Nutrition planner
Sets personal nutrition targets - protein at 1.6-2.2 g/kg, a calorie budget from goal and activity, fiber and hydration floors - and a repeatable meal structure with a review-and-adjust protocol for fat loss, muscle gain, or maintenance. Use when someone asks "how much protein should I eat", "set my macros for a cut", "why has my weight stalled", or "build me a sustainable diet framework". General wellness guidance, not medical advice. Do NOT use to produce a specific week of recipes with a shopping list and prep schedule - use meal-planner instead (this skill sets the targets; meal-planner cooks to them); for the broader multi-pillar health routine, use longevity-protocol.From its SKILL.md
npx -y skills add SkillMedev/skills --skill nutrition-plannerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
7.1 KB, ~1.5k tokens by cl100k_base, as published. Nobody here has run it
Nutrition Planner
Most diets fail on adherence, not knowledge: targets are set too aggressively, protein is an afterthought, and there is no rule for when and how to adjust. This skill sets defensible targets, wraps them in a repeatable meal structure, and installs a review protocol - so the plan survives month three, not just week one. It sets the numbers; turning them into a specific week of recipes, a shopping list, and a prep schedule is meal-planner's job.
Operating procedure
Order matters: protein is set before calories because it is the highest-leverage macro and it anchors satiety; structure comes last because it exists to deliver the targets, not the reverse.
Step 1: Gather inputs
Collect: body weight (kg or lbs), goal (fat loss, muscle gain, or maintenance), training days per week and type, occupation activity (desk vs on-feet), dietary pattern or restrictions (vegetarian, allergies - allergies are non-negotiable), rough current eating pattern, and past diet attempts with why they broke down. If weight or activity is a guess, label it a guess and use the conservative end of every range. Screen for the medical conditions in Escalation before setting any deficit.
Step 2: Set the protein target
Default 1.6-2.2 g per kg of body weight per day: low end for sedentary individuals, high end for anyone training 3+ days per week. Distribute across at least 3 meals to maximize muscle protein synthesis - a 140 g target is roughly 3 × 45 g, not one 100 g dinner. Anchor foods: eggs, Greek yogurt, cottage cheese, chicken, fish, legumes, tofu. For plant-based users, bias toward the higher end of the range to offset lower per-food density.
Step 3: Set the calorie budget
Estimate maintenance as body weight in lbs × 14-16 (14 for desk workers, 16 for active individuals). Then apply the goal adjustment: fat loss, a 300-500 kcal deficit; muscle gain, a 200-300 kcal surplus; maintenance, no adjustment. Hard red line: never program a deficit beyond 750 kcal/day - it reliably destroys adherence and muscle mass. Whatever calories remain after protein split between carbohydrate and fat according to preference; adherence beats any particular ratio.
Step 4: Set the quality, fiber, and hydration floors
Build 80% of intake from whole, minimally processed foods - vegetables, fruits, legumes, whole grains, lean proteins, nuts, seeds - and leave 20% flexible; rigid perfection is the enemy of long-term adherence, and no food is categorically off-limits (frequency and portion govern outcomes). Fiber: 25-35 g/day. Water: 2.5-3.5 L/day, more with heavy training or heat.
Step 5: Design the repeatable meal structure
Design a template of 3-4 meals rather than lifelong tracking of every bite. Default pattern: protein + vegetable + starchy carb at each main meal, plus one or two protein-anchored snacks if needed to hit the target. Prescribe batch-cooking of grains, proteins, and roasted vegetables once or twice per week to kill decision fatigue. When the user wants the actual recipes and shopping list for a specific week, hand the targets to meal-planner.
Step 6: Install the review-and-adjust protocol
Review every 2-3 weeks, never daily - day-to-day scale weight is noise (water, sodium, glycogen). Compare the weekly average. If weight has not moved as intended after 3 full weeks, adjust calories by 10-15% in the needed direction before overhauling anything else. If adherence is breaking (meals skipped, tracking abandoned), reduce complexity first - fewer distinct meals, simpler defaults - because simplicity beats precision.
