The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes local shell commands to facilitate the code refactoring workflow.
Employs git rev-parse, git diff, and git ls-files to resolve the repository context and identify target files for simplification.
Encourages the execution of project-defined verification commands, such as lint, test, and typecheck, to ensure the integrity of the refactored code.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it processes code from external files that may contain untrusted content.
Ingestion points: Workflow Step 1 and 2 involve reading repository files to determine scope and behavior baselines.
Boundary markers: The skill does not define specific delimiters to separate processed code from its internal instructions.
Capability inventory: The agent is authorized to read and write to the file system and execute local commands for testing and git operations.
Sanitization: There is no explicit sanitization of the code content; however, the skill mandates strict behavior preservation and verification steps which mitigate risk.

code-simplify