Weather
全球高级定制化 AI 旅游攻略 Skill Pack — 9 skills, zero API key, Hermes/Cursor/Claude compatible
npx -y skills add wpfbcr/AtlasAgent --skill weatherAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 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.
What its author says it does
Copied from the file, not written here
Fetches global weather forecasts via Open-Meteo without an API key. Use when planning travel dates, packing, outdoor activities, or when the user asks about weather, 天气, forecast, or climate at a destination.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
1.4 KB, as published. Nobody here has run it
Weather
Open-Meteo forecasts for travel planning (replaces wttr.in — more reliable globally).
Setup
export ATLAS_ROOT="${ATLAS_ROOT:-$HOME/AtlasAgent}"
export ATLAS_SCRIPTS="$ATLAS_ROOT/scripts"
Commands
python3 "$ATLAS_SCRIPTS/weather_client.py" forecast --city "Tokyo" --days 7
python3 "$ATLAS_SCRIPTS/weather_client.py" forecast --lat 48.8566 --lon 2.3522 --days 5
python3 "$ATLAS_SCRIPTS/weather_client.py" current --city "Paris"
python3 "$ATLAS_SCRIPTS/weather_client.py" forecast --city "Sydney" --days 10 --json
Output Use
- Summarize in itinerary weather section
- Rain → swap outdoor sights for indoor backups
- Extreme heat/cold → packing notes
- Forecast beyond 7 days = trend only
Pitfalls
- Southern hemisphere seasons differ (June in Sydney = winter)
- Mountain/coastal microclimates may differ from city forecast
Verify
python3 "$ATLAS_SCRIPTS/weather_client.py" forecast --city Paris --days 3