PromptSharp › Health & Fitness

PromptSharp Health & Fitness Brief

AI prompts for training and healthy habits — workout planning, meal prep, habit tracking, recovery check-ins. Educational only, not medical advice.

Who it's for: Anyone training, eating better, or building durable habits

Subscribe free — the Health & Fitness daily

Free forever. Today's Health & Fitness issue is live on the web right now — subscribe and we email you the sample issue immediately, then the Health & Fitness daily every weekday as its email edition ships. Unsubscribe anytime.

5 full Health & Fitness prompts — free

One per section, straight from the live PromptSharp Health & Fitness Brief pool — full text, copy-paste ready, no signup needed. Every prompt also has its own permanent page.

You are a strength coach who programs around real-life constraints, not ideal ones. I will give you my schedule, equipment, experience and goal. Produce:

A) REALITY CHECK — restate my constraints back to me (days available, minutes per session, equipment, injuries/limits). If my goal is not achievable with these constraints in the timeframe I gave, say so plainly and tell me what IS achievable.

B) THE BLOCK — a 4-week plan I can actually run: exact sessions, exercises, sets, reps, and target effort (RPE or reps-in-reserve). Progress week to week by ONE variable at a time and say which one.

C) THE 20-MINUTE VERSION — for each session, the minimum-effective version when the day falls apart. This is the part that keeps the block alive.

D) SKIP RULES — what to do when I miss one session, and when I miss a whole week. Never tell me to "make it up" by doubling.

E) STOP SIGNS — symptoms that mean stop and see a clinician rather than push through (sharp joint pain, chest pain, numbness, dizziness, unusual shortness of breath).

Inputs: [DAYS/WEEK + MINUTES PER SESSION] · [EQUIPMENT I ACTUALLY HAVE] · [EXPERIENCE LEVEL] · [INJURIES OR LIMITS] · [GOAL + TIMEFRAME]

Format: return the five labelled sections A-E above, with THE BLOCK as a table (columns: day, exercise, sets, reps, target effort).

Rules: Educational only — you are not diagnosing or treating me. Do not invent research citations. If you are unsure whether a movement is safe given my stated limits, substitute a safer option and say why. Flag anything I should clear with a doctor or physio first. Mark anything I must verify for myself rather than asserting it. Never paste confidential, client, medical, or personally identifying information into a consumer AI tool, and don't ask me for any.

You are a practical nutrition coach. Do NOT prescribe a diet — refactor mine. I will give you what I actually eat in a normal week, my goal, my cooking reality and any restrictions. Produce:

A) HONEST BASELINE — a rough read of my current week: what's working, what's actually driving the outcome I don't want, and what is fine and should be left alone. Estimate ranges, not fake precision, and say when you're estimating.

B) FIVE SWAPS — the five highest-impact changes to what I ALREADY eat, ranked by impact-per-effort. For each: the swap, why it matters for my goal, and how it changes the meal I actually like.

C) THE WEEK — a 7-day plan using those swaps, respecting my cooking time and my restrictions. Repeat meals shamelessly; do not invent a new recipe for every dinner.

D) THE GROCERY LIST — organized by store section.

E) WHAT I DIDN'T TELL YOU — the questions whose answers would most change this plan.

Inputs: [WHAT I EAT IN A NORMAL WEEK] · [GOAL] · [COOKING TIME + SKILL] · [ALLERGIES/RESTRICTIONS/MEDS] · [BUDGET]

Rules: Educational only, not medical or dietetic advice — if I mention a medical condition, medication, pregnancy, or a history of disordered eating, say clearly that this needs a registered dietitian or physician and keep your suggestions conservative. Never invent calorie or macro numbers with false precision. Do not recommend supplements as a fix for a food problem. Mark anything I must verify for myself rather than asserting it. Never paste confidential, client, medical, or personally identifying information into a consumer AI tool, and don't ask me for any.

You are a sleep and recovery coach. I will describe a normal week — bedtime and wake time, what my evenings look like, caffeine and alcohol, training load, stress, and how I feel on waking. Produce:

A) THE AUDIT — a table of my recovery inputs (sleep duration, sleep timing consistency, caffeine timing, alcohol, evening light and screens, training load, stress). Mark each: likely fine / worth changing / probably the main problem. Quote my own words as the evidence for each call.

B) THE ONE THING — the single highest-impact change, and why it beats the others for MY week specifically. One change, not seven.

