nz-stac SKILL.md skillA

nz-stac from thecolab-ai/.skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add thecolab-ai/.skills/nz-stac@git:20261011.1a28fac

Pins git:20261011.1a28fac in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: thecolab-ai/.skills
Path: skills/nz-stac/SKILL.md
Versions recorded: 2
Latest version: git:20261011.1a28fac, committed Oct 11, 2026
First version recorded: Oct 8, 2026
Size: 6,295 bytes
Repository stars: 33
License: MIT

Find LINZ elevation, coastal LiDAR, and aerial imagery collections and COG tiles from public NZ STAC catalogues. Use for DEM/DSM, coastal elevation footprints, RGB/infrared footprints, bbox tile searches and elevation point sampling guidance.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# NZ STAC

Find datasets and Cloud Optimised GeoTIFF (COG) tile URLs in LINZ's public
`nz-elevation`, `nz-imagery`, and `nz-coastal` AWS buckets, hosted in
`ap-southeast-2`. Python 3.10+, stdlib only; no AWS credentials, boto3, or
LINZ Data Service key. Coastal commands return collection metadata and COG
hrefs only. They do not download DEM or DSM rasters.

## Workflow

1. Run `collections` with the bucket kind and optional region. Copy the returned
   `collection` selector (kind plus published path), or use its HTTPS
   `collection.json` URL. `info` returns the upstream STAC id and full metadata.
2. Check capture interval, product and resolution with `info`. DEM represents
   terrain; DSM includes surface features. Use the source capture dates for
   freshness, rather than its processing/update date.
3. Use a small WGS84 bbox to find tiles. `--format geojson` emits a
   FeatureCollection of the actual STAC footprints. Assets are public HTTPS COG
   URLs. The helper fetches bounded JSON metadata only, never raster files.
4. For a terrain point, use an elevation DEM collection with `point`. Coastal
   collections are not accepted there. It returns
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add thecolab-ai/.skills/nz-stac@sha256:0e2898a40026065e

The line at the top of this page pins the label git:20261011.1a28fac, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_enevdyvad6zhisdv.svg)](https://markdownregistry.com/a/art_enevdyvad6zhisdv)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Oct 8, 2026 and Oct 11, 2026, about one every 4 days.

version	committed	commit	size	audit
git:20261011.1a28fac latest	2026-10-11	1a28fac	6,295 B	A	view · diff
git:20261008.c9d8874	2026-10-08	c9d8874	5,284 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (6295 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

thecolab-ai/.skills · 33 stars · license MIT · pushed 2026-10-12 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_enevdyvad6zhisdv
GET https://markdownregistry.com/api/v1/resolve?ref=thecolab-ai/.skills/nz-stac
GET https://markdownregistry.com/api/v1/blob/0e2898a40026065e39192a3fbe01d6fd369791b5e340df271ad1bf8e68f7156a

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.