The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown instructions and guidelines. It does not contain any executable code, shell scripts, or command-line operations.
[SAFE]: No external dependencies, packages, or remote resources are downloaded or executed. All referenced content is local to the skill directory.
[SAFE]: The skill does not access sensitive files, environment variables, or hardcoded credentials. It is purely instructional.
[SAFE]: The content includes security-positive instructions, specifically advising the use of the allowed-tools field to restrict an agent's capabilities and prevent unauthorized file modifications or network access.

writing-skills