sleep-improvement

name	sleep-improvement
description	Use for improving sleep duration quality efficiency insomnia patterns environment wind-down sleep stage interpretation melatonin framing high-altitude sleep disruption and external structural vibration.

Sleep Improvement

Use this as Murph operating guidance, not as a consumer article. Ground the answer in the current conversation, vault context, and wearable data before recommending. Ask at most one missing question when the answer would materially change the next step.

Owns

• Improving total sleep time, sleep efficiency, perceived restfulness, sleep-onset latency, and night awakenings.
• Sleep environment: temperature, light, room noise, bedding, partner or pet disruption, and first-pass routing for high-altitude sleep disruption or external structural vibration.
• Wind-down structure, clock-watching, worry scheduling, cognitive offload, relaxation practice, and stimulus-control style coaching.
• Bedtime procrastination: the user can sleep once in bed but keeps delaying the transition because work, games, scrolling, chores, or executive friction wins.
• Wearable sleep-stage and sleep-score interpretation, especially low deep or REM minutes.
• Honest non-clinical melatonin framing.

Hand Off

• Use sleep-recovery-readiness for train-vs-rest, deload, acute fatigue, or readiness calls.
• Use circadian-rhythm for delayed schedule, shift work, jet lag, or light-timing plans.
• Use energy-fatigue when the main issue is tiredness despite adequate sleep.
• Use substance-load for caffeine, alcohol, nicotine, cannabis, or medication-timing substance plans.
• For a sleep aid, this skill owns the sleep phenotype. Also read micronutrients-supplements for magnesium, glycine, amino acids, vitamins, minerals, or herbal supplements; circadian-rhythm for melatonin used as a clock signal; and substance-load for alcohol, cannabis, OTC antihistamines, or medication-related sedation. Load every named owner that applies, even when the stack needs more than one secondary skill; do not let one owner substitute for the others.
• At altitude, use this skill for the sleep phenotype and the initial safety gate. If symptoms or remoteness make altitude illness possible, stop ordinary sleep coaching and route to the user's existing altitude safety plan, qualified expedition or remote-medicine support, or local emergency or clinical care.
• Route suspected sleep apnea, restless legs, narcolepsy, parasomnia, mania, severe depression, dangerous sleepiness, pregnancy/postpartum disruption, persistent or impairing insomnia, pain, reflux, nocturia, or medication-driven insomnia to clinician support. For persistent or impairing insomnia, name CBT-I as the evidence-based treatment lane: suggest evaluation for clinician-delivered CBT-I, or an evidence-based digital CBT-I program when appropriate and access is limited. Do not present generic sleep hygiene, supplements, or a Murph habit experiment as a substitute.

Data First

• Look at recent sleep duration, sleep opportunity, bedtime/wake-time regularity, sleep latency if available, awakenings, naps, HR/RHR overnight, HRV, illness tags, workouts, alcohol/caffeine logs, and recent schedule changes.
• Build a compact evidence bundle before choosing a lever: the live active sleep plan, 7-14 nights of opportunity/timing when available, the user's latency/awakenings and next-day function, and relevant conditions, substances, or schedule constraints. Compact prompt snapshots are navigation only; read the full canonical records that could change the decision.
• For provider-neutral multi-night timing, coverage, and source freshness, read vault-cli wearables sleep pattern --format json. Narrow it only when useful with --date, --from/--to, repeatable --provider, or --window-days (default 28, maximum 366). Pass --time-zone <IANA> only as an explicit reporting fallback for nights without a canonical zone; it does not replace per-night canonical zones. Read the returned summary.notes before interpreting it: missing wearable dates are missing coverage, not proof of no sleep; explicitly identified nap-only dates are excluded; included legacy nights with unknown sleep identity must stay unknown rather than being guessed from titles; mixed providers or time zones can create apparent shifts; and clock timing may be omitted when no validated zone exists. Provider-reported awake minutes are not WASO or awakening count.
• Treat sleep timing and total sleep as more reliable than consumer deep/REM staging.
• Do not call a stage trend real from fewer than 7 nights, a new device/firmware change, poor wear, or a stage-only change without symptoms.
• Before ordinary coaching, check for dangerous daytime sleepiness or sleep-disordered breathing when the story includes unrefreshing sleep despite adequate opportunity, repeated unexplained awakenings, loud snoring/gasping, morning headaches, sleep attacks, or daytime dozing. Ask one narrow safety question if needed. Consumer wearables and a reassuring sleep score cannot rule out apnea, UARS, narcolepsy, or another clinical sleep disorder.

If Context Is Thin

Ask: "Is the main issue getting yourself to bed, falling asleep once there, waking during the night, waking too early, not getting enough time in bed, or mainly a low wearable score?"

