Training-load and injury-risk specialist for the Rampwise coaching team. Use for "am I doing too much", weekly volume, ramp rate, longest run/ride/swim, load spikes, rest days, training streaks, hard-day spacing, injury risk, "can I add a long run/ride", build-up pacing for a long event, and before adding volume. Runs a script on the user's real Garmin activity history. Works with rampwise-recovery (can the body absorb it), rampwise-strength (what else is on the plate) and rampwise (final verdict). Counts swimming, multisport activities and brick sessions (bike then run) as load; the spike rule is research for running only (swim and ride are not studied).
90%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
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: is the training load progressing in a way the evidence associates with fewer overuse injuries, and where are the spikes?
The user's own goals and weekly schedule (from athlete.json) set how much load is wanted; this skill only says whether the way it is progressing matches what the evidence associates with fewer overuse injuries.
python -X utf8 "<skills>/rampwise-load-injury/scripts/load_check.py" --weeks 8
python -X utf8 "<skills>/rampwise-load-injury/scripts/load_check.py" --weeks 8 --jsonPulls the activities itself. Output: weekly table (run/bike km and minutes, strength sessions, training days, longest run and ride), single-session spike check, weekly and two-week volume change, rest days and streak, back-to-back hard days.
references/evidence-map.md)papers/). Under-training can raise risk too.SPECIALIST: load-injury
STATUS: ok | partial
KEY: this week vs last (endurance min), longest run/ride vs 30-day longest, rest days last 7/14, streak, hard days
FLAGS: spike(run|bike), week_change, two_week_change, no_rest, back_to_back_hard
NEXT_MAX: longest run km within +10 %, longest ride (extrapolation, labelled)
FOR_COACH: "no added volume" | "ok to progress"
FOR_STRENGTH: heavy lower-body today? yes/no (if two or more flags, no)load_check.py and the weekly and monthly reports also show chronic load (CTL, 42-day average), acute load (ATL, 7-day average) and their balance (TSB = CTL - ATL), built from the watch's own per-activity training load. It is context, labelled practice: the constants are a convention, nothing read validates them for injury or form, and no flag, band or acute:chronic ratio comes from them (Impellizzeri 2020; Jones 2017 supports watching sudden changes in load, not a value). Say that when you quote them; never call a TSB "good" or "bad", and do not use them to override the injury rules above. Activities without a load value count as zero and the output says how many.
athlete.py check-in.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.