HomeCAN I VIBECODE
Plan to Eat?
BUILD FIRST
- One defined user and a repeatable end-to-end job
- A small, clear data model with sign-in only if it is genuinely needed
- Loading, empty, error, and success states that make the workflow feel complete
LEAVE FOR LATER
- Large integration marketplaces
- Multi-region scale and enterprise administration
- Every power-user setting from the established product
RESEARCH NOTES
What this tool actually does.
Plan to Eat is a subscription meal-planning web app (plus mobile access) whose core loop is: collect recipes, schedule them, and get an automated grocery list. Recipes are saved into a Recipe Book via a browser recipe clipper from across the web. The planner lets users assign recipes to specific dates and mealtimes, adjust serving sizes, plan leftovers, and add notes and single grocery items to the calendar. Adding recipes auto-populates an aisle-by-aisle organized shopping list that users can edit and supplement with household items. 'Menus' let users save and reuse entire meal plans; the 'Freezer' tracks batch-cooked and frozen recipes with quantities and preparation dates. Nutrition features auto-calculate recipe macros and show daily totals on the planner. The plan is printable for fridge display, searchable across planning history, and has customizable calendar views. Positioned for
RESEARCHED BUILD PROMPT
Give this to your coding agent.
Build 'MenuBoard', a working replacement web app for the core Plan to Eat workflow, without copying its brand, logo, proprietary copy, or UI. Replicate the workflow: (1) Add recipes (paste full recipe text or a URL) into a Recipe Book; (2) drag or pick recipes onto a weekly calendar grid with date + meal slot (breakfast/lunch/dinner/snack), adjust serving sizes per plan, and attach per-day notes and one-off shopping items; (3) an auto-generated shopping list that merges ingredients across the planned week, groups them by aisle-like category (Produce, Dairy, Meat, Pantry, Other), supports check-off and manual household extras; (4) save an entire planned week as a reusable 'Menu' and restore it later; (5) optional per-recipe macro totals (calories, protein, carbs, fat) computed from ingredient quantities and shown on the plan. Technical approach: single-page app with React + Vite + TypeScript, local-first storage via localStorage with JSON export/import, or a minimal Node/Express + SQLite backend; parse pasted recipe ingredients with a small heuristics parser (qty-unit-item regex) rather than a full NLP library. User-facing requirements: responsive phone/desktop layout, printable weekly plan, easy undo/delete on the calendar, no auth (single household). Explicitly out of scope: real web scraping of recipe sites, native mobile apps, barcode scanning, a nutrition database, multi-user accounts, payment/subscription features. Deliver a README covering setup, how ingredient parsing works, and important limitations (heuristic parsing fails on nonstandard ingredient lines, localStorage size limits, no sync across devices).
Do not copy the original brand, proprietary assets, or UI; create an original visual system.