S2-SP-OS Energy Radar

S2-SP-OS Energy Radar. Maps spatial inventory and generates advanced local visual dashboards (Bar/Pie/Trend) for user insights without cloud analytics. / S2...

This skill appears to be what it says (local inventory + charts) but it also pushes the agent toward active device control and suggests downloading an on-device ML model from an unspecified source. Before installing or running it: - Review the energy.py functions that were elided (run_inventory, read_smart_breaker) to confirm they don't phone home or perform unexpected network I/O. - If you plan to use vision/edge-model features, only download models from a trusted URL (official project or vendor release); avoid arbitrary/unverified model downloads. - Be cautious about wiring RS485/Modbus hardware and about permitting cross-skill automation: if you allow the agent to invoke other skills that can actuate (cut power), require explicit user confirmation before any actuation. - Run the skill in an isolated environment (non-privileged account, limited network) until you're comfortable with behavior. If you want a safer thumbs-up, provide the full content of run_inventory and read_smart_breaker and the exact model download URL so I can re-check network calls, unknown hosts, or any code that would transmit data off the device.

Type: OpenClaw Skill Name: s2-energy-perception Version: 1.1.1 The s2-energy-perception skill is a local energy monitoring and visualization tool that uses standard libraries (pandas, matplotlib) to generate household energy reports. The code in energy.py operates entirely locally, generating PNG charts in the current directory and returning file URIs to the agent without any network exfiltration or unauthorized file access. It includes a mandatory privacy consent check via environment variables and the instructions in SKILL.md and AGENT-EXAMPLES.md are strictly aligned with the stated purpose of energy analysis and local dashboarding.