activity-deep-dive

# Activity Deep-Dive Produces a standardised per-activity coaching note. All deterministic statistics (session-kind detection, terrain, zones, cadence, efficiency, cardiac drift, VAM/GAP, recovery estimate) are computed by `scripts/fitness-lab.ts` — this skill runs it once, interprets the JSON, and writes the coaching narrative. Raw Strava streams never enter context: the script fetches and reduces them; the skill only sees the reduced metrics. Interval sessions get work-interval HR progression and between-bout recovery quality; steady sessions get pace/HR efficiency and cardiac drift. 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. **Resolve subjective RPE.** Read `.claude-code-hermit/state/activity-notes.json`. If it exists and has an entry for the resolved activity ID (or, for `latest`, hold the check until step 2 returns the ID), keep `rpe` and `notes` for the output template and artifact frontmatter. The script does NOT read RPE — this is the skill's job. 2. **Run the analysis script.** Issue a single Bash call: ``` bun ${CLAUDE_PLUGIN_ROOT}/scripts/fitness-lab.t...