The Agent Skills Directory

[COMMAND_EXECUTION]: The skill makes extensive use of system commands including git, gh (GitHub CLI), and glab (GitLab CLI) to manage repository state, create commits, and open pull/merge requests. These capabilities are essential for the skill's primary function but represent a broad execution surface.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the repository and platform APIs which could be used to influence the agent's planning or commit generation.
Ingestion points: Pull request metadata via gh pr view/glab mr view, and repository configuration files like CODEOWNERS, CONTRIBUTING.md, AGENTS.md, and CLAUDE.md.
Boundary markers: None identified; external content is processed directly to determine ownership and coding conventions.
Capability inventory: Full repository access including branch creation, commit creation, and remote pushing (git push, gh pr create, glab mr create). It also uses file system tools like mktemp, cp, and rm.
Sanitization: There is no explicit instruction to sanitize or escape data retrieved from external sources before using it in planning or command construction.
[EXTERNAL_DOWNLOADS]: The skill performs network operations to fetch metadata and repository content from GitHub and GitLab. These operations are directed at well-known, trusted developer platforms and are necessary for the skill's stated purpose.

split-pr