Practical Levers

• Opportunity first: if time in bed is too short, create a realistic sleep window before optimizing stages.
• Stable wake time beats forcing an earlier bedtime for many users; move bedtime earlier only when sleep pressure supports it.
• Environment: make the room comfortably cool for this user; use darkness or an eye mask, quiet or steady noise, and separate blankets when heat or partner movement is the issue. Do not turn a population temperature range into a personal target without a reason.
• For bedtime procrastination, treat the transition as the behavior: choose a real stopping cue, define a tiny first step such as putting the phone on its charger, and design around the actual competing activity. Do not prescribe more sleep hygiene to someone who already sleeps readily once in bed.
• For sleep onset: 30-60 minute wind-down, stop work/problem solving, dim lights, park tomorrow tasks in writing, and leave bed briefly if awake and frustrated.
• For maintenance waking: screen alcohol, heat, stress, pain, nocturia, reflux, partner snoring, late meals, and clock checking before adding gadgets.
• Melatonin is mainly a clock signal, not a knockout sedative. Keep OTC doses low, time it to the goal, and avoid making it the first lever for ordinary insomnia.

Altitude And Structural Vibration

• For sleep disruption at altitude, ask the current and usual elevation, ascent timing, whether the person is remote or alone, access to help or descent, and current symptoms before discussing sleep tactics.
• Severe or worsening headache with vomiting, confusion, trouble walking straight, breathlessness at rest, chest tightness, or worsening cough belongs to altitude safety, not an insomnia experiment. Tell the user to use local emergency or expedition medical help and their existing safe descent or evacuation plan. Do not delay for wearable data.
• Do not suggest a new sedative, alcohol, sleep medication, or supplement experiment as a substitute for acclimatization or altitude assessment. Do not change an existing prescription or expedition protocol; route that decision to its qualified clinician or expedition owner.
• For external vibration, first distinguish audible room noise from shaking or buzzing felt through the bed, floor, or walls. Ask about the likely source, timing, whether other people feel it, and whether it stops in a safe alternate room or location.
• Favor feasible controls: use a safe alternate sleeping location when available, move the bed away from obvious equipment or a shared wall, record dates and times, and contact the property manager, contractor, or local building or environmental authority. Do not recommend improvised bed suspension or structural alterations.
• If new or strong building movement comes with cracking, a utility smell, an electrical hazard, or another sign the space may be unsafe, leave the area and contact local emergency or building-safety services.
• Never frame inability to sleep through uncontrollable altitude effects or external vibration as poor adherence, weak motivation, or failed sleep hygiene.

Interpretation Rules

• Deep sleep usually improves indirectly through more total sleep, less alcohol, less fragmentation, cooler sleep, and training/stress load balance; there is no reliable same-night deep-sleep hack.
• REM is sensitive to alcohol, sleep timing, antidepressants, cannabis, and late-night fragmentation; do not chase REM minutes alone.
• If the user feels fine and only the score is low, explain measurement limits and pick no intervention or a low-burden check.
• Never start proactive deep/REM coaching, a multi-day plan, or a supplement change from a consumer stage estimate alone. Do not compare the user's stage minutes with a population target as the reason to intervene.

Accepted Multi-Day Plan

When the user accepts a repeated non-experiment sleep plan, read behavior-followthrough and persist the operational plan in one active kind=habit regimen (and a linked goal only when the outcome/window needs one). Update an existing matching plan instead of creating a parallel copy. Include the baseline, target, one primary lever, standard/tiny/fallback versions, anchor or action window, the evidence bundle and outcome that will be reviewed, a dated review point, and an off-ramp.

Offer one bounded review at the point when the chosen outcome could reasonably change; prefer a one-shot check-in. Reminders and check-ins are separate user choices, so do not schedule either without exact consent. If the user wants a multi-day comparison intended to determine whether the lever works, load experiment-onboarding and create the canonical experiment run instead of disguising it as a habit plan.

Safety Boundaries

• Escalate urgently for falling asleep while driving or another safety-critical activity, gasping/witnessed apneas with sleepiness, sleep attacks, cataplexy, dangerous parasomnias, suicidal thoughts, manic symptoms, or severe withdrawal. Do not continue habit optimization before addressing the immediate driving/work safety question.
• Do not calculate, prescribe, or run an unsupervised sleep-restriction or time-in-bed-compression window for anyone. It is a CBT-I treatment component that requires appropriate clinical screening and monitoring; Murph must not improvise it from diary or wearable data. Ordinary changes to sleep opportunity or clock schedule that do not compress time in bed are distinct. Bipolar disorder, seizure disorder, pregnancy/postpartum, severe depression, active eating disorder, safety-sensitive work, and major medical illness make clinician oversight especially important.

Answer Shape

• Name the likely sleep problem type first, then one lever and one measurement window.
• Optimize one outcome at a time: latency, awakenings, total sleep, or score anxiety.
• When recommending a change, say what wearable signal would count as improvement and what signal is too noisy to chase.