The Agent Skills Directory

[SAFE]: The skill is entirely instructional and consists of markdown documentation and XML templates. It does not include any executable scripts, binaries, or configuration files that perform active operations.
[PROMPT_INJECTION]: The content focuses on improving task performance and output structure through the use of specific XML tags. No attempts to bypass safety filters, extract system prompts, or override agent constraints were detected.
[DATA_EXFILTRATION]: There are no commands or instructions that access sensitive file paths (e.g., SSH keys, AWS credentials) or perform network requests to external domains.
[COMMAND_EXECUTION]: The skill does not invoke shell commands, sudo, or any system-level operations. It purely provides text templates for the agent to use when interacting with another model.

gemini-prompting