AtlasAgent — Global Travel Planning

Orchestrates worldwide trip planning: multi-plan comparison, daily schedules, budgets, visa/diet/transport decisions, PDF export.

Install

If not installed yet, follow $ATLAS_ROOT/docs/install.md or tell the user:

帮我安装 AtlasAgent：https://raw.githubusercontent.com/wpfbcr/AtlasAgent/main/docs/install.md

Verify: bash "$ATLAS_ROOT/scripts/atlas-agent" doctor

When to Use

• User provides origin, dates, party size — needs an itinerary
• User wants destination recommendations with plan comparison
• User has booked flights/hotels and needs a concrete schedule
• Multi-city or cross-timezone trips

Required Inputs

For a real booking plan, confirm missing fields before planning. For a demonstration or test, use user-approved assumptions and list them explicitly:

Paths (required)

Install the full repository — skills/ alone is not enough.

export ATLAS_ROOT="${ATLAS_ROOT:-$HOME/AtlasAgent}"
export ATLAS_SCRIPTS="$ATLAS_ROOT/scripts"
export ATLAS_REF="$ATLAS_ROOT/skills/atlas-agent/references"

Install: see $ATLAS_ROOT/docs/install.md — full repo required, not skills/ alone.

Workflow

Phase 0 — Profile

1. For international travel, passport nationality → read visa-entry; for domestic travel, state that visa analysis is not applicable
2. Dietary restrictions → read dietary-global skill
3. Booked tickets/hotels → treat as fixed anchors

Phase 0.5 — Disambiguation

Do not guess ambiguous names. Present options and ask the user to choose:

• Location, transport, duration, ticket/booking needs
• Local + English names

Examples: Paris (France vs Texas), Springfield (30+ US cities).

Phase 1 — Data (parallel)

# Weather
python3 "$ATLAS_SCRIPTS/weather_client.py" forecast --lat <confirmed-lat> --lon <confirmed-lon> --timezone <IANA-timezone> --from YYYY-MM-DD --days <N>

# Currency
python3 "$ATLAS_SCRIPTS/currency_client.py" rates --base <currency>
python3 "$ATLAS_SCRIPTS/currency_client.py" convert <amount> --from <A> --to <B>

# Calendar
python3 "$ATLAS_SCRIPTS/holiday_check.py" --city "<city>" --from YYYY-MM-DD --days <N>

Weather output must cover the exact trip dates. Outside the supported forecast window, label climate reference explicitly and recheck near departure. A network error or missing field is unavailable data, never a zero or sunny default.

Geography (first available):

1. $MAPS_SCRIPT if set (any geocoder/POI CLI, e.g. OpenStreetMap client)
2. Web search + $ATLAS_REF/destinations/<city>.md
3. Never invent hotel/restaurant names

Flights/hotels (optional L1): trvl MCP or web search — see $ATLAS_ROOT/mcp/recommended-servers.md

Reviews (optional L1): local-intel skill

Phase 2 — Scheduling

1. Use holiday_check.py for weekdays and closure hints, then verify each scheduled venue’s specific opening calendar from official sources
2. Book major sights on weekdays when possible
3. Arrival day = half day; allow jet-lag buffer after eastbound flights
4. Multi-city: minimize backtracking (use distance/routing tools if available)
5. Respect booked transport times as hard constraints

Phase 3 — Itinerary

Each plan includes:

• Round-trip transport (route, time, price in local + user currency)
• Weather summary (Open-Meteo)
• Visa/entry summary (from visa-entry)
• One-line trip theme + destination timezone

Daily table:

Required sections: must-eat list, 2–3 stays, budget table (budget-optimizer), transport decision (transport-global), document checklist (travel-documents), cautions.

Final validation: check exact day count, weekdays, opening days, sum of budget items, party-size division, currency labels, and budget constraints. Mark any unresolved information as unverified. Same-currency budgets need no exchange rate date.

Meals: every meal = restaurant + dishes with dietary tags (🟢🟡🔴⚠️) + price per person.

Pace: only one "intense" day; others relaxed. Mark activity hours.

Comparison rubric: references/comparison-rubric.md

Phase 4 — Compare & Recommend

Multi-plan table (days, budget, travel time, romance/food/photo/culture/family stars, effort, visa complexity). End with 1–2 sentence ranking.

Phase 5 — Export

python3 "$ATLAS_SCRIPTS/md2pdf.py" itinerary.md

Capability Tiers

If data is estimated, say: 「基于 reference 估算，出行前请验证」.

Companion Skills

Pitfalls

• Rate-limit POI APIs (>2s between calls); fall back to references
• Visa/policy: always note query date; re-check before departure
• FX: note rate date (Frankfurter/ECB)
• Southern hemisphere seasons invert vs northern
• Tipping varies by country → budget-optimizer
• Never recommend conflicting transport if user already booked

Verify

python3 "$ATLAS_SCRIPTS/weather_client.py" forecast --city Paris --days 3
python3 "$ATLAS_SCRIPTS/currency_client.py" convert 100 --from EUR --to CNY
python3 "$ATLAS_SCRIPTS/holiday_check.py" --city Paris --from 2026-07-14 --days 5