The Agent Skills Directory

[COMMAND_EXECUTION]: The examples/quantify_splicing.py script uses subprocess.run to execute external bioinformatics CLI tools like suppa.py. The script follows security best practices by passing arguments as a list rather than a shell string, mitigating common command injection risks.
[INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface for indirect prompt injection as it is designed to ingest and process biological data files such as GTF, BAM, and TPM files.
Ingestion points: The example script reads data from external files using pd.read_csv in the filter_reliable_events and parse_rmats_output functions.
Boundary markers: No specific delimiters or safety instructions are used to separate biological data from agent instructions, though this is typical for research software.
Capability inventory: The skill possesses the capability to read files from the filesystem and execute system commands via the subprocess module.
Sanitization: The provided examples do not implement sanitization or validation of the internal content of processed data files.
[EXTERNAL_DOWNLOADS]: The skill provides instructions for installing dependencies from well-known bioinformatics sources and official repositories.
Evidence: The usage-guide.md documentation includes commands for installing software via pip (PyPI), conda (Bioconda), and devtools (GitHub).

bio-splicing-quantification