The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes build and test scripts defined within the repository (e.g., npm run build, yarn run test). This triggers the execution of arbitrary commands specified in the project's own configuration files.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection from the codebase it processes. Maliciously formatted comments or documentation in the target repository could potentially subvert the agent's logic during the autonomous 'polish' phase.
Ingestion points: Scans repository files using Read, Grep, and Glob tools.
Boundary markers: No specific boundary markers or instructions to disregard embedded directives are used when the agent processes file content.
Capability inventory: Includes file modification (Edit, Write), task orchestration (Task), and repository interaction via the shell (Bash for git and gh CLI).
Sanitization: No validation or sanitization of the repository content is performed before it is used to determine automated actions.
[EXTERNAL_DOWNLOADS]: Communicates with remote git hosts via git pull, git push, and gh pr create to synchronize code and manage Pull Requests.

repo-polish