py",{"path":104,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":105,"sourceHtmlUrl":106},"evals\u002Ftargets\u002Ftest\u002Feval_2_test_target.py",3152,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fearth2studio-create-datasource\u002Fevals\u002Ftargets\u002Ftest\u002Feval_2_test_target.py",{"path":108,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":109,"sourceHtmlUrl":110},"evals\u002Ftargets\u002Ftest\u002Feval_3_test_target.py",3741,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fearth2studio-create-datasource\u002Fevals\u002Ftargets\u002Ftest\u002Feval_3_test_target.py",{"path":112,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":113,"sourceHtmlUrl":114},"evals\u002Ftargets\u002Ftest\u002Feval_4_test_target.py",4571,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fearth2studio-create-datasource\u002Fevals\u002Ftargets\u002Ftest\u002Feval_4_test_target.py",{"path":116,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":117,"sourceHtmlUrl":118},"references\u002Fimplementation-guide.py",17722,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fearth2studio-create-datasource\u002Freferences\u002Fimplementation-guide.py",{"path":120,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":121,"sourceHtmlUrl":122},"references\u002Ftesting-guide.py",10367,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fearth2studio-create-datasource\u002Freferences\u002Ftesting-guide.py",{"path":124,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":125,"sourceHtmlUrl":126},"references\u002Fvalidation-guide.md",9771,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fearth2studio-create-datasource\u002Freferences\u002Fvalidation-guide.md",{"path":128,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":129,"sourceHtmlUrl":130},"skill-card.md",2613,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fearth2studio-create-datasource\u002Fskill-card.md",{"path":132,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":133,"sourceHtmlUrl":134},"skill.oms.sig",8065,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fearth2studio-create-datasource\u002Fskill.oms.sig",[136,143,150,184,210,234],{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":19},"01M73Z1NPMJ667E0DSPBS9FH0B","jetson-set-target","Switch the active Jetson target-platform pointer to an existing profile YAML. Use before customize\u002Fbuild\u002Fflash to change target; not for authoring profiles — use jetson-init-target instead.","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fjetson-set-target\u002FSKILL.md",[],[],{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":149,"publishedAt":19},"01M73YC29YWGCW521P7B0NM3HQ","earth2studio-data-fetch","Fetch weather\u002Fclimate data via Earth2Studio data sources for specific variables and times. Do NOT use for inference pipelines, model discovery, or installation.","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fearth2studio-data-fetch\u002FSKILL.md",[],[],{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":154,"sourceHtmlUrl":155,"categories":156,"keywords":165,"publishedAt":183},"01M71QDV4DM8T19HEHWATEF1K4","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[157,162],{"categoryNo":158,"categoryName":159,"taxonomyType":160,"taxonomyTypeDesc":161},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":163,"categoryName":164,"taxonomyType":160,"taxonomyTypeDesc":161},"01JBSEEDCAT000000000000009","前端开发",[166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182],"webapp testing","testing","webapp","for","applications","local","frontend","debugging","toolkit","logs","browser","with","playwright","web","behavior","ui","screenshots","2026-11-10 13:02:02",{"skillNo":185,"name":186,"nameZh":6,"description":187,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":188,"sourceHtmlUrl":189,"categories":190,"keywords":192,"publishedAt":183},"01M71QDH2GGMXGA9105C9W1N7B","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fweb-artifacts-builder\u002FSKILL.md",[191],{"categoryNo":163,"categoryName":164,"taxonomyType":160,"taxonomyTypeDesc":161},[193,179,194,195,196,197,198,172,199,200,201,202,203,204,205,206,207,208,209,169],"web artifacts builder","artifacts","artifacts builder","builder","ui components","Tailwind","single","use","file","components","react","multi","state","routing","state management","single-file","css",{"skillNo":211,"name":212,"nameZh":6,"description":213,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":214,"licenseFileUrl":215,"sourceHtmlUrl":216,"categories":217,"keywords":219,"publishedAt":183},"01M71QD9T2XC3EWMQNN9ACNWQ1","vueuse-functions","Apply VueUse composables where appropriate to build concise, maintainable Vue.js \u002F Nuxt features.","MIT","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fvueuse-functions\u002FLICENSE.md","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fvueuse-functions\u002FSKILL.md",[218],{"categoryNo":163,"categoryName":164,"taxonomyType":160,"taxonomyTypeDesc":161},[220,221,222,223,224,225,226,227,228,229,230,231,232,233],"vueuse functions","vueuse","functions","concise","project","nuxt","apply","github","build","https","features","vue","js","composables",{"skillNo":235,"name":236,"nameZh":6,"description":237,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":214,"licenseFileUrl":238,"sourceHtmlUrl":239,"categories":240,"keywords":243,"publishedAt":183},"01M71QD51HWSGYMCMB7RW7PGK8","vue-testing-best-practices","Use for Vue.js testing. Covers Vitest, Vue Test Utils, component testing, mocking, testing patterns, and Playwright for E2E testing.","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fvue-testing-best-practices\u002FLICENSE.md","https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fvue-testing-best-practices\u002FSKILL.md",[241,242],{"categoryNo":158,"categoryName":159,"taxonomyType":160,"taxonomyTypeDesc":161},{"categoryNo":163,"categoryName":164,"taxonomyType":160,"taxonomyTypeDesc":161},[167,244,231,245,246,247,248,200,249,232,250,169,251,227,252,253,254,255,178],"best practices","testing best practices","vue testing best practices","e2e","utils","patterns","e2e testing","vitest","mocking","component","testing patterns","test"]