Agent Skills
› ruvnet/RuView
› calibrate-room
calibrate-room
GitHub执行房间校准流水线，通过基线采集、人员注册及模型训练，构建针对特定房间的感知专家模型，用于实时监测存在、姿态、呼吸等生理指标。
Trigger Scenarios
需要为新的物理空间部署或更新AI感知模型
执行传感器数据校准与特征提取流程
Install
npx skills add ruvnet/RuView --skill calibrate-room -g -y
SKILL.md
Frontmatter
{
"name": "calibrate-room",
"description": "Run the ADR-151 per-room calibration pipeline — baseline → enroll → extract → train → a bank of small specialists (presence\/posture\/breathing\/heartbeat\/restlessness\/anomaly)."
}
calibrate-room
Turn a provisioned node + sensing-server into a working room model. Pure-Rust,
edge-deployable (ADR-151). Use the ruview_calibrate tool (installed
wifi-densepose binary, else cargo run -p wifi-densepose-cli).
Sequence
- baseline — capture the empty room (Welford amplitude + von Mises phase). Leave
the room empty.
ruview_calibrate {step: "baseline"} - enroll — record the occupant(s) doing the target activities.
ruview_calibrate {step: "enroll"} - train-room — train the bank of small specialists from baseline + enrollment.
ruview_calibrate {step: "train-room"} - room-watch — live presence/posture/breathing from the trained room.
ruview_calibrate {step: "room-watch"}(or theroom-watchskill)
Honesty
The specialists are calibrated to this room; cross-room transfer is a separate
problem (LoRA recalibration, ADR-079 P9). Report which room a number came from, and
tag presence/vitals accuracy MEASURED only with a held-out check — run
ruview_claim_check on the writeup.
Version History
- a3b6e1d Current 2026-08-20 13:11
