Agent Skills
› ruvnet/RuView
› onboard
onboard
GitHub指导新用户快速搭建 RuView WiFi 感知环境，提供 docker 演示、源码构建或 ESP32 实机部署三种路径，并强调准确性验证流程。
Trigger Scenarios
新用户入职项目
需要搭建开发测试环境
初次运行 WiFi 感知应用
Install
npx skills add ruvnet/RuView --skill onboard -g -y
SKILL.md
Frontmatter
{
"name": "onboard",
"description": "Zero-to-sensing path picker for RuView (WiFi-DensePose) — pick docker-demo, repo-build, or live-esp32 and run the next concrete step."
}
onboard
Get a newcomer from nothing to a working RuView setup. First fact to set: WiFi
sensing infers coarse pose/presence/breathing from Channel State Information — it
is not a camera, and any accuracy number must be MEASURED against a baseline
(use the verify skill / ruview_claim_check tool). Never present WiFi output as
camera-grade.
Pick a path
Run ruview_onboard {path} or decide from:
- docker-demo — fastest, no hardware. Replays sample CSI into the dashboard.
docker run -p 8000:8000 ruvnet/wifi-densepose→ openhttp://localhost:8000. Use to see what it looks like. - repo-build — for developers.
cd v2 && cargo test --workspace --no-default-features(1,031+ tests pass), thencargo run -p wifi-densepose-cli -- --help. - live-esp32 — a real install. Flash a node (
provision-nodeskill), point it at the sensing-server, thencalibrate-room. This is the only path that senses a real room.
Then
- Live sensing → go to provision-node, then calibrate-room.
- Evaluating a model/claim → go to verify and run
ruview_claim_checkon any report before you quote a number.
Version History
- a3b6e1d Current 2026-08-20 13:11
