The Agent Skills Directory

[PROMPT_INJECTION]: The skill uses slash commands like /think and /verify to structure the AI's internal reasoning process. No patterns were found that attempt to bypass safety filters or override core agent instructions.
[REMOTE_CODE_EXECUTION]: No scripts, external package dependencies, or remote code download patterns were detected.
[DATA_EXFILTRATION]: No network access commands or sensitive data access patterns (such as reading credentials or SSH keys) are present in the skill.
[COMMAND_EXECUTION]: The skill is composed entirely of natural language instructions and does not perform any system-level command execution or subprocess spawning.
[NO_CODE]: This skill is strictly a set of prompting instructions (YAML and Markdown) and does not deliver any executable software components.

meta-prompting