← ClaudeAtlas

domain-brainstormlisted

On-demand fitness-voice brainstorm — reads Strava history and training-goal signals to surface at most 2 coverage-gap or imbalance ideas, each gated by proposal-triage before becoming a PROP. Invoke when the operator asks "what am I neglecting?", "anything off with my training?", or "brainstorm training gaps". Never runs autonomously.
gtapps/claude-code-hermit · ★ 60 · AI & Automation · score 81
Install: claude install-skill gtapps/claude-code-hermit
# Domain Brainstorm ## Kill criteria (read before running) After ≥8 invocations, read `.claude-code-hermit/state/proposal-metrics.jsonl` and filter events where `type:"brainstorm-emit"` and `skill:"domain-brainstorm"`. Count CREATE vs total emits with ideas (triage-survival) and read `status:` of the resulting PROP files (PROP-acceptance). If triage-survival < 25% or PROP-acceptance < 30%, cut this skill rather than tune it — signal-to-noise isn't there. ### Gate 0 — Gather inputs Start with the connection check; then read the remaining sources in parallel. Do not run tests or install tools. **Connection check** Call `mcp__strava__check-strava-connection`. If disconnected, stop immediately: ``` Domain brainstorm aborted — Strava disconnected. Reconnect and retry. ``` **Stated goals** Read `MEMORY.md` (the index). For each entry whose title or description suggests goals, training preferences, or athlete profile, read that topic file. Extract stated goals and named disciplines (e.g. "marathon training", "strength 2×/week", "sleep 8h target"). If no goals are parseable from MEMORY.md, derive implicit goals from the Strava activity mix gathered below — note in every grounding citation that the goal is inferred, not stated. **What's been logged** Delegate bulk aggregation to `@claude-code-fitness-hermit:strava-data-cruncher`: ``` Last 8 weeks of activities. Return: per-week count + total minutes by sport/activity type. Flag any sport with zero sessions in the last 4 weeks.