The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown-based instructions and reference guides. It does not include any executable scripts (.py, .js, .sh) or active code components.
[SAFE]: All command-line examples provided in the documentation (such as zip, unzip, git, and mkdir) are presented as educational material for users to manage their own skills and do not represent automated execution by the agent.
[SAFE]: No instances of prompt injection, data exfiltration, or obfuscation were found. The content focuses on best practices for prompt engineering and explicitly references adhering to the base model's safety and system guidelines.

crafting-instructions