endurance-coach-external-positioninglisted

Load this before writing or reviewing ANY outward-facing claim about the Endurance Coach project — a release note, blog post, README pitch, changelog, conference talk, paper abstract, tweet, "is this novel?" question, or a competitive comparison against AI Endurance (AIE), TrainingPeaks, Humango, intervals.icu, Strava, or Garmin. Triggers: "is this novel / original / state of the art", "can we claim X publicly", "how do we compare to <platform>", "what's our differentiator / edge / moat", "write the launch / release / marketing copy", "positioning", "one-pager", "elevator pitch", "what must be proven before we say this", "reproducibility statement", "is this overselling", or editing docs/PRODUCT.md, README's positioning/non-goals sections, or the "Principles" list. Also load it whenever a draft is about to state a performance-prediction claim, a "better than <competitor>" claim, or an "n=1 causal proof" claim — those three are the ones most likely to overreach. Do NOT load this for the open research problems
maxeskell/personal-training-app · ★ 0 · AI & Automation · score 70

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

# Endurance Coach — external positioning **Use this when** you are writing or reviewing anything the outside world reads about this project (release note, blog, README pitch, changelog, talk, paper, comparison table) and you need to know what is genuinely novel, what is standard practice dressed up, what must be proven before it can be claimed, and where this app is deliberately *worse* than the competition. **Don't use this when** you want the open research problems themselves (→ `endurance-coach-research-frontier`) or the internal mechanics of when a finding counts as proven (→ `endurance-coach-research-methodology`). This skill decides **what may be said publicly and the gate every claim clears first** — it consumes the evidence bar those siblings define; it does not redefine it. **One rule above all: no oversell.** The house voice is honest to a fault. Anything unproven ships labelled `MODEL` / `estimate` / `candidate` / `exploratory`. If a claim would embarrass the maintainer when a skeptic checks it, cut it or downgrade it. A wrong public claim is worse than a modest one. Jargon, defined once: - **AIE** — AI Endurance (https://aiendurance.com), the paid platform that is this app's data spine. Its ML sets adaptive training volume, race-finish predictions, and a recovery model. - **n=1** — statistics on a single athlete's own longitudinal data, rather than group averages. - **CTL / ATL / TSB** — chronic / acute training load and training-stress balance (fitness / fa