load-anomaly-guard
检测训练负荷中的不安全峰值,并发出安全标志,进行保守的调整。
📖 中文导读:检测训练负荷中的不安全峰值,并发出安全标志,进行保守的调整。 以下正文为该技能的原始 SKILL.md 内容(英文),上方安装命令可直接使用。
name: load-anomaly-guard description: Detects unsafe spikes in training load and emits SafetyFlags with conservative adjustments. metadata: short-description: Background load monitor that flags spikes and proposes protective changes.
When Codex should use it
- Nightly background check on training data.
- Immediately after a high-intensity or long run is logged.
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.