The Agent Skills Directory

[SAFE]: The skill acts as an instructional framework for generating task-oriented prompts. It does not contain any executable scripts, obfuscated payloads, or persistence mechanisms. The instructions explicitly state that the skill generates copyable prompts and does not execute them without separate user authorization.
[EXTERNAL_DOWNLOADS]: The 'Deep Research' component provides a methodology for the agent to fetch documentation and best practices from reputable sources such as official vendor sites, GitHub, and academic repositories. These operations are performed using the agent's built-in tools for the purpose of informing strategic task planning.
[COMMAND_EXECUTION]: The skill incorporates local project analysis (e.g., checking git history or running tests) into its verification step. These actions are intended for context gathering and validation within standard development workflows and do not exhibit signs of malicious command injection or privilege escalation.

goalpro