The Agent Skills Directory

[SAFE]: The skill focuses on established software engineering best practices such as the Single Responsibility Principle (SRP), DRY, and KISS to ensure code maintainability and clarity.- [COMMAND_EXECUTION]: The skill defines a set of verification scripts for various audits (security, accessibility, performance, etc.) located in the local '.agent/skills/' directory. It mandates a safety-conscious 'READ -> SUMMARIZE -> ASK' protocol, ensuring that the agent does not execute automated fixes without explicit user approval after reviewing the script output.- [PROMPT_INJECTION]: Instructions use emphatic language like 'CRITICAL' and 'MANDATORY' to prioritize coding standards. These are standard instructional reinforcements for quality control and do not attempt to bypass safety filters or override the agent's core instructions.- [DATA_EXFILTRATION]: No network exfiltration or unauthorized sensitive file access patterns were detected. Tool usage is scoped to standard project file operations (Read, Write, Edit).

clean-code