The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown instructions and lacks any executable scripts, tools, or remote dependencies. It functions purely as a prompt template for generating textual checklists based on pull request context.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external pull request changes, which constitutes a theoretical injection surface. However, the risk is negligible as the skill lacks any capabilities for command execution, file system access, or network operations.
Ingestion points: Pull request changes and file lists are processed as described in SKILL.md.
Boundary markers: None.
Capability inventory: No tools or scripts are defined within the skill.
Sanitization: None.

pr-checklist