The Agent Skills Directory

[COMMAND_EXECUTION]: The skill involves executing Python code that interacts with laboratory hardware through specific backends like Hamilton STAR and Opentrons OT-2. These operations are primary to the skill's intended use in lab automation.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of the 'pylabrobot' library from PyPI and refers to its official GitHub repository for source code and documentation.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its processing of untrusted external data. • Ingestion points: Data enters the agent's context through JSON files for deck layouts ('Deck.load_from_json_file') and measurements from analytical devices like plate readers and scales. • Boundary markers: The instructions lack explicit boundary markers or warnings to disregard embedded instructions within these data sources. • Capability inventory: The skill has extensive capabilities including hardware manipulation (aspirate, dispense, centrifuge control), network requests for robot communication, and file system writes for data export. • Sanitization: No validation or sanitization procedures are outlined for the content of resource configuration files or incoming instrument data.

pylabrobot