The Agent Skills Directory

[SAFE]: The skill provides instructions for the agent to perform a static, reasoning-based review of source code files (modbus, opcua, mqtt) to ensure they comply with naming, timestamping, and database write standards defined in CLAUDE.md.
[SAFE]: No remote code execution or external downloads were detected. The skill operates entirely on local project files such as tag_database.csv, register_map.csv, and config/{client}.yaml.
[SAFE]: No hardcoded credentials or sensitive data exposure patterns were found. The instructions for writing to the database use a pre-existing DBWriter abstraction rather than raw connection strings or secrets.
[SAFE]: No obfuscation, persistence mechanisms, or privilege escalation attempts were identified.

validate-contract