The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the qsys-pp-cli tool using npx from the @mvanhorn/printing-press-library package and via go install from the vendor's GitHub repository (github.com/mvanhorn/printing-press-library). These actions are performed to set up the necessary environment for the skill's operations.
[COMMAND_EXECUTION]: The skill relies on executing the qsys-pp-cli binary with various arguments and flags, including an --agent mode that automates responses and outputs JSON data.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources, specifically Q-SYS product specification PDFs and configuration help pages.
Ingestion points: Commands such as product get, page get, and connect retrieve content from external product documentation sites.
Boundary markers: The instructions do not specify explicit delimiters or "ignore" instructions for the harvested content, though the CLI aims to return "clean text".
Capability inventory: The agent has the ability to execute shell commands, write to local files, and send data to network webhooks via the CLI's delivery features.
Sanitization: The skill does not describe specific sanitization or filtering protocols for the external data before it is presented to the agent.
[DYNAMIC_EXECUTION]: The skill implements an "Automatic learning" loop where task sequences (playbooks) are synthesized from the session journal and replayed in future sessions using the recall command. This involves dynamic resolution of entity slots and execution of stored command steps.
[DATA_EXFILTRATION]: The qsys-pp-cli tool includes a --deliver flag that allows routing command output to arbitrary local files (file:<path>) or external webhooks (webhook:<url>), which could be leveraged to move data out of the agent's immediate environment.

pp-qsys