The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the arboreto library and its dependencies (scipy, scikit-learn, numpy, pandas, dask, distributed) from standard package registries. These are well-known libraries in the scientific and data science communities.
[COMMAND_EXECUTION]: The skill provides a dedicated Python script (scripts/basic_grn_inference.py) and various code examples designed to be executed in a local or distributed Python environment to process genomic data.
[INDIRECT_PROMPT_INJECTION]: The skill processes gene expression data from external TSV files, representing a potential surface for indirect prompt injection if the resulting data or logs are interpreted by an LLM.
Ingestion points: Untrusted external data is ingested via pd.read_csv in scripts/basic_grn_inference.py and other workflow examples.
Boundary markers: The skill does not implement specific boundary markers or instructions to ignore embedded prompts within the input data files.
Capability inventory: The skill possesses the capability to write files to the local disk and establish network connections via Dask clients.
Sanitization: No specific sanitization or validation is applied to gene names or metadata within the input TSV files before they are processed or displayed.

arboreto