load-anomaly-guard
Detects unsafe training load spikes (>20-30% week-over-week) and emits safety flags. Use in nightly background jobs or when reviewing weekly training volume with conservative adjustment recommendations.
When & Why to Use This Skill
The load-anomaly-guard is a specialized safety skill designed to monitor and regulate athletic training volume. It automatically detects unsafe 'load spikes'—defined as a week-over-week increase exceeding 20-30%—to prevent overtraining and reduce injury risk. By analyzing training history and planned activities, it provides conservative adjustment recommendations and emits safety flags, ensuring that AI-generated fitness plans remain within safe physiological boundaries.
Use Cases
- Nightly Background Audits: Automatically scan athlete training logs every night to identify and flag any sudden increases in volume that could lead to injury.
- Post-Workout Safety Checks: Evaluate the impact of high-intensity or long-duration runs immediately after they are logged to adjust the remaining weekly schedule for safety.
- Training Plan Validation: Review proposed weekly training patterns to ensure that volume progression follows deterministic safety caps and avoids 'monotony' issues.
- Injury Prevention Guardrails: Proactively suggest rest days or activity swaps when the system detects signs of excessive fatigue or when injury signals are present in the user data.
| name | load-anomaly-guard |
|---|---|
| description | Detects unsafe training load spikes (>20-30% week-over-week) and emits safety flags. Use in nightly background jobs or when reviewing weekly training volume with conservative adjustment recommendations. |
| short-description | Background load monitor that flags spikes and proposes protective changes. |
When Claude should use this skill
- Nightly background check on training data
- Immediately after a high-intensity or long run is logged
- When analyzing weekly training load patterns for safety issues
Invocation guidance
- Provide recent
TrainingHistory, plannedPlanwindow, and any injury flags. - Compute week-over-week changes and monotony; flag spikes > deterministic caps.
- Suggest adjustments (rest/swaps) and emit
SafetyFlag[].
Input schema
See references/input-schema.json.
Output schema
See references/output-schema.json.
Integration points
- Background job: nightly cron.
- API:
v0/app/api/plan/load-guard(new) returning flags + suggested adjustments. - UI: Badge on Plan/Today screens; push/email via
v0/lib/email.ts.
Safety & guardrails
- If spike >20–30% week-over-week, emit
load_spikeand recommend rest or reduced volume. - If injury signals present, bias toward
rest-dayadjustments. - No medical diagnosis; advise professional consult on repeated spikes or pain.
Telemetry
- Emit
ai_skill_invoked,ai_safety_flag_raised, and optionallyai_adjustment_appliedwhen suggestions are auto-applied.