endurance-coach-n1-validation-campaignlisted

The executable, decision-gated campaign for the project's hardest live problem — proving that an insight-engine finding is REAL for THIS one athlete on noisy, single-athlete (n=1) data, not "impressive-looking nonsense". Load this when you are about to add, change, or trust a detector in src/insights/ — especially monitoring.ts, correlations.ts, efficiency.ts, or the stats.ts primitives — or when someone asks "is this signal real?", "should this ship as confirmed or exploratory?", "validate this detector/insight", "prove the monitoring rule", "why did my correlation not surface?", "this correlation looks too good", "is this FDR-confirmed?", "the CI spans zero", "walk-forward / holdout / permutation null", "did I p-hack the lag?", "is the outcome independent of the predictor?", or when reviewing a finding tagged exploratory vs confirmed. It walks Phase 0 (pre-register the hypothesis) → Phase 1 (data-sufficiency gates) → Phase 2 (run the honest estimator) → Phase 3 (confirm/exploratory decision rule) → Phase 4
maxeskell/personal-training-app · ★ 0 · AI & Automation · score 70

Install: claude install-skill maxeskell/personal-training-app

# n=1 validation campaign — is this signal real for THIS athlete? **Use this when** you are about to trust, ship, or change a finding from the insight engine (`src/insights/`) and you need a repeatable go/no-go procedure that ends in "confirmed" or "exploratory" — never a hunch. The core files are `monitoring.ts`, `correlations.ts`, `efficiency.ts`, and their shared primitives in `stats.ts`. **Don't use this when** you want: - the *derivations* of the estimators (why effective-N, why Fisher-z, why Bonferroni-before-BH, how the permutation null works) → **`endurance-coach-proof-and-analysis-toolkit`**. - the general *epistemics* (evidence bar, pre-registration template, idea lifecycle) → **`endurance-coach-research-methodology`**. - the *meaning* of a metric (what CTL/HRV/EF/decoupling is) → **`endurance-domain-reference`**. - the *test conventions and CI contract* → **`endurance-coach-validation-and-qa`**. - to *ship* the change → the gate lives in **`endurance-coach-change-control`** (this campaign routes through it at Phase 5). **Vocabulary (defined once).** *n=1* = a single athlete's own data, so group statistics don't apply and everything is autocorrelated. *Autocorrelation* = today looks like yesterday (fitness, HRV, weight all drift), which fakes strong correlations. *effective N (effN)* = the sample size after discounting for that drift — the honest count. *CI* = confidence interval; "CI excludes 0" = the effect is distinguishable from nothing. *FDR* = false-disco