The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes Python's subprocess module in several scripts (improve_description.py, run_eval.py, generate_review.py) to call the claude CLI and system utilities like lsof. This is the intended mechanism for running evaluations of other skills and managing the local visualization server.
[EXTERNAL_DOWNLOADS]: The evaluation viewer (viewer.html) loads the SheetJS library from cdn.sheetjs.com to enable the rendering of Excel files within the review interface. SheetJS is a well-known and established service for spreadsheet processing.
[DATA_EXFILTRATION]: No unauthorized network operations or credential harvesting patterns were identified. The local HTTP server started by generate_review.py binds to 127.0.0.1, restricting access to the local machine.
[PROMPT_INJECTION]: The instructions focus on the operational workflow of skill development. While it provides guidance on writing effective skill descriptions to ensure proper triggering, it does not attempt to bypass safety filters or override the agent's core instructions.

skill-creator