Worked artifact
Example: 80 kg (176 lb) desk worker, trains 4 days/week, goal fat loss.
NUTRITION TARGETS - 80 kg / fat loss / trains 4x week
Protein: 2.0 g/kg x 80 kg = 160 g/day (~53 g x 3 meals)
Maintenance: 176 lb x 15 (desk + trains) = ~2,640 kcal
Fat-loss budget: 2,640 - 450 deficit = ~2,200 kcal/day
Fiber floor: 30 g/day Water: 3 L/day
Structure: 3 meals + 1 protein snack
Breakfast: Greek yogurt bowl + berries + oats (~45 g protein)
Lunch: chicken + rice + big roast-veg tray (~55 g protein)
Dinner: salmon or tofu + potatoes + salad (~45 g protein)
Snack: cottage cheese or protein shake (~20 g protein)
Batch-cook Sunday: rice, chicken, roast vegetables.
Review: weekly-average weight, adjust only after 3 flat weeks, by 10-15%.
Deliverable
Produce a one-page targets sheet containing: protein target in grams with per-meal split, calorie budget with the maintenance estimate shown, fiber and water floors, the 80/20 quality rule, the 3-4 meal structure with anchor foods, the batch-cook instruction, and the written review-and-adjust rule with its 3-week trigger.
Do NOT
- Do not set the deficit past 750 kcal/day, and do not let an eager user talk the plan into it - aggressive deficits trade two fast weeks for a collapsed month three.
- Do not set calories before protein; protein-last plans chronically under-deliver it.
- Do not react to daily scale readings or adjust more often than every 2-3 weeks.
- Do not ban foods or prescribe rigid clean-eating rules; flexibility is what makes the 80% hold.
- Do not drift into writing a week of recipes with a shopping list - that is meal-planner's job; deliver targets and structure.
- Do not prescribe for medical conditions; see Escalation.
Quality bar
The plan ships when: every target is a number derived from the user's actual body weight and activity (guesses labeled), the deficit or surplus sits inside the stated bands, protein has a per-meal distribution, the structure names real anchor foods the user will eat, the review rule states both the cadence and the 10-15% adjustment size, and the plan would plausibly still be followable in month three.
Escalation
This is general wellness education, not medical advice - a licensed physician or registered dietitian owns anything clinical. Refer out before planning when any of these are present: diagnosed diabetes or medications affecting blood sugar, kidney disease (protein targets need medical supervision), pregnancy or breastfeeding, a history of disordered eating (calorie targets can be actively harmful - refer to an RD or therapist), BMI-driven rapid-weight-loss requests, or unexplained weight change without trying. Route neighbors: meal-planner for the concrete weekly menu, longevity-protocol for the full health routine, strength-training-plan for the training these targets support.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most plan spec skills give in ~1.5k tokens
Counted across 1,099 of the 1,860 authors here whose files we hold, read 2026-08-07
- Ask one question at a timein 51 of 1099
- Break plans into vertical slicesin 29 of 1099, across 11 files
- Publish issues in dependency orderin 27 of 1099, across 9 files
- Iterate until user approves the breakdownin 25 of 1099, across 7 files
- Explore the repository to understand the codebase statein 24 of 1099, across 7 files
- Use domain glossary vocabularyin 23 of 1099, across 5 files
- Apply correct triage labels to published issuesin 23 of 1099, across 5 files
- Prefer AFK slices over HITLin 22 of 1099, across 7 files
- Write a specification before writing any codein 22 of 1099, across 14 files
- Write failing tests before implementation codein 22 of 1099, across 20 files
- Ask clarifying questions until requirements are concretein 21 of 1099, across 13 files
- Respect existing architecture decision recordsin 20 of 1099, across 5 files
Said here and by no other author read
- collect body weight, goal, activity, and dietary restrictions
- use conservative estimates for guessed inputs
- set protein target before setting calorie budget
- distribute protein across at least three meals
- cap daily calorie deficit at 750 kcal
- set fiber and water floors
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.