Skip to content
Agentmart
Submit a tool

akl-housing-capacity

Query Auckland housing supply trends and 2022/23 plan-enabled and feasible housing capacity.

Skill by thecolab-ai

IndexedMIT★ 34
Write a review

Chalk Labs

Need help deploying akl-housing-capacity?

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-housing-capacity

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

Query Auckland housing supply trends and 2022/23 plan-enabled and feasible housing capacity. Use for monthly housing updates, building consents, HBA, capacity for growth, PC78, local-board growth capacity, social housing delivery and housing demolition source discovery.

Use cases: marketing

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 6

  • codeload.github.com · found in install command
  • hud.govt.nz · found in code
  • kaingaora.govt.nz · found in code
  • knowledgeauckland.org.nz · found in code
  • schemas.openxmlformats.org · found in code
  • untrusted.invalid · found in code

Files it touches

  • ~/.claude/skills/akl-housing-capacity

What's inside

Skill name
akl-housing-capacity
Description
Query Auckland housing supply trends and 2022/23 plan-enabled and feasible housing capacity. Use for monthly housing updates, building consents, HBA, capacity for growth, PC78, local-board growth capacity, social housing delivery and housing demolition source discovery.
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: degraded · thecolab.writes: false · thecolab.browser: false · thecolab.category: housing · thecolab.cache_ttl: none · thecolab.data_class: public · thecolab.maintainer: @adam91holt · thecolab.skill_type: public-download · thecolab.source_url: https://knowledgeauckland.org.nz/ · thecolab.access_mode: public-download · thecolab.source_type: official · thecolab.source_owner: Auckland Council · thecolab.last_verified: 2026-10-08 · thecolab.schema_version: 1 · thecolab.allowed_domains: knowledgeauckland.org.nz,www.knowledgeauckland.org.nz,www.hud.govt.nz,www.kaingaora.govt.nz
Instructions
72 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (16)

  • SKILL.md
  • source-notes.md · references/
  • cli.py · scripts/
  • housing.py · scripts/
  • provenance.py · scripts/
  • smoke_test.py · scripts/
  • sources.py · scripts/
  • test_contract.py · scripts/
  • workbook.py · scripts/
  • business.zip · tests/fixtures/
  • capacity.xlsx · tests/fixtures/
  • contract.json · tests/fixtures/
  • feasibility.xlsx · tests/fixtures/
  • housing.xlsx · tests/fixtures/
  • hud.xlsx · tests/fixtures/
  • landing.html · tests/fixtures/

SKILL.md (first lines)

# Auckland housing capacity

Use `scripts/cli.py` to read the current Auckland Council housing datasheet,
2022/23 PC78 residential capacity summaries and HUD/MCERT social housing delivery.
Python 3.10+ standard library only; no keys or setup required.

```bash
python3 skills/akl-housing-capacity/scripts/cli.py sources --json
python3 skills/akl-housing-capacity/scripts/cli.py housing-update --json
python3 skills/akl-housing-capacity/scripts/cli.py housing-update --month 2026-07 --area "Henderson-Massey" --json
python3 skills/akl-housing-capacity/scripts/cli.py housing-update --source hud --month 2026-08 --area Auckland --json
python3 skills/akl-housing-capacity/scripts/cli.py capacity --area Whau --json
python3 skills/akl-housing-capacity/scripts/cli.py capacity --detail typology --area Whau --json
python3 skills/akl-housing-capacity/scripts/cli.py capacity --dataset business --json
python3 skills/akl-housing-capacity/scripts/cli.py demolitions --area Auckland --json
```

1. Use `sources` for the offline verified URL registry and access limitations.
   It labels records `retrieval_kind: source_registry`; it does not fetch data.
2. `housing-update` discovers the current XLSX link on the official landing page.
   `--month` selects an **observation month** from the latest workbook, not an
   archived publication. Without it, Council results use the latest month per
   sheet and area; HUD results use the latest delivery month for the chosen area.
   The default HUD area is Auckland. Council results include regional consents,
   CCCs, parcel creation and local-board consents. Area matching ignores accents,
   spaces and hyphens; a name substring can match more than one board.
   These Council consent counts are Auckland Council's monthly datasheet. They
   are not the Stats NZ building-consents release: use `statsnz-building-consents`
   for official national and regional counts, values, floor area and seasonal
   adjustment. Do not add the two series. Council CCCs are completion evidence,
   not consents, and HUD `Delivery` also includes leases, transfers and stock
   removals.
3. `capacity` returns paired plan-enabled/feasible dwelling totals from the PC78
   model. `--detail typology` returns built-form capacity and dwelling prices
   under the alternative `Max_Profit` and `MinDUPrice` selections. Keep scenarios
   separate; do not sum overlapping selections or regional and local-board totals.
4. `capacity --dataset business` verifies and inventories the public HBA 2023
   ZIP. These are file counts and sizes for File Geodatabases, not business
   feature counts or floorspace estimates. Feature queries need GIS software.
5. `demolitions` returns exit 7 (`unsupported_operation`) with the public Kāinga
   Ora OIA URL. The release is PDF-only, and live retrieval was blocked on the
   verification network; no structured site extract was verified. Do not
   interpret this error as zero demolitions.

`--zone` is accepted on `capacity` but returns exit 7: the supported XLSX tables
have no zone field. For **PC120 zoning maps**, use the existing `nz-arcgis` skill
with the relevant Auckland Council service. PC120 zoning and the historic PC78
capacity model are different sources and dates. These summary commands contain
no coordinates, so they do not offer `--bbox` or GeoJSON.

JSON uses `{meta, results}` with source URL, publisher and UTC retrieval time;
known data licence and latest reporting period appear in `meta`. Errors use the
same envelope, empty results and a typed `error`, and exit non-zero. Valid filters
with no matching observations return an empty results array. Each required Council
sheet, and the HUD `Delivery` series, must exist before those filters are applied.
Missing sheets, renamed series, unexpected local-board headers, implausible
periods and malformed workbooks are schema failures, not empty successes.
A discovered download on an allowed host that uses a non-default port is
upstream unavailable.

Read [references/source-notes.md](references/source-notes.md) for exact downloads,
field meanings, licensing, overlap and coverage limits. The XLSX reader in
`scripts/workbook.py` uses `zipfile` and `xml.etree.ElementTree`, streams the large
HUD worksheet, and reads cached formula results without calculating formulas.
Synthetic format fixtures live in `tests/fixtures/`.

```bash
python3 skills/akl-housing-capacity/scripts/test_contract.py
python3 skills/akl-housing-capacity/scripts/smoke_test.py
```

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-housing-capacity 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-housing-capacity?

CallGet help
Cite this page

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