Skip to content
Agentmart
Submit a tool

akl-ontrack

Read AKLOnTrack's public Auckland train observation archive.

Skill by thecolab-ai

IndexedMIT★ 34
Write a review

Chalk Labs

Need help deploying akl-ontrack?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

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-ontrack

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.

We use your email only for this newsletter. Privacy

About

Read AKLOnTrack's public Auckland train observation archive. Use for daily stop-by-stop lateness, cancellations and skipped stops from data.aklontrack.com, not the live Auckland Transport API or a GTFS timetable.

Use cases: backend, data

No 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 5

  • aklontrack.com · found in code
  • codeload.github.com · found in install command
  • data.aklontrack.com · found in code
  • example.invalid · found in code
  • github.com · found in code

Files it touches

  • ~/.claude/skills/akl-ontrack

What's inside

Skill name
akl-ontrack
Description
Read AKLOnTrack's public Auckland train observation archive. Use for daily stop-by-stop lateness, cancellations and skipped stops from data.aklontrack.com, not the live Auckland Transport API or a GTFS timetable.
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: public-data · thecolab.cache_ttl: none · thecolab.data_class: public · thecolab.maintainer: @adam91holt · thecolab.skill_type: public-api · thecolab.source_url: https://aklontrack.com/data · thecolab.access_mode: public-api · thecolab.source_type: community · thecolab.source_owner: AKLOnTrack · thecolab.last_verified: 2026-10-11 · thecolab.schema_version: 1 · thecolab.allowed_domains: data.aklontrack.com,aklontrack.com
Instructions
49 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (17)

  • SKILL.md
  • source-notes.md · references/
  • cli.py · scripts/
  • provenance.py · scripts/
  • smoke_test.py · scripts/
  • test_contract.py · scripts/
  • contract.json · tests/fixtures/
  • day-bad-width.json · tests/fixtures/
  • day-empty.json · tests/fixtures/
  • day-positive.json · tests/fixtures/
  • index-empty-day.json · tests/fixtures/
  • index-empty.json · tests/fixtures/
  • index-match.json · tests/fixtures/
  • index-off-host.json · tests/fixtures/
  • index-positive.json · tests/fixtures/
  • index-unlicensed.json · tests/fixtures/
  • malformed-body.txt · tests/fixtures/

SKILL.md (first lines)

# AKLOnTrack observations

Read-only client for the public observation archive at `data.aklontrack.com`.
It lists catalogue dates and fetches one day file named by that catalogue.
It does not call the live Auckland Transport API, GTFS timetable zips, trip-outcome
files, monthly CSV bundles, or the station-name reference.

## Commands

Run from the repository root. Python 3.10+, standard library only. Each network
call times out after 15 seconds. `--json` prints a provenance envelope.

```bash
python3 skills/akl-ontrack/scripts/cli.py index --limit 20 --json
python3 skills/akl-ontrack/scripts/cli.py day 2026-07-23 --limit 20 --json
python3 skills/akl-ontrack/scripts/cli.py day --latest --limit 20 --json
```

`index` returns observation dates, byte sizes, row counts, trip counts, sha256
and `written_at`, newest first. The default returns every catalogue date, up to
a hard bound of 800. `--limit` accepts 1–500.

`day` takes one `YYYY-MM-DD` date or `--latest`. `--latest` selects the newest
index day whose row count is greater than zero and whose file is within the
byte cap, then fetches that file only. A date that is not in the index is an
error. An indexed day with zero stop rows returns an empty `results` array.

Stop observations keep the publisher's units: `arrival_delay` and
`departure_delay` are seconds late (negative means early); `arrival` and
`departure` are seconds from `t0`, Auckland midnight at the start of
`service_date`. `arrival_time` and `departure_time` are that instant in
`Pacific/Auckland`. If the day file omits a time field or sends JSON null, the
result uses null and does not substitute zero. `state` 0 is stopped, 1 cancelled,
2 skipped, 3 no report.
`trip_rel` and `stop_rel` stay as Auckland Transport sent them. Empty `trip_id`
stays empty. The default window is 20 observations; `--limit` is 1–500 and
`--offset` is 0–20000.

The day file's byte length and sha256 must match the index, and the index `rows` value must match the number of stop rows.
A licence object other than CC BY 4.0, a non-JSON body, an off-host redirect,
HTTP 429 or HTTP 503 is an error, not an empty timetable.

## Tests

`scripts/test_contract.py` is offline. `scripts/smoke_test.py` replays fixtures
and then performs one live `day --latest` call (the index plus that one day).
Details and the column layout are in `references/source-notes.md`.

From thecolab-ai/.skills, MIT.

More from thecolab-ai/.skills

Signals

Stars
34
Forks
7
Open issues
10
Last commit (this folder)
Oct 11, 2026 (19 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from thecolab-ai

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get akl-ontrack running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying akl-ontrack?

CallGet help
Cite this page

akl-ontrack skill. Agent Mart. https://agentmart.dev/skills/thecolab-ai-akl-ontrack (last updated 2026-10-24)