endurance-coach-research-frontierlisted

Load this when the task is FORWARD-LOOKING research ideation for the Endurance Coach project — "where could this advance the state of the art", "what are the open research problems", "what could we publish / write a paper on", "what's the next big bet", "where is this genuinely novel", "can we do real causal inference on one athlete", "n=1 causal identification", "per-athlete intervention design", "close the dose-cycle loop", "prove which training change actually works for this athlete", "change-point detection tied to interventions", "separate heat/collinearity confounds from durability or economy", or any brainstorm about advancing beyond current features. This is the map of OPEN candidate frontiers (all labelled open/candidate, nothing achieved) with, per frontier, why current SOTA fails, the specific repo asset that makes it tractable here, the first three concrete steps naming exact files, and a falsifiable "you have a result when…" milestone. Do NOT load this to make public/marketing claims (use enduran
maxeskell/personal-training-app · ★ 0 · AI & Automation · score 70

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

# Endurance Coach — research frontier (open problems where this could advance SOTA) **Use this when** you are ideating *beyond current features*: scoping an open research problem, deciding a next big bet, judging where this project could genuinely advance the state of the art, or sketching what might be publishable. Everything here is **open / candidate** — a direction, not a shipped result. **Don't use this when** you want to: - make a public/competitive claim or write a release note → `endurance-coach-external-positioning`. - run the evidence bar, pre-registration, or the idea→adopt/retire lifecycle → `endurance-coach-research-methodology`. - execute the go/no-go validation campaign for a detector that exists *today* → `endurance-coach-n1-validation-campaign`. - derive the statistics (Fisher-z CI, FDR, permutation null, Banister) → `endurance-coach-proof-and-analysis-toolkit`. - look up what a metric *means* (CTL/ATL/TSB, EF, DFA-α1, dose-cycle) → `endurance-domain-reference`. **Jargon, defined once.** *SOTA* = state of the art. *n=1* = a study of one subject (this single athlete), so no cross-person averaging is possible. *Causal inference* = proving X *changed* Y, not merely that X and Y move together. *Confound* = a third variable (e.g. summer heat) that fakes or masks the X→Y link. *Group-average model* = a model fit across many athletes; its prediction for any one person is the crowd's mean, which can be wrong for a *non-responder* (someone whose physiology reacts u