akl-rainfall
Query Auckland Council rainfall gauges and river or stream levels and flows.
Skill by thecolab-ai
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/thecolab-ai-akl-rainfall
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 2
codeload.github.com· found in install commandenvironmentauckland.org.nz· found in code
Files it touches
~/.claude/skills/akl-rainfall
What's inside
- Skill name
akl-rainfall- Description
- Query Auckland Council rainfall gauges and river or stream levels and flows. Use for Auckland monitoring sites, observed rainfall or water-level time series, and latest rainfall with spatial filters.
- License
- MIT
- Compatibility
- Requires Python 3.10+ and network access for live data
- Metadata
- thecolab.auth: none · thecolab.pack: nz-public-data · thecolab.risk: low · thecolab.health: healthy · thecolab.writes: false · thecolab.browser: false · thecolab.category: environment · thecolab.cache_ttl: none · thecolab.data_class: public · thecolab.maintainer: @adam91holt · thecolab.skill_type: public-api · thecolab.source_url: https://environmentauckland.org.nz/ · thecolab.access_mode: public-api · thecolab.source_type: official · thecolab.source_owner: Auckland Council · thecolab.last_verified: 2026-10-08 · thecolab.schema_version: 1 · thecolab.allowed_domains: environmentauckland.org.nz
- Instructions
- 104 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (13)
- SKILL.md
- source-notes.md · references/
- cli.py · scripts/
- provenance.py · scripts/
- smoke_test.py · scripts/
- test_contract.py · scripts/
- catalogue.json · tests/fixtures/
- contract.json · tests/fixtures/
- fixtures.json · tests/fixtures/
- flow-day.json · tests/fixtures/
- level-raw.json · tests/fixtures/
- rainfall-bulk-hour.json · tests/fixtures/
- rainfall-hour.json · tests/fixtures/
SKILL.md (first lines)
# Auckland rainfall and rivers
Use the stdlib Python CLI in `scripts/cli.py` to query Auckland Council's
Environment Auckland AQUARIUS WebPortal. Site discovery and JSON exports work
without a login, API key, cookies or browser.
## Workflow
1. Find gauges with `sites`, selecting rainfall, river/stream level or flow.
2. Copy the site's `site` identifier into `series` and choose a date window.
3. Use `latest` for each rainfall gauge's most recent non-null increment within
the last 72 hours. Inspect observation time, age and quality before using it.
```bash
python3 skills/akl-rainfall/scripts/cli.py sites --parameter rainfall --json
python3 skills/akl-rainfall/scripts/cli.py sites --parameter level --bbox '174.8,-37.1,175.0,-36.9' --format geojson --json
python3 skills/akl-rainfall/scripts/cli.py series --site 649940 --parameter rainfall --from 2026-10-07 --to 2026-10-08 --interval hour --json
python3 skills/akl-rainfall/scripts/cli.py series --site 43803 --parameter level --from 2026-10-07 --to 2026-10-08 --json
python3 skills/akl-rainfall/scripts/cli.py series --site 43803 --parameter flow --from 2026-10-07 --to 2026-10-08 --interval day --json
python3 skills/akl-rainfall/scripts/cli.py latest --parameter rainfall --bbox '174.88,-36.99,174.89,-36.97' --json
```
## Commands and output
- `sites [--parameter rainfall|level|flow] [--bbox minLon,minLat,maxLon,maxLat]`
lists monitoring sites, coordinates and available dataset identifiers. With
no parameter it returns the union of those three parameters. Includes old
gauges; inspect `end_of_record` (the Council's advertised record bound).
bbox filtering is local, inclusive point containment on site coordinates;
sites without coordinates are excluded. Bounds must strictly increase.
- `series --site ID --parameter rainfall|level|flow --from ISO --to ISO
[--interval hour|day] [--max-points N]` returns source observations or upstream aggregates.
Exact site names also work; identifiers avoid ambiguity. Windows are inclusive,
at most 31 days, and boundaries must have minute precision. A date means midnight.
Raw output (no `--interval`) has `--max-points` (default and maximum 5,000);
excess fails with code 2. Set a smaller positive limit to bound output further.
