endurance-coach-change-controllisted

Load this BEFORE making ANY code change to the Endurance Coach repo — it is the constitution for how work lands. Triggers: "can I commit this", "how do I ship", "is this gated", "what's the definition of done", "what are the rules here", "am I allowed to", classifying a change (display-only vs behavioural vs write-path vs schema vs config vs profile), before touching the write path / dashboard HTML / config (`config.ts`, `.env.example`) / `profile.local.yaml` / any AI Endurance write / the LLM coach flows / the wellbeing gate, "should this be behind a flag", "does this need a test", "which docs move with this code", "can I edit main directly", "my commits landed on main", worktree/branch hygiene, "should I hard-code a training rule", "can I override what AI Endurance says", "can I rebuild the load model". This skill OWNS the change-classification table, the definition of done, the four gates every change passes (green-before-commit, propose→confirm write gate, wellbeing gate, branch-then-ship), and the three
maxeskell/personal-training-app · ★ 0 · AI & Automation · score 70

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

# Endurance Coach — change control (the constitution) **Use this when** you are about to change ANY code, config, doc, profile field, or write path in this repo — to classify the change and route it through the right gate before you commit. **Don't use this when** you need to *operate* the app (ship mechanics, services → `endurance-coach-run-and-operate`), *diagnose a live break* (`endurance-coach-debugging-playbook`), check *whether a past fix already settled a question* (`endurance-coach-failure-archaeology`), or prove a *statistical* finding (`endurance-coach-validation-and-qa`, `endurance-coach-n1-validation-campaign`). The repo is a **local-first, single-athlete AI endurance coach** at `/Users/maxeskell/dev/personal-training-app` (TypeScript, ESM, Node ≥20, run via `tsx`; no database, flat JSON under `data/`). Jargon defined once as it appears. Everything below is verified against the repo on 2026-07-04 — see **Provenance and maintenance** for the re-check commands. --- ## 0. The one-paragraph mental model Every change lands the same way: **branch → make the change WITH its docs → run the green gate → commit → ship.** Four gates stand in the way, and no change may route around any of them: | Gate | What it protects | Where it lives | |------|------------------|----------------| | **Green-before-commit** | Nothing broken ships | `npm run typecheck && npm test` (must pass locally) | | **Propose→confirm write gate** | No AI Endurance (AIE) write fires without explicit