The Agent Skills Directory

[SAFE]: The skill contains instructional content and behavioral protocols for managing code review feedback without providing any executable scripts, remote dependencies, or configuration files.- [COMMAND_EXECUTION]: The instructions describe the use of the grep command to search the codebase for feature usage as part of a 'YAGNI' (You Ain't Gonna Need It) check. This is a standard read-only developmental operation used for verifying technical requirements.- [PROMPT_INJECTION]: The skill processes data from external reviewers, creating a surface for indirect prompt injection. Ingestion points: Feedback from external sources. Boundary markers: No explicit data delimiters are defined, though the skill mandates a skepticism-first behavioral approach ('be skeptical, but check carefully'). Capability inventory: Employs grep for code analysis and implies the ability to modify local code files. Sanitization: No explicit sanitization or filtering of input data is mentioned. The skill's primary focus is providing a defensive layer against blindly following external instructions.

receiving-code-review