Stats
Actions
Tags
From running-coach
Computes adherence delta between actual and prescribed workout: pace deviation %, completion %, HR drift, RPE delta. Returns a structured signal dict. Called automatically after log-workout or fetch-strava-activity.
How this skill is triggered — by the user, by Claude, or both
Slash command
/running-coach:analyze-workoutThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Given an actual workout and its prescribed counterpart, computes a structured adherence signal dict using the threshold rules from DESIGN.md §4. The verdict (`on-target`, `under`, `over`, `aborted`) drives the downstream `adapt-plan` strike rules. This skill is never invoked directly by the user — it is always called programmatically by `log-workout` or `fetch-strava-activity`.
Given an actual workout and its prescribed counterpart, computes a structured adherence signal dict using the threshold rules from DESIGN.md §4. The verdict (on-target, under, over, aborted) drives the downstream adapt-plan strike rules. This skill is never invoked directly by the user — it is always called programmatically by log-workout or fetch-strava-activity.
log-workout captures user input.fetch-strava-activity normalizes a Strava activity.A dict {completion_pct, pace_delta_pct, rpe_delta, hr_drift_bpm, verdict} stored in workouts.json[].analysis and returned in-memory to the caller for immediate use by adapt-plan.
See body.md for full instructions and scripts/analyze.py for the deterministic delta computation.
npx claudepluginhub josix/claude-running-coach --plugin running-coachCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.