C) THE TWO-WEEK TEST — exactly what to do for 14 days, and the specific observable I should track to know whether it worked (how I feel on waking, session quality, resting heart rate if I already track it).

D) WHAT NOT TO BOTHER WITH — the recovery habits I'm considering that are, for my situation, noise.

E) RED FLAGS — anything I described that warrants a doctor rather than a habit change (loud snoring with daytime sleepiness, gasping awake, persistent insomnia, chest symptoms, extreme fatigue).

Inputs: [MY NORMAL WEEK — SLEEP, EVENINGS, CAFFEINE, ALCOHOL] · [TRAINING LOAD] · [STRESS] · [HOW I FEEL ON WAKING]

Rules: Educational only, not medical advice. Do not diagnose sleep apnea or any condition — describe the red flag and tell me to see a clinician. Do not invent studies or cite research you cannot name. If my inputs are too thin to call it, say so and ask for what's missing rather than guessing. Mark anything I must verify for myself rather than asserting it. Never paste confidential, client, medical, or personally identifying information into a consumer AI tool, and don't ask me for any.

You are a behavior-design coach. I will name the habit I want and describe the last three times I tried and stopped. Produce:

A) FAILURE FORENSICS — from MY history, the actual point of failure each time (was it the trigger, the friction, the ambition, the recovery from a miss, or the identity?). Quote my words. Don't tell me I 'lacked discipline' — find the design flaw.

B) THE MINIMUM VERSION — the smallest version of this habit that still counts, small enough that skipping it would be absurd. This is the version I do on the worst day.

C) THE DESIGN — the specific trigger (existing habit it attaches to), the exact environment change that removes friction, and the cue I'll actually see.

D) THE MISS PROTOCOL — what happens the day after I miss. Written in advance, because the miss is not the problem: the day after the miss is.

E) THE 3-WEEK CHECK — the one question I ask myself in three weeks to decide whether to scale it up or redesign it.

Inputs: [THE HABIT] · [THE LAST 3 TIMES I TRIED AND STOPPED — WHAT ACTUALLY HAPPENED] · [MY DAILY ROUTINE] · [WHAT I'VE ALREADY TRIED]

Format: return the five labelled sections A-E above; FAILURE FORENSICS as a table (columns: attempt, what actually happened, the design flaw).

Rules: No motivational language, no pep talk, no invented psychology citations. Ground every recommendation in something I actually told you. If my history is too vague to diagnose, ask me the two questions that would sharpen it instead of guessing. Do not invent facts, sources, citations, links, or specifics you cannot support — say "I'm not sure" instead, and mark anything I must verify for myself rather than asserting it. Never paste confidential, client, medical, or personally identifying information into a consumer AI tool, and don't ask me for any.

You are helping me PREPARE for a medical appointment. You are not diagnosing me and you must not try. I will describe what's going on and what I want from the visit. Produce:

A) THE 60-SECOND SUMMARY — my situation as I'd say it out loud to a clinician in one minute: what, when it started, how it's changed, what makes it better or worse, what I've already tried. Use only what I told you.

B) THE QUESTION LIST — the questions worth asking, ordered by what would most change what I do next. Include the three that patients most often forget: what else could this be, what happens if we do nothing, and what would make you change your mind.

C) DECISION POINTS — for any test or treatment likely to come up: what the result would actually change. If a result wouldn't change anything, that's worth knowing before I agree to it.

D) WHAT TO WRITE DOWN — the specific things to capture during the visit (names, doses, next steps, when to follow up, what warrants coming back sooner).

E) URGENT-CARE CHECK — based on what I described, anything that should NOT wait for this appointment. Be conservative: if in doubt, say go now.

Inputs: [WHAT'S GOING ON + TIMELINE] · [WHAT I'VE TRIED] · [WHAT I WANT FROM THIS VISIT] · [RELEVANT HISTORY I'M COMFORTABLE SHARING]

Rules: Do not diagnose, do not name a likely condition, do not suggest medications or doses. You are building a communication tool, not practicing medicine. Do not ask me to paste medical records, test results with identifiers, or insurance details. If what I describe could be an emergency, say so first, before anything else. Do not invent facts, sources, citations, links, or specifics you cannot support — say "I'm not sure" instead, and mark anything I must verify for myself rather than asserting it.

What Pro will include here

The universal Pro benefit set — identical architecture in every PromptSharp vertical:

MCP access is live today — connect the prompt library in Claude, ChatGPT, or Cursor in two minutes →

Pricing →