How to Build a Weather App

<context>
App: Weather App
Difficulty: Beginner
Estimated build time: 1–2 days

Data model:
  Location: lat, lon, name, country — stored in localStorage, no DB needed for basic version
  WeatherCache: location_key, data (JSON from API), fetched_at — cache in localStorage or Redis to avoid re-fetching on every render

Recommended build order:
  1. Fetch and display current conditions — Call Open-Meteo's /forecast endpoint with hardcoded lat/lon. Display temperature, weather code (mapped to icon), humidity, and wind speed. Open-Meteo is free, no API key.
  2. Add geolocation — Call navigator.geolocation.getCurrentPosition() on load. Use the returned lat/lon for the API call. Show a loading state while geolocation resolves.
  3. City search — Use Open-Meteo's Geocoding API to search for cities by name. Show a dropdown of results. On select, store the lat/lon/name and refetch weather.
  4. Hourly and 7-day forecast — Add the hourly and daily forecast sections to the API request. Render hourly as a horizontal scrolling row of cards. Daily as a vertical list with min/max temps and icons.
  5. Favourite locations — Add a favourite button on each location. Store favourites in localStorage as an array of {name, lat, lon}. Add a favourites panel with one-click switching.
  6. Cache API responses — Before calling the API, check if you have a cached response for this location from the last 15 minutes. If yes, use it. This prevents hitting API limits and speeds up repeat views.
  7. AI plain-English summary — Take the day's hourly forecast data and send it to Claude Haiku with a prompt: "Summarise this forecast in one casual sentence for a non-technical user." Display above the data.

Known pitfalls to avoid:
  - Calling the API on every render — wrap your fetch in a useEffect with the location as a dependency and cache the result. Without caching, switching tabs and back triggers a fresh API call every time.
  - Mapping weather codes manually — Open-Meteo returns numeric weather codes (0–99). Use their official code table to map them to descriptions and icons. Don't invent your own mapping.
  - Not handling geolocation denial — if the user denies location access, show a city search input immediately instead of a broken loading state.

Tech stack (intermediate): Next.js + Open-Meteo + Mapbox for radar map embed
</context>

<role>
You are a Senior Full-Stack Engineer and product architect who has shipped production Weather Apps before. You know exactly where developers get stuck and how to structure the project to avoid rewrites.
</role>

<task id="step-1-clarify">
Before writing any code or spec, ask me 3–5 clarifying questions that will meaningfully change the architecture. Focus on: scale expectations, auth requirements, platform (web / mobile / both), must-have vs nice-to-have features for the MVP, and any hard constraints (budget, deadline, existing infrastructure).

<example>
BAD: "What tech stack do you want to use?" — too broad, doesn't change architecture decisions.
GOOD: "Do you need real-time sync across devices, or is single-device with periodic refresh acceptable? This decides whether we use WebSockets or simple REST polling and significantly affects infrastructure complexity."
</example>
</task>

<task id="step-2-architect">
After I answer your questions, generate a complete project specification including:

1. Final tech stack with version numbers
2. Full file and folder structure
3. Complete database schema — every table, column, type, index, and foreign key
4. All API routes with request/response shapes and auth requirements
5. Component tree with TypeScript props interfaces
6. Auth and authorisation flow (who can do what)
7. Step-by-step implementation plan in the exact build order from <context> above
8. All environment variables with descriptions

<self_check>
Before presenting the spec, verify:
□ Every answer I gave in step 1 is reflected in the spec
□ The database schema matches the data model in <context>
□ The implementation plan follows the build order from <context>
□ No circular dependencies in the component tree
□ Auth is wired up before any protected routes are built
□ All known pitfalls from <context> are addressed in the spec
</self_check>
</task>

<task id="step-2.5-agents-md">
Generate an AGENTS.md file at the project root. This file is read automatically by Claude Code, Cursor, Windsurf, Sourcegraph Cody, and all major AI coding tools at the start of every session.

Include:
- Project overview (2–3 sentences)
- Tech stack with version numbers
- Folder structure with one-line descriptions
- Key architectural decisions and why they were made
- Coding conventions: naming (camelCase components, kebab-case files), max 200 lines per file, one concern per file
- Available commands: dev, build, test, lint, db:migrate, db:seed

Note in the file: "Cursor users can symlink .cursorrules → AGENTS.md. Claude Code users can symlink CLAUDE.md → AGENTS.md."
</task>

<task id="step-3-implement">
Implement the full project following the spec from step 2, in the exact order defined. For each step:
- Write the complete code (no placeholders or TODOs)
- Confirm the step is working before moving to the next
- Note any deviations from the spec with an explanation

<constraints>
- Max 200 lines per file. WHY: every file must fit in one AI context window for easy review and editing.
- One concern per file. WHY: mixing auth logic into API routes makes it impossible to reuse — extract to lib/auth.ts.
- TypeScript strict mode, no `any` types. WHY: catches data shape mismatches at compile time, not in production at 2am.
- All database queries in server components or API routes only. WHY: keeps credentials server-side, prevents accidental client-side exposure.
- All environment variables documented in .env.example. WHY: the next developer (or your future self) should be able to set up the project in under 5 minutes.
- Comment every non-obvious decision. WHY: AI tools read your comments to understand intent — without them, the next edit will break the pattern you established.
</constraints>
</task>