The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the arboreto library and its associated dependencies, including dask, distributed, numpy, pandas, scikit-learn, and scipy, via standard package managers like PyPI and Bioconda.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external transcriptomics data provided by the user, which presents a surface for potential indirect instructions if the ingested data is processed by an LLM.
Ingestion points: The scripts/basic_grn_inference.py script loads external TSV data files using pd.read_csv and transcription factor lists via load_tf_names.
Boundary markers: There are no explicit boundary markers or instructions defined to prevent the agent from interpreting content within these data files as instructions.
Capability inventory: The skill possesses capabilities for file system writes (to_csv) and parallel/distributed execution through the Dask framework.
Sanitization: The data ingestion process does not implement specific sanitization or validation routines for non-numeric content within the input files.

arboreto