plan-adjuster
Recomputes upcoming workouts based on recent runs and user feedback. Use when recent performance deviates from plan, user provides negative feedback, or recovery signals indicate adjustment needed with deterministic safety caps.
When & Why to Use This Skill
The plan-adjuster skill enables dynamic, data-driven training plan optimization by recomputing workout schedules based on real-time performance and user feedback. It solves the problem of rigid training schedules by providing adaptive adjustments that account for fatigue, injury, and performance trends, ensuring a safer and more effective training journey through deterministic safety guardrails.
Use Cases
- Performance-Based Plan Scaling: Automatically increasing or decreasing the intensity of future workouts when recent run telemetry indicates the user is deviating from their target pace or fitness level.
- Fatigue-Responsive Adjustments: Modifying the training calendar to prioritize recovery or suggest rest days when user feedback signals high RPE (Rate of Perceived Exertion), poor sleep quality, or physical soreness.
- Safety-Gated Training Modifications: Applying deterministic safety caps to prevent overtraining while providing actionable recovery recommendations and change logs for future sessions.
| name | plan-adjuster |
|---|---|
| description | Recomputes upcoming workouts based on recent runs and user feedback. Use when recent performance deviates from plan, user provides negative feedback, or recovery signals indicate adjustment needed with deterministic safety caps. |
| short-description | Adaptive adjustment of future sessions with change logs and recovery tips. |
When Claude should use this skill
- Nightly job or immediately after a run is logged
- When the user reports fatigue/injury or requests easier/harder weeks
- When performance data indicates plan adjustment is needed
Invocation guidance
- Load
Plan,Workout,TrainingHistory, andRecentRunTelemetry[]. - Apply deterministic ceilings from
v0/lib/planAdaptationEngine.tsandv0/lib/plan-complexity-engine.tsbefore calling the model. - Return
Adjustment[], optionalRecoveryRecommendation, andconfidence.
Input schema (JSON)
{
"profile": UserProfile,
"currentPlan": Plan,
"trainingHistory": TrainingHistory,
"feedback": { "rpeTrend"?: number, "soreness"?: string, "sleepQuality"?: string }
}
Output schema (JSON)
{
"appliedAt": string,
"updates": Adjustment[],
"recovery"?: RecoveryRecommendation,
"confidence": "low" | "medium" | "high",
"safetyFlags"?: SafetyFlag[]
}
Integration points
- API:
v0/app/api/plan/adjust(to add), or chat-triggered adjustments. - Logic:
v0/lib/planAdjustmentService.ts,v0/lib/planAdaptationEngine.ts. - UI: Plan/Today screens (badge adjusted sessions) and notifications via
v0/lib/email.ts.
Safety & guardrails
- Never rewrite completed history; adjust only future sessions.
- If fatigue/injury signals present, lower intensity/volume and consider rest-day insertion.
- Emit
SafetyFlagon unsafe load proposals; clamp to deterministic caps.
Telemetry
- Emit
ai_skill_invokedandai_adjustment_appliedwithadjustments_count,confidence,safety_flags.