The Agent Skills Directory

[SAFE]: The skill contains instructional guidelines for software development workflows designed to prevent hallucinations and errors in multi-step tasks.
[COMMAND_EXECUTION]: The skill suggests using platform-provided tools such as grep_files, read_file, and agent_spawn for workspace inspection and task management. These operations are consistent with the skill's stated purpose of improving coding task reliability and do not involve unauthorized shell execution.
[PROMPT_INJECTION]: The instructions are focused on task performance and accuracy. No patterns of safety bypass, role-play injection, or behavior overrides were detected.
[DATA_EXFILTRATION]: No network operations or attempts to access sensitive system files (e.g., credentials, SSH keys, or environment variables) were detected. All file access described is directed towards project source code.

v4-best-practices