The Agent Skills Directory

[COMMAND_EXECUTION]: The recalc.py script invokes the LibreOffice soffice binary to recalculate spreadsheet formulas. This is performed using subprocess.run with a list of arguments, a practice that correctly mitigates the risk of shell command injection from user-provided filenames. Additionally, the script automatically manages a StarBasic macro within the local LibreOffice configuration directory to facilitate the calculation process.
[EXTERNAL_DOWNLOADS]: The skill instructions and troubleshooting guides reference standard, well-known Python packages including pandas, openpyxl, xlrd, and xlcalc for robust spreadsheet processing.
[PROMPT_INJECTION]: The skill processes untrusted data from external spreadsheet files, establishing a surface for indirect prompt injection attacks.
Ingestion points: Data enters the agent's context via pd.read_excel() and load_workbook() calls as documented in SKILL.md and the reference materials.
Boundary markers: No specific delimiters or instructions to ignore embedded instructions are used when reading data from cell ranges.
Capability inventory: The skill possesses the capability to write files to the system and execute local commands through the formula recalculation script.
Sanitization: Spreadsheet content is ingested using standard library methods without additional validation or sanitization of cell values.

xlsx