The Agent Skills Directory

[SAFE]: The skill defines a mandatory 'Announce-Show-Wait-Apply-Verify' protocol designed to prevent autonomous or accidental code changes. This micro-step approach ensures all agent actions are transparent and user-authorized.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform legitimate development tasks such as running test suites and linters. This execution is scoped to the current project context and is part of the verification step in the collaborative workflow.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface as it reads and processes project files. However, the risk of indirect prompt injection (where instructions hidden in code influence the agent) is significantly mitigated by the requirement for the agent to display all proposed changes for manual user review before application.

pair-programming