The Agent Skills Directory

[SAFE]: The skill contains only natural language instructions and philosophical guidelines. There are no executable scripts, commands, or automated actions defined within the skill.
[SAFE]: The skill explicitly includes a 'Hard boundary' section that instructs the agent to refuse requests for unauthorized access, credential theft, surveillance, or malware, reinforcing existing safety guardrails.
[SAFE]: The included external link refers to a well-known historical technical essay for reference purposes only and does not involve automated downloads or execution.

hacker-manifesto