The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a Node.js utility script scripts/critique-storage.mjs used for persisting and managing design audit snapshots. This script performs file system operations to read and write reports within the .aposd/critique directory of the workspace.
[COMMAND_EXECUTION]: The skill provides shell script examples (e.g., examples/full-audit-workflow.sh) that demonstrate how to execute the audit process and interact with the persistence helper using the command line.
[DATA_INGESTION]: The skill operates by ingesting and analyzing untrusted source code provided by the user. While this creates a surface for indirect prompt injection (e.g., instructions hidden in code comments), the skill's design—which requires counting specific, observable constructs according to a strict rubric—significantly mitigates the risk of the agent deviating from its primary task.

aposd-audit