The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to inspect the file system (e.g., tree -h src), run verification tools (e.g., typecheck, lint), and manage version control via git commit and git push.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes project source files which are untrusted data. * Ingestion points: Source code files within the src directory or other specified directories (as described in SKILL.md). * Boundary markers: Absent. The skill does not provide instructions to the agent to use specific delimiters or to ignore instructions embedded in the source code. * Capability inventory: The skill has the capability to modify the file system (refactoring files), execute shell commands (lint/typecheck), and perform version control operations (commit/push). * Sanitization: Absent. There is no evidence of sanitization or validation of the ingested source code content.

refactor-structure