The Agent Skills Directory

[SAFE]: The skill provides structured guidelines and documentation templates for incremental code refactoring. No malicious patterns, obfuscation, or unauthorized access attempts were identified.
[NO_CODE]: No executable code, scripts, or binaries are provided with this skill; it consists entirely of instructional documentation.
[INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing external code files which serves as an entry point for untrusted data.
Ingestion points: Commands such as refactor:analyze <file> and refactor:plan <file> take user-provided file paths as input for processing.
Boundary markers: No specific delimiters or instructions for the agent to treat the code content as untrusted data are present.
Capability inventory: The skill is limited to generating documentation and logs within the .claude/logs/refactors/ project directory. It does not possess network, credential access, or arbitrary command execution capabilities.
Sanitization: The instructions do not define specific sanitization or filtering logic for the code content being analyzed.

refactor-expert