data-pipeline
Skill203 starsChanged 8 months agoMITView on GitHub
Guide agent through geospatial ETL workflows using built-in, learned, and fabricated geo tools
10 other projects use a version of this.
Adopted by
Most recently taken up by
- nisarth/claude-skills-storetheir own version, first seen Nov 8, 2026
- PuckAPI/claude-sports-analyticstheir own version, first seen Oct 14, 2026
- kensaurus/cursor-kenjitheir own version, first seen Oct 1, 2026
- kensaurus/skillstheir own version, first seen Oct 1, 2026
- khuynh22/agent-dev-teamtheir own version, first seen Aug 31, 2026
- changocr/agents-labtheir own version, first seen Jul 31, 2026
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
- claude-office-skills/skills★ 433same name
- kensaurus/cursor-kenji★ 9same name
- kensaurus/skills★ 9same name
- khuynh22/agent-dev-team★ 9same name
- PuckAPI/claude-sports-analytics★ 3same name
- leezhuuuuu/skills★ 1same name
- nisarth/claude-skills-store★ 1same name
- samarth777/modal-skills★ 1same name
- changocr/agents-lab★ 0same name
- erdcpatel/agent-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository2 other files it gives its agents.
- remote-sensingSkill
- spatial-analysisSkill
The file
We split this skill into the rules it gives an agent
11 rules. 0 are common, 6 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill for geospatial ETL tasks: ingest, normalize, convert, reproject, and prepare datasets for analysis.
- Very specific: line 11
Start by locating candidate datasets with geo_data_catalog, then inspect them with geo_info and geo_crs_detect.
- Very specific: line 14
Before composing a new ETL flow, inspect whether pipelines/geo/ already contains a similar learned sequence for the same transformation …
- Very specific: line 17
Use geo_process when the workflow needs reprojection, clipping, or batch GDAL/OGR steps.
- Very specific: line 18
Use geo_format_convert for direct format changes.
- Distinctive: line 21
When the pipeline targets PostGIS, inspect the codebook before composing custom SQL:
- Very specific: line 30
If the ETL step is repetitive and not covered by learned pipelines or built-in geo tools, fabricate a persistent workspace tool under …
- Distinctive: line 34
Prefer learned pipelines before inventing a fresh ETL sequence.
- Distinctive: line 35
Prefer GeoPackage for intermediate vector outputs.
- Distinctive: line 36
Prefer GeoTIFF for intermediate raster outputs.
- Distinctive: line 37
Keep intermediate and final outputs inside the workspace.
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Data Pipeline Workflow
Use this skill for geospatial ETL tasks: ingest, normalize, convert, reproject, and prepare datasets for analysis.
Step 1: Discover and Inspect Inputs
Start by locating candidate datasets with geo_data_catalog, then inspect them with geo_info and geo_crs_detect.
Step 2: Reuse Learned Pipelines First
Before composing a new ETL flow, inspect whether pipelines/geo/ already contains a similar learned sequence for the same transformation goal.
Step 3: Normalize CRS and Format
Use geo_process when the workflow needs reprojection, clipping, or batch GDAL/OGR steps.
Use geo_format_convert for direct format changes.
Step 4: Reuse Verified SQL Patterns First
When the pipeline targets PostGIS, inspect the codebook before composing custom SQL:
geo_sql_codebook(action="list", intent="<pipeline validation goal>")
geo_sql_codebook(action="render", pattern="<pattern_name>", values={...})
geo_spatial_query(action="schema")
geo_spatial_query(action="query", sql="SELECT ...")Step 5: Fabricate a Reusable Pipeline Tool
If the ETL step is repetitive and not covered by learned pipelines or built-in geo tools, fabricate a persistent workspace tool under tools/geo/.
Conventions
- Prefer learned pipelines before inventing a fresh ETL sequence.
- Prefer GeoPackage for intermediate vector outputs.
- Prefer GeoTIFF for intermediate raster outputs.
- Keep intermediate and final outputs inside the workspace.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.