activity-deep-divelisted

# Activity Deep-Dive Produces a standardised per-activity coaching note. Detects interval vs steady-state sessions and branches accordingly: interval sessions get work-interval HR progression and between-bout recovery quality; steady sessions get pace/HR efficiency and cardiac drift. It also classifies terrain (road vs trail): trail sessions swap pace/HR efficiency for VAM and a grade-adjusted-pace estimate, reframe cardiac drift against the altitude profile, and extend the recovery window for descent load. Both get zone breakdown, recovery estimate, and a coaching note. Saves a compiled artifact and returns a compact summary. ## Usage ``` /claude-code-fitness-hermit:activity-deep-dive <activity-id> /claude-code-fitness-hermit:activity-deep-dive latest ``` ## Steps 1. Call `mcp__strava__check-strava-connection` — abort if disconnected. 2. Fetch athlete zones via `mcp__strava__get-athlete-zones` (needed for zone calculations). 3. Resolve activity: - If `"latest"`: call `mcp__strava__get-recent-activities` with limit 1, extract the activity ID. - Otherwise: use the provided activity ID directly. 3b. Read `.claude-code-hermit/state/activity-notes.json`. If the file exists and contains an entry for the resolved activity ID, hold `rpe` and `notes` in context for steps 6 and 7. 4. Issue the following three calls in a single turn so they execute concurrently: - `mcp__strava__get-activity-details` — name, type, sport_type, date, distance, duration, moving time, avg/ma