The Agent Skills Directory

[SAFE]: The skill consists exclusively of Markdown-based instructions and a template for structuring sprint data and team feedback.
[NO_CODE]: There are no executable scripts, shell commands, or network operations defined in the skill files.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data (team feedback and sprint metrics). However, because the skill lacks executable capabilities such as file system access, network requests, or subprocess execution, the risk associated with processing this data is negligible. No boundary markers were found, which is standard for purely output-oriented templates.

create-retrospective