The Agent Skills Directory

[NO_CODE]: The skill is entirely composed of Markdown instructions and lacks any executable scripts, hooks, or configuration files that could run code automatically during installation or runtime.\n- [SAFE]: The skill does not request or perform any network operations, nor does it attempt to access sensitive system files or credentials. It functions purely as a planning template generator.\n- [SAFE]: Analysis of the skill's content found no evidence of prompt injection, obfuscation, privilege escalation, or persistence mechanisms. The documentation additionally promotes security best practices by encouraging users to manually review source updates via Git before applying them.

blueprint