ecological-data-foundation

Ingest, clean, and harmonize ecological occurrence data from GBIF, iNaturalist, OBIS, and IUCN.

2|Updated Mar 2, 2026
One-click install
npx skills add https://github.com/baratadiego/ecological-agent-skills --skill ecological-data-foundation
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ecological-data-foundation
Source: https://github.com/baratadiego/ecological-agent-skills/tree/main/skills/ecological-data-foundation
Command: npx skills add https://github.com/baratadiego/ecological-agent-skills --skill ecological-data-foundation

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, numpy, pygbif, pyinaturalist, requests, and includes scripts (resource) components.

What problem does it solve?

This Skill cleans, validates, and standardizes ecological occurrence records from multiple sources, producing analysis-ready datasets and accompanying quality metadata.

Core Features & Use Cases

  • Ingest, validate, and standardize Darwin Core records from GBIF, iNaturalist, OBIS, and IUCN.
  • Apply coordinate QA, duplicate detection, taxonomic harmonization, and metadata generation to support reproducible analyses.
  • Use cases include preparing data for species distribution models, occupancy analyses, PVA, and conservation prioritization workflows.

Quick Start

Run the end-to-end cleaning workflow on a raw dataset and write the cleaned data and QA report to the output directory.

Frequently Asked Questions about ecological-data-foundation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I clean and standardize ecological occurrence data from GBIF and iNaturalist?

To clean Darwin Core occurrence records, this Skill ingests raw data from GBIF, iNaturalist, OBIS, and IUCN, applies coordinate QA, duplicate detection, and taxonomic harmonization, and outputs analysis-ready datasets with quality metadata.

Can I use this to prepare occurrence data for species distribution models?

Yes, you can prepare occurrence data for species distribution models by running the end-to-end cleaning workflow, which standardizes records and generates QA reports suitable for SDMs, occupancy analyses, and conservation prioritization workflows.

Do I need Python and R to run the Darwin Core data validation workflow?

Yes, standardizing Darwin Core occurrence data requires Python and R-based tooling to execute data ingestion, quality assurance, and taxonomic harmonization for reproducible ecological workflows.

What's the best way to harmonize taxonomy across multiple ecological occurrence datasets?

The best way to harmonize taxonomy across multiple ecological occurrence datasets is to ingest records from GBIF, iNaturalist, OBIS, and IUCN, then apply automated taxonomic harmonization to align species names into a standardized format.

Does this workflow support coordinate QA and duplicate detection for biodiversity records?

Yes, the workflow supports coordinate QA and duplicate detection for biodiversity records, automatically cleaning and validating raw occurrence data to ensure high-quality inputs for downstream conservation and ecological analyses.

How do I generate metadata reports after cleaning ecological occurrence data?

You can generate metadata reports after cleaning ecological occurrence data by running the end-to-end workflow, which writes both the cleaned dataset and a detailed quality assurance report to your output directory.