AlvaroLaraFF/training-load
.claude/skills/training-load/SKILL.md
Compute Performance Management Chart (CTL/ATL/TSB) from the user's training history. Use when the user asks about fitness, fatigue, form, training load, or how their condition is trending.
data-ai
Updated Apr 16, 2026
$ install --global
skillsauthnpx skillsauth add AlvaroLaraFF/strava-coach training-loadInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 16, 2026, 5:41 PM24.5s3 files scanned
SKILL.md
- name:
- training-load
- description:
- >
- allowed-tools:
- Bash(python3 *), Read
training-load
Computes the Banister Performance Management Chart over the local activity history:
- CTL (Chronic Training Load, 42-day EWMA) — fitness
- ATL (Acute Training Load, 7-day EWMA) — fatigue
- TSB (Training Stress Balance = CTL − ATL) — form
Daily load is derived from each activity using power-based TSS when watts are available, otherwise a TRIMP-style HR score. Activities with neither are counted as load=0.
Pre-flight check
python3 -c "
import sys, time
sys.path.insert(0, '.')
from strava.db import load_token
from strava.client import get_default_db_path
t = load_token(get_default_db_path())
print('OK' if t else 'NO_TOKEN')
"
If NO_TOKEN, tell the user to run the strava-setup wizard first.
Pre-flight: read snapshot for flags
python3 .claude/skills/athlete-snapshot/scripts/read_snapshot.py
Extract ftp_w, hr_max_bpm, hr_rest_bpm from the snapshot and pass them
as --ftp, --hr-max, --hr-rest below. If no snapshot exists, use script
defaults.
Run
python3 .claude/skills/training-load/scripts/training_load.py --days 120
Optional flags: --days N (window length, default 120), --ftp <watts>, --hr-max <bpm>, --hr-rest <bpm> to override the autodetected values.
Present the result
Parse the JSON data block and show:
- Current state — today's CTL, ATL, TSB with a one-line interpretation:
- TSB > +10: very fresh / detrained
- TSB +5 to +10: fresh, race ready
- TSB −10 to +5: optimal training
- TSB < −10: overreached, recovery needed
- 7-day trend — CTL change, ATL change
- Key dates — fitness peak in window, lowest TSB
Post-run: update snapshot
After presenting results, persist the computed load metrics:
python3 .claude/skills/athlete-snapshot/scripts/update_snapshot.py --source training-load --ctl <CTL> --atl <ATL> --tsb <TSB>
Replace <CTL>, <ATL>, <TSB> with the values from the script output.
If the response contains alerts, show them to the user.
On error: auto-recovery chain
If the script returns "success": false, interpret the error and chain:
| Error contains | Action |
|---|---|
| No token / NO_TOKEN / StravaAuthError | Invoke skill strava-setup, then re-run this script |
| No activities / Sync first / No usable HR or power | Invoke skill strava-sync with --level summary, then re-run this script |
| anything else | Show the error to the user |
Only chain ONCE — if the second attempt also fails, surface the error.
Related Skills
AlvaroLaraFF/weekly-log
data-ai
VerifiedTrustedCommunity
Show a weekly training log: activities grouped by ISO week and sport, with totals for distance, time and elevation. Use when the user asks "what did I do this week", "weekly summary", "training log".
SKILL.mdUpdated Apr 16, 2026
AlvaroLaraFF/weather-correlation
tools
VerifiedTrustedCommunity
Cross-reference recent runs/rides with historical weather (temperature, humidity, wind) from Open-Meteo to find correlations with performance. Use when the user asks "do I run worse in the heat", "weather impact", "temperature vs pace".
SKILL.mdUpdated Apr 16, 2026
AlvaroLaraFF/tri-discipline-balance
testing
VerifiedTrustedCommunity
Show how the user's training time and volume distribute across run, ride and swim, and flag underweighted disciplines. Use when the user asks "am I balanced", "discipline balance", "which sport am I neglecting".
SKILL.mdUpdated Apr 16, 2026
AlvaroLaraFF/tri-combined-load
data-ai
VerifiedTrustedCommunity
Compute a combined CTL/ATL/TSB across run, ride and swim for triathletes. Use when the user asks "my combined load", "triathlon training load", "total TSS across sports".
SKILL.mdUpdated Apr 16, 2026