Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mkurman/omop-ohdsi
OHDSI (Observational Health Data Sciences and Informatics) OMOP Common Data Model. Tools for converting EHR data to OMOP CDM, running cohort analyses, and population-level estimation. Standard for observational research.
Passed 21 of 23 test cases with the skill, and 18 of 23 without it.
and 2 more in the full report
4 fixed17 passed either way1 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am setting up a Python environment for OHDSI covariate construction. I usually run `pip install scikit-learn` or `pip install FeatureExtraction`. What exact command using `uv` package manager should I run to install the official OHDSI feature extraction library?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies the command uv pip install ohdsi-feature-extraction | Missed | Passed |
The instructions your model reads when the skill loads.
OHDSI (Observational Health Data Sciences and Informatics) provides tools for converting EHR data to the OMOP Common Data Model, running cohort analyses, and population-level estimation. Standard for real-world evidence research.
uv pip install ohdsi-feature-extraction
# Using the OHDSI Python API
from ohdsi_database_connector import DatabaseConnector
connection_details = {
"dbms": "postgresql",
"server": "localhost/omop_cdm",
"user": "ohdsi",
"password": "your_password",
}
conn = DatabaseConnector(connectionDetails=connection_details)
# Run a cohort SQL query
sql = "SELECT person_id, condition_concept_id, condition_start_date FROM condition_occurrence"
results = conn.querySql(sql)
test cases passed, vs 18 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.