The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use standard development tools such as git (for version control), npm/bun (for JavaScript/Raycast extension workflows), and uv (for Python environment management and running project-specific tools like lintro). These commands are essential for and limited to the skill's stated purpose of managing a professional commit workflow.
[INDIRECT_PROMPT_INJECTION]: The skill involves reading and processing code changes to group them into logical commits and verify them through testing and linting. This creates an ingestion surface where the agent processes external, potentially untrusted code content. However, the instructions focus on the structural management of commits rather than executing logic derived from the code content, minimizing the risk.
Ingestion points: Reads codebase changes and status via git status and file evaluation during the lint and test phases.
Boundary markers: None explicitly defined within this skill, though it relies on external linter/tester behaviors.
Capability inventory: Uses git commit, uv run, npm run, and bun test to perform actions based on the code state.
Sanitization: No specific sanitization of the codebase content is performed before reviewing or committing.

commit