The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute 'csvtk' subcommands in the shell to perform data manipulation tasks like filtering, joining, and sorting tabular data.
[INDIRECT_PROMPT_INJECTION]: The skill handles untrusted external data in the form of CSV, TSV, and Excel files.
Ingestion points: Input files processed by subcommands like grep, filter, and join (documented in SKILL.md).
Boundary markers: The skill establishes strict rules requiring explicit format definitions (e.g., -t for TSV) to prevent incorrect data interpretation.
Capability inventory: Shell execution of 54 different csvtk subcommands for data processing.
Sanitization: The references/traps.md file provides extensive documentation on avoiding silent parsing errors and ensures the agent treats input data with specific, safe configurations.

csvtk