The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs several static analysis tools as Ruby gems, including attractor, flog, and reek, along with their language-specific plugins. These tools are used to calculate code complexity and detect smells.
[COMMAND_EXECUTION]: The skill executes shell commands to interact with the local git repository and host platforms (GitHub and GitLab) via their respective CLIs (gh and glab). It also utilizes docker and devcontainer commands to manage ephemeral QA environments.
[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it processes untrusted content from the repository under review.
Ingestion points: PR metadata (titles, bodies) and file contents are read into the agent's context via gh pr view, glab mr view, and git show (Phase 0 in references/guide.md).
Boundary markers: The skill does not implement specific delimiters or 'ignore' instructions for the data ingested from the PR.
Capability inventory: The skill possesses significant capabilities, including shell command execution, file system access, and the ability to post comments to external platforms.
Sanitization: While the output is formatted according to Simplified Technical English, there is no specific technical sanitization of the input data before it is processed or used in narrative generation.

jr-rails-pr-tour