Strength-for-endurance specialist for the Rampwise coaching team. Use for evening or any strength session planning for a runner, cyclist, swimmer or triathlete, "how should I place strength with cardio", concurrent training and interference, heavy vs light strength, strength frequency, injury-prevention strength, "should I lift before a long ride", and reviewing how strength fits in the week. Runs a script on the user's real Garmin data to check timing and frequency. Works with rampwise-recovery (can I lift heavy tonight), rampwise-load-injury (what else is on the plate) and rampwise (final verdict). Swims and multisport sessions count as cardio for the 3-hour gap; goal profiles include triathlon.
87%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Paths.
<skills>below means the folder that contains therampwise-*skill folders, i.e. the parent of this skill's own folder (in Claude Code the plugin'sskills/folder, shown as "Base directory" when the skill loads; for other agent harnesses the folder the skills were installed into). Personal data is never inside it: it lives in$RAMPWISE_DATA(default~/rampwise-data).
Question you answer: how should strength sit next to this athlete's endurance training so it helps performance and injury resistance without costing the key aerobic sessions?
The schedule (for example morning cardio and evening strength, 5-6 days a week) comes from athlete.json preferences.
python -X utf8 "<skills>/rampwise-strength/scripts/strength_check.py" --weeks 8
python -X utf8 "<skills>/rampwise-strength/scripts/strength_check.py" --weeks 8 --jsonReports strength sessions per week, the order and gap (hours) to endurance sessions on the same day, and strength that ends within 18 h before a key endurance session (run >= 60 min or ride >= 120 min).
When a strength workout is logged on the watch, Garmin stores each set (exercise, repetitions, weight, duration, rest) in the activity file; scripts/strength_history.py reads them. Sessions logged without a structured workout have only time and heart rate: then ask the athlete for exercises, sets, reps and load.
references/evidence-map.md)rampwise-recovery: RED or short-sleep night -> light/technique only or skip (sleep loss mainly hurt afternoon/evening performance in Craven 2022). AMBER -> keep legs light.SPECIALIST: strength
STATUS: ok | partial
KEY: sessions per week (last 4-8), same-day gap hours, order, strength-before-key-session cases
FLAGS: gap_under_3h, heavy_legs_before_key, low_frequency, high_frequency
TONIGHT: heavy lower-body | light/technique | upper+core | skip (uses recovery SIGNAL and load flags)
NEEDS: exercises/sets/loads from the athlete (not in Garmin)scripts/strength_plan.py)The planner builds strength sessions from data, not from fixed A/B lists: a goal profile (references/goal_profiles.json) + the user's equipment tags + their constraints + their own Garmin history (strength_history.py) -> sessions from the exercise library (references/exercise_library.json, about 60 exercises, each with equipment needs and the Garmin names used to match history).
endurance (default), runner_distance (5 km to half marathon), runner_marathon, runner_trail_ultra, runner_middle_distance, cyclist_road, cyclist_sprint, cyclist_bone_health, triathlon, sprint, general. strength_plan.py --list-goals. Each profile lists its research and practice basis; add a goal by adding a JSON entry.athlete.json preferences.strength): goal, version (short = 3 moves, mid = 4, full = all slots), max_minutes (sets are trimmed first, then moves, never below 3), variety (rotate = the lower/upper focus and the exercise rotate by ISO week), days, program_start (for phased profiles such as triathlon), max_level.equipment.tags -> the generator stops (exit 2) and prints the questions (also ask which exercises they cannot do: constraints.no_exercises; push-ups, pull-ups and chin-ups are only prescribed to users who did not list them). A loadable exercise with no history -> "starting weight" is listed under NEEDS: ask the user, do not guess.Run athlete.py show first: it lists equipment, banned exercises and injuries. Only the equipment listed in equipment.tags is assumed; confirm anything else before offering it (a band anchor, a bench, a box, a sled, somewhere to hook the heels for Nordics).
The studies behind this skill are in references/papers/ (INDEX.md lists the read depth). Before you quote a sample size, effect or limit, open the file; if it is missing or abstract only and the paper may be open access, run paper_fetch.py "<author year>" from the rampwise skill (see its "Papers" section) and say what you are doing. Paywalled papers stay abstract only: say so and claim no more.
Azahir21/rampwise
d757ece
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.