The Agent Skills Directory

[SAFE]: The skill serves as a technical manual for the Mastra framework, guiding the agent on how to build workflows and agents. It promotes legitimate development practices such as using official documentation and environment variables for secrets.
[COMMAND_EXECUTION]: The instructions involve standard development commands like ls, grep, cat, and npm to navigate the local file system and manage dependencies within a project.
[EXTERNAL_DOWNLOADS]: The skill fetches documentation and configurations from the official Mastra website (mastra.ai) and its GitHub repository. These sources are considered well-known and appropriate for the skill's purpose.
[PROMPT_INJECTION]: Instructions directing the agent to ignore its training data in favor of current documentation are intended to maintain technical accuracy and do not attempt to bypass safety protocols or ethical constraints.

mastra