How does the plan-adjuster ensure user safety?

The skill applies deterministic ceilings from the planAdaptationEngine and emits safety flags if proposed loads are too high, ensuring adjustments stay within safe physiological limits.

Can this skill modify my previous workout logs?

No, the skill is strictly designed to only adjust future training sessions and will never rewrite or modify completed training history.

What data does the skill need to make adjustments?

It requires the user profile, current training plan, historical training data, and recent feedback such as RPE trends, soreness, and sleep quality.

Does it provide explanations for the changes it makes?

Yes, it returns recovery recommendations and adjustment logs to explain why a workout was modified, along with a confidence rating for the change.

Adaptive Training Plan Adjuster

Name: Adaptive Training Plan Adjuster
Author: nadavyigal

bynadavyigal

•

データサイエンスとML

Recalibrates upcoming training sessions dynamically based on recent performance, user feedback, and safety constraints.

概要

The plan-adjuster skill enables Claude to intelligently manage and optimize running training plans by analyzing recent run telemetry, user feedback regarding fatigue or soreness, and established safety limits. By integrating with deterministic adaptation engines, it provides safe, data-driven adjustments to upcoming workouts to ensure athletes stay on track while minimizing the risk of overtraining. It is ideal for developers building fitness applications that require automated, high-confidence schedule modifications and recovery recommendations.

主な機能

Integration of subjective feedback like RPE and sleep quality
Automated recovery recommendations for injury prevention
Detailed adjustment logging for transparency and auditing
1 GitHub stars
Safety-first logic with deterministic load ceilings
Dynamic workout recalibration based on real-time telemetry

ユースケース

Scaling back workout intensity after a user reports high muscle soreness
Increasing training volume following a series of high-performance runs
Injecting mandatory rest days into a plan when fatigue signals exceed safety thresholds

概要

主な機能

Integration of subjective feedback like RPE and sleep quality
Automated recovery recommendations for injury prevention
Detailed adjustment logging for transparency and auditing
1 GitHub stars
Safety-first logic with deterministic load ceilings
Dynamic workout recalibration based on real-time telemetry

ユースケース

Scaling back workout intensity after a user reports high muscle soreness
Increasing training volume following a series of high-performance runs
Injecting mandatory rest days into a plan when fatigue signals exceed safety thresholds