How do I install the Onboard skill?

Run npx skillmds@latest add ruvnet/onboard-3 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Onboard skill do?

Zero-to-sensing path picker for RuView (WiFi-DensePose) — pick docker-demo, repo-build, or live-esp32 and run the next concrete step. It is listed under DevOps & Infra on SkillMD.

Is Onboard safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Onboard?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Onboard free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Onboard?

ruvnet (@ruvnet) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Onboard by ruvnet — Agent Skill

Name: Onboard
Rating: 4.666666666666667 (3 reviews)
Author: ruvnet

File contents

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 → open http://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), then cargo run -p wifi-densepose-cli -- --help.
live-esp32 — a real install. Flash a node (provision-node skill), point it at the sensing-server, then calibrate-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_check on any report before you quote a number.

Source: ruvnet/RuView → harness/ruview/.claude/skills/onboard/SKILL.md

Frequently asked questions

Onboard