Use `--interval hour|day` or a shorter window to reduce the output.
- `latest --parameter rainfall [--bbox minLon,minLat,maxLon,maxLat]` returns
the most recent non-null recorded increment per gauge within 72 hours, with
`age_hours` and `stale` (over 24 hours). Reports gauges outside the lookback and
gauges without values separately. This is an increment, not a 24-hour total.
Every command accepts `--json`, returning `{"meta": {...}, "results": [...]}`.
Shared `meta` includes `source_url`, `publisher`, `licence`, `retrieved_at`, and
`latest_data` when published, plus counts, warnings and query details. Errors
return the same `meta`, empty `results`, and `error` with code, type and message.
Spatial commands also accept `--format json|geojson`; either implies machine
output. GeoJSON uses WGS84 longitude, latitude order and top-level `meta`.
Latest gauges retain their individual export `source_url`; other shared
provenance appears once in `meta`. Retrieval times are UTC; data times are
**fixed NZST (UTC+12)** even in summer. Do not interpret naive input as
daylight-saving Auckland time.
Dataset records use `start_of_record`/`end_of_record` for coverage; sites report
`end_of_record`. Series `meta.latest_data` is the advertised end of that dataset's record; it can be
newer than the requested historical window.
Latest metadata reports the newest returned observation. POST `source_url` is
the bare public endpoint; `meta.request`/`meta.catalogue_requests` record its
method and form separately. GET export URLs retain replayable query parameters.
With `--interval`, rainfall is the total over the preceding interval; level/flow
are averages. Aggregate `time` is the interval end. Use `period_start` and
`period_end` for day attribution; days run midnight–midnight NZST (01:00–01:00
NZDT in summer). Retain `grade_code`, `grade_name`, approvals, qualifiers and
interpolation fields. Missing source values (`"NaN"`) become `null`, with
`missing: true` and the original `source_missing_marker`. Never treat them as zero.
An empty valid time window remains an empty result; malformed exports fail.
A window outside the dataset's advertised record includes a metadata warning;
an empty series is not evidence of no rain.
## Limits and attribution
- Data is for the sole use of the recipient. Do not redistribute or republish
raw extracts without agreement; attribute **Auckland Council** in any output.
Data may be measured or synthesised and is not for safety decisions. See the
[portal terms](https://environmentauckland.org.nz/Disclaimer), including indemnity.
The skill's MIT licence covers its code; no open data licence was found.
- Some stations are operated by ESNZ/NIWA and distributed through the Council
portal. Check the station owner and its terms before reuse.
- Gauges are provisional and may be old, missing or unverified. These are gauge
measurements, not street flood depths or official warnings.
- No radar imagery or forecasts. Historical coverage varies. Council says additional
parameters and historical data can be requested through its contact dashboard.
- Each network call uses a 10-second timeout. Latest downloads use one request per active
gauge and at most four concurrent requests; one failed request fails the command.
No credentials, caches or external dependencies are required.
## Resources and checks
See `references/source-notes.md` for verified endpoints, source terms and schema
details. Hand-written synthetic parser fixtures are in `tests/fixtures/`;
`fixtures.json` marks their fictional contents and the source shapes they mirror.
```bash
python3 scripts/validate_skill.py skills/akl-rainfall --strict
python3 skills/akl-rainfall/scripts/test_contract.py
python3 scripts/run_smoke_tests.py akl-rainfall
```
`scripts/test_contract.py` checks synthetic parsers and the shared CLI contract.
`scripts/smoke_test.py` checks fixtures before bounded live sites, rainfall, level,
flow and latest probes. Network outages are skips; parser failures are failures.From thecolab-ai/.skills, MIT.
More from thecolab-ai/.skills
- 0.658score
belib-ev-live
thecolab-ai
Look up live Belib electric-vehicle charge-point availability in Paris.
SkillAFreshness: A★ 34Claude Code +9 - 0.658score
auckland-bin-schedule
thecolab-ai
Query Auckland Council rubbish, recycling, and food scraps collection days for Auckland properties using the public collection-day website flow.
