trip-map-builder（旅行地图生成器）

Trip Map Builder

Three-phase pipeline: Plan → Research → Build.

Phase 1: Plan the itinerary

Read references/trip-planning.md for the full methodology.

Core sequence:

1. Extract hard constraints — dates, flight times, terminals, hotel location
2. Group user's wishlist — city-easy / needs-reservation / far-suburbs / pass-through
3. Cut high-risk items first — too far, holiday-crowded, weather-dependent. Say what was cut and why.
4. Arrange by area — one main area per day, first day light, last day close to airport
5. Fill in meals — route-proximity first, vibe second, fame last. Always give main + backup.
6. Add tickets & transport — only critical ones (museum tickets, airport transfer)
7. Write executable doc — conclusion first, then daily plan, then what was cut

Key principles:

• Not everything the user listed fits. Delete for them.
• One area per day. One reservation-required spot per day max.
• Itineraries should be smooth, not packed.
• All user-facing questions follow the 4-beat format: Re-ground → Simplify → Recommend → Options. See references/trip-planning.md § 用户交互 for examples and anti-patterns.

Phase 2: Research via 小红书

Read references/xhs-research.md for the full OpenCLI + CDP workflow.

Core sequence:

1. Launch Chrome with --remote-debugging-port=9223
2. Connect via OpenCLI's CDPBridge
3. Navigate to xiaohongshu.com/search_result?keyword=<encoded> (never simulate input box)
4. Intercept POST /api/sns/web/v1/search/notes response
5. Pick top 2-3 notes by relevance, open detail pages
6. Extract via DOM: #detail-title, #detail-desc, .author-container.username
7. Compress to one decision-useful sentence per store, write back to local .md

Filtering rules:

• Keep: specific store name, address, dish, personal experience, repeated keywords
• Drop: generic area roundups, reposts, pure emotion, "氛围很好" x3
• Output: store name + one representative link + 2-3 sentence verdict

Phase 3: Build the map page

1. Copy assets/template.html → index.html
2. Fill HOTEL object and DAYS array with structured data from Phase 1+2
3. Each location needs: name, lat/lng, type, time, desc; optional: budget, detail, pay, xhs, reserve, gmap
4. Fill overviewContent() with trip summary, payment warnings
5. Apply design system — default template uses Apple style, but can switch to any style from awesome-design-md

Location types: food | spot | drink | hotel | transport

Payment chip values: 1 = confirmed yes (green), 0.5 = maybe (orange), omit = not shown

Design system (optional)

Default template uses Apple design system (SF Pro, light theme, frosted glass).

To use a different style, grab a DESIGN.md from awesome-design-md:

# Browse available design systems
# Apple, Vercel, Linear, Stripe, Notion, Airbnb, Nike, Spotify, etc.
curl -O https://raw.githubusercontent.com/VoltAgent/awesome-design-md/main/design-md/<brand>/DESIGN.md

Then adjust template.html's :root CSS variables (colors, fonts, spacing, border-radius) to match the chosen DESIGN.md tokens.

Deploy (optional)

git init && git add . && git commit -m "trip map"
gh repo create REPO --public --source=. --push
# Import from vercel.com/new — auto-deploys on push

Dependencies

Resources

• references/trip-planning.md — itinerary planning methodology, input/output templates, selection principles, common pitfalls
• references/xhs-research.md — OpenCLI installation, Chrome CDP setup, 小红书 search workflow, API details, filtering criteria
• assets/template.html — single-file HTML map template (Leaflet + Apple design system)
• awesome-design-md — 60+ brand design systems (Apple, Vercel, Stripe, Linear, etc.) for alternative styling