The Agent Skills Directory

[SAFE]: No malicious patterns or behaviors were identified in the skill content or metadata. The provided files consist of documentation and refactoring guidelines.- [PROMPT_INJECTION]: Indirect Prompt Injection Surface: The skill is intended to read and process external code files which may contain untrusted data.
Ingestion points: The skill uses Read, Glob, and Grep tools to access project source files as defined in SKILL.md.
Boundary markers: There are no explicit instructions or delimiters used to separate user-provided code from the agent's task-specific instructions.
Capability inventory: The skill is permitted to use powerful tools including Write, Edit, and Bash to modify files and run commands as specified in SKILL.md.
Sanitization: No sanitization or filtering is applied to the code content before it is processed by the agent.

refactoring-specialist