The Agent Skills Directory

[PROMPT_INJECTION]: The skill instructs the agent to adopt an independent and critical thinking posture. These guidelines are behavioral in nature and do not attempt to bypass safety filters, ignore system instructions, or extract internal prompts.
[DATA_EXFILTRATION]: There is no evidence of network activity, credential harvesting, or access to sensitive file paths.
[REMOTE_CODE_EXECUTION]: The skill does not include any commands for downloading or executing external scripts or binaries.
[COMMAND_EXECUTION]: No shell commands or subprocess calls are present in the instructions.
[SAFE]: The skill consists entirely of natural language instructions designed to improve reasoning quality and dialogue depth without technical security risks.

deep-thinker