Train/evaluate WiFi pose models honestly — camera-supervised (MediaPipe + CSI) and camera-free (WiFlow), always checked against the mean-pose baseline before any PCK is quoted.
82%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
Build a CSI→pose model without overstating it. The project has a retracted 92.9%/100% history — the discipline below exists so it never recurs.
A pose model that always predicts the dataset's mean pose already scores ~50% PCK. Quote PCK only as a delta over that baseline, on a held-out split with no subject or temporal leakage. Example honest result (ADR-181):
Held-out PCK@20 59.5% vs a 50% mean-pose baseline = +9.4 pp real signal — MEASURED.
npx @ruvnet/ruview train-plan --mode pose-smoke # command, cwd, outputs; runs nothing
npx @ruvnet/ruview train --mode pose-smoke --confirm # SYNTHETIC pipeline smoke (libtorch 2.11 for tch 0.24)
npx @ruvnet/ruview train --mode pose --data-dir <in-repo MM-Fi dir> --confirm
npx @ruvnet/ruview train-gate --file eval-report.json # mean-pose baseline + leakage gateThe gate returns the only acceptable claim sentence. Quote nothing it fails.
(model − baseline) in pp, with the split definition (chronological /
blocked-gap / grouped-bucket; no leakage).ruview_claim_check the writeup — it flags any untagged or 100%/perfect claim.ruvnet/RuView
3bae24a
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.