The Agent Skills Directory

[SAFE]: The skill provides a rigorous methodology for agent behavior during complex planning tasks, ensuring that the agent remains within the scope of coordinated multi-artifact work without spawning unauthorized subprocesses.
[SAFE]: Resource discovery using tools like credentials, nodes, and data-tables is performed for planning purposes only and follows the principle of least privilege by recommending assumptions over unnecessary user prompts.
[SAFE]: The task graph rules enforce a structured briefing format for downstream executors, which helps maintain clarity and reduces the risk of misinterpretation during workflow construction.
[SAFE]: No indicators of malicious intent, such as prompt injection attempts, obfuscated code, or unauthorized network operations, were found in the skill's instructions or metadata.
[SAFE]: The skill correctly handles external data ingestion as part of its primary coordination purpose using standard tools (parse-file, research) without introducing excessive risk.

planning