Tempest

What it does

When your agent uses it

• The user asks about weather
• Forecast data from their own Tempest/WeatherFlow station
• Wants to parse the hubs UDP port 50222 broadcast
• City forecasts without a Tempest station (public weather services serve those)

Example prompts

• “/tempest”

Requirements

• Python 3
• A credential in TEMPEST_TOKEN
• A credential in YOUR_TOKEN
• Compatibility (from SKILL.md): Requires TEMPEST_TOKEN env var for REST (create it in the Tempest web app under Settings -> Data Authorizations), Python 3.8+, and `requests`. UDP listening needs a Tempest hub on the LAN and no token. `--help` and `--dry-run` work without credentials.

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

1. 1Create a personal access token: sign in to the Tempest web app
2. 2Export it

What it can do on your machine

Read from SKILL.md and the folder at commit 22b4723. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 2 files in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • jq

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • TEMPEST_TOKEN

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Requires TEMPEST_TOKEN env var for REST (create it in the Tempest web app under Settings -> Data Authorizations), Python 3.8+, and `requests`. UDP listening needs a Tempest hub on the LAN and no token. `--help` and `--dry-run` work without credentials.

  From compatibility in the SKILL.md frontmatter.

Context cost

Tempest loads about 3.3k tokens when it runs, and up to ~13k if it reads all its reference files. Until then it costs about 197 tokens; SKILL.md has 1,226 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~197

When it runs · the whole SKILL.md, loaded when a task matches

~3.3k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~13k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from magnus919/agent-skills at commit 22b4723, republished under its MIT licence (© magnus919). 1,226 words, ~3,281 tokens.

name

tempest

description

Query hyper-local weather from a WeatherFlow Tempest station over its REST API and the hub's local UDP broadcast: current conditions, forecast, historical observations, and real-time decoded datagrams (obs_st, rapid_wind, evt_precip, evt_strike, hub_status). Use when the user asks about weather, temperature, rain, wind, humidity, or forecast data from their own Tempest/WeatherFlow station, or wants to parse the hub's UDP port 50222 broadcast. Do not use this skill for generic or city forecasts without a Tempest station (public weather services serve those), for Shakespeare's play The Tempest or other literature questions, or for weather hardware from other vendors - the REST endpoints require a personal-use token and the UDP broadcast only exists on a Tempest hub's LAN.

compatibility

Requires TEMPEST_TOKEN env var for REST (create it in the Tempest web app under Settings -> Data Authorizations), Python 3.8+, and `requests`. UDP listening needs a Tempest hub on the LAN and no token. `--help` and `--dry-run` work without credentials.

license

MIT

metadata.tags

weather, tempest, weatherflow, forecast, station, udp, hyper-local

metadata.sources

https://apidocs.tempestwx.com/reference/quick-start, https://weatherflow.github.io/Tempest/api/udp/v171/

export TEMPEST_TOKEN="<YOUR_TOKEN>"

tempest stations                       # names, station ids, device types, serials
tempest stations --json | jq '.stations[] | {station_id, name,
  devices: [.devices[] | {device_id, device_type, serial_number}]}'

tempest current                                       # human-readable, converted
tempest current --json                                # metric-native, jq-ready
tempest current --station-id 12799 --device-id 60526  # pin exact hardware

tempest forecast                       # current + 5-day daily + next 12 hours
tempest forecast --days 7 --json
tempest forecast --station-id 12799 --days 3

tempest obs --device-id 60526 --days 1       # last UTC day (day_offset)
tempest obs --device-id 60526 --days 7
tempest obs --device-id 60526 --json

tempest udp listen                          # live stream until Ctrl-C
tempest udp listen --timeout 30             # auto-stop after 30s
tempest udp listen --timeout 60 --json      # one JSON object per datagram
tempest udp listen --show-all               # include hub_status/device_status

# Stage 1 -> stage 2: stations --json emits integer ids that current consumes
tempest stations --json | jq -r '.stations[].devices[]
  | select(.device_type == "ST") | .device_id' | head -1
tempest current --device-id <DEVICE_ID> --json

tempest obs --device-id 60526 --days 1 --json \
  | jq '{samples: (.observations | length),
         day_rain_mm: .observations[-1].local_day_rain_accumulation}'
tempest udp listen --timeout 600 --json | jq 'select(.type == "evt_precip")'

tempest forecast --days 7 --json \
  | jq '{units_temp: .forecast.units.units_temp,
         highs_f: [.forecast.forecast.daily[] | .air_temp_high * 9 / 5 + 32],
         rain_hours: [.forecast.forecast.hourly[]
                      | select(.precip_probability > 30) | .local_hour]}'

tempest current --json | jq '{temp_c: .observation.air_temperature,
  temp_f: (.observation.air_temperature * 9 / 5 + 32),
  wind_mph: (.observation.wind_avg * 2.237),
  rain_in: (.observation.rain_accumulation / 25.4)}'

© magnus919, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 8 other files (scripts, references) in tempest of magnus919/agent-skills.

• SKILL.md
• README.md
• evals/evals.json
• references/cli-worked-recipes.md
• references/observation-layouts-and-units.md
• references/rest-api-and-auth.md
• references/udp-broadcast-protocol.md
• scripts/tempest
• scripts/test_tempest.py

Open the folder on GitHubat commit 22b4723