readiness-check
Pre-run safety gate that evaluates readiness and recommends proceed/modify/skip decisions. Use before scheduled workouts to assess recovery status, injury signals, and training load based on sleep, soreness, and recent activity.
When & Why to Use This Skill
The readiness-check skill serves as an intelligent safety gate designed for fitness and athletic AI agents. It evaluates a user's physical readiness for scheduled workouts by analyzing recovery metrics, injury signals, and training load. By providing data-driven 'proceed, modify, or skip' recommendations, it ensures user safety and prevents overtraining through conservative decision-making logic and proactive health screening.
Use Cases
- Pre-workout Safety Screening: Automatically assess a runner's health status and recovery levels before allowing a GPS-tracked session to start, ensuring the user is fit for the activity.
- Dynamic Training Adjustment: Modify planned workout intensity or volume in real-time when the user reports poor sleep, high fatigue, or muscle soreness to prevent burnout.
- Injury Risk Mitigation: Identify critical red flags like pain or dizziness to proactively recommend skipping workouts and advising the user to seek professional medical consultation.
- Automated Recovery Monitoring: Run nightly checks to precompute next-day readiness based on recent training history and self-reported wellness data.
| name | readiness-check |
|---|---|
| description | Pre-run safety gate that evaluates readiness and recommends proceed/modify/skip decisions. Use before scheduled workouts to assess recovery status, injury signals, and training load based on sleep, soreness, and recent activity. |
| short-description | Pre-run safety and readiness gate with conservative recommendations. |
When Claude should use this skill
- Before starting a planned workout or recording a run
- When the user reports fatigue, soreness, or poor sleep
- When user asks if they should run today or if they're ready for a workout
Invocation guidance
- Supply
UserProfile, recentTrainingHistory, andselfReport(sleep, soreness, mood). - Evaluate against load/monotony caps and health signals; prefer conservative outcomes.
- Return a readiness decision with
SafetyFlag[]and recommended modifications.
Input schema
See references/input-schema.json.
Output schema
See references/output-schema.json.
Integration points
- UI: Pre-run modal; disable GPS start if decision is
skipormodify. - API: New route
v0/app/api/run/readiness. - Background: Can run nightly to precompute next-day readiness.
Safety & guardrails
- If pain/dizziness/injury keywords detected → decision must be
skip, advise stop and consult professional. - If data missing or uncertain → default to
modify, emitSafetyFlagmissing_data. - Never provide medical diagnosis.
Telemetry
- Emit
ai_skill_invokedandai_safety_flag_raised(if any) withdecision,safety_flags,model,latency_ms.