SkillAFreshness: A★ 34Claude Code +9 - 0.658score
dft-pedal-cycle-factsheet
thecolab-ai
Read the Department for Transport 2025 Great Britain pedal-cycle road casualty factsheet tables.
SkillAFreshness: A★ 34Claude Code +9 - 0.658score
brisbane-intersection-traffic
thecolab-ai
Read keyless Brisbane City Council real-time intersection lane volume, occupancy and traffic-signal locations from data.brisbane.qld.gov.au.
SkillAFreshness: A★ 34Claude Code +9 - 0.658score
bkg-starkregen-wms
thecolab-ai
Query the BKG Hinweiskarte Starkregengefahren WMS for Germany heavy-rain hint layers and one extraordinary-event flow-velocity point.
SkillAFreshness: A★ 34Claude Code +9 - 0.658score
au-energy-rating
thecolab-ai
Look up Australian and New Zealand Energy Rating labelled appliance registrations from the Australian Government data.gov.au CKAN package.
SkillAFreshness: A★ 34Claude Code +9 - 0.655score
akl-ontrack
thecolab-ai
Read AKLOnTrack's public Auckland train observation archive.
SkillAFreshness: A★ 34Claude Code +9 - 0.655score
akl-housing-capacity
thecolab-ai
Query Auckland housing supply trends and 2022/23 plan-enabled and feasible housing capacity.
SkillAFreshness: A★ 34Claude Code +9 - 0.655score
fenz-incidents-nz
thecolab-ai
Query official Fire and Emergency New Zealand operational reports and annual incident datasets by place, type and period.
SkillAFreshness: A★ 34Claude Code +9 - 0.655score
akl-transport-performance
thecolab-ai
Query Auckland Transport patronage by mode and route, monthly punctuality and reliability, car park facility inventory with undated availability, and…
SkillAFreshness: A★ 34Claude Code +9 - 0.655score
berlin-starkregen-wfs
thecolab-ai
Read Berlin Starkregen flood model areas from the official Geoportal Berlin WFS.
SkillAFreshness: A★ 34Claude Code +9 - 0.655score
customs-tariff-nz
thecolab-ai
Search and look up official New Zealand Customs tariff classifications, rates, levies and formula records.
SkillAFreshness: A★ 34Claude Code +9
Signals
- Stars
- 34
- Forks
- 7
- Open issues
- 10
- Last commit (this folder)
- Oct 8, 2026 (20 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/thecolab-ai/.skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from thecolab-ai
- 0.658score
belib-ev-live
thecolab-ai
Look up live Belib electric-vehicle charge-point availability in Paris.
SkillAFreshness: A★ 34Claude Code +9 - 0.658score
brisbane-intersection-traffic
thecolab-ai
Read keyless Brisbane City Council real-time intersection lane volume, occupancy and traffic-signal locations from data.brisbane.qld.gov.au.
SkillAFreshness: A★ 34Claude Code +9 - 0.658score
auckland-bin-schedule
thecolab-ai
Query Auckland Council rubbish, recycling, and food scraps collection days for Auckland properties using the public collection-day website flow.
SkillAFreshness: A★ 34Claude Code +9 - 0.658score
au-energy-rating
thecolab-ai
Look up Australian and New Zealand Energy Rating labelled appliance registrations from the Australian Government data.gov.au CKAN package.
SkillAFreshness: A★ 34Claude Code +9 - 0.658score
bkg-starkregen-wms
thecolab-ai
Query the BKG Hinweiskarte Starkregengefahren WMS for Germany heavy-rain hint layers and one extraordinary-event flow-velocity point.
SkillAFreshness: A★ 34Claude Code +9 - 0.658score
dft-pedal-cycle-factsheet
thecolab-ai
Read the Department for Transport 2025 Great Britain pedal-cycle road casualty factsheet tables.
SkillAFreshness: A★ 34Claude Code +9
Cite this page
akl-rainfall skill. Agent Mart. https://agentmart.dev/skills/thecolab-ai-akl-rainfall (last updated 2026-10-24)