Home / thecolab-ai / .skills · GitHub

find-experts-nz SKILL.md skillA

find-experts-nz 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/find-experts-nz@git:20260719.1748a98

Pins git:20260719.1748a98 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/find-experts-nz/SKILL.md
Versions recorded: 2
Latest version: git:20260719.1748a98, committed Jul 19, 2026
First version recorded: Jul 9, 2026
Size: 8,579 bytes
Repository stars: 33
License: MIT

Discover New Zealand experts by topic across public sources — the OpenAlex and Crossref scholarly graphs, Wikidata, ORCID, and university "Find an Expert" directories (University of Auckland, Massey). Use when you need a citable candidate shortlist of who could speak to a research question — expert matching, "find an expert", verifying a finding, or building an SME/advisory candidate list. Returns ephemeral shortlists from public data only — discovery is not consent and output is never a…

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

# Find Experts (NZ)

## Goal

Turn a research topic into a ranked, citable shortlist of NZ-affiliated experts —
who has published on this, where they're based, with links to public profiles.
Keyless, read-only queries across **two** scholarly graphs (OpenAlex + Crossref)
plus ORCID. Searching both broadens the range beyond universities into Crown
Research Institutes (NIWA, Manaaki Whenua, ESR…) and government science (e.g. MPI),
whose authors OpenAlex's institution filter often misses. Python stdlib only.

## Use this when

- A stream/finding flags an expertise gap and you need candidate people who could verify it.
- You're building a candidate list for a consented SME / advisory network.
- You want to corroborate a surprising claim by finding who researches it in NZ.
- You need a public, machine-readable link (OpenAlex id / ORCID iD) for reproducible provenance.

## Do not use this for

- Building or storing a contact list. **Discovery is not consent.** Output is an
  *ephemeral* shortlist for a human steward to review — never a mailing list, never
  auto-contacted, never persisted as a `candidate` registry.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add thecolab-ai/.skills/find-experts-nz@sha256:e495512b1a30f597

The line at the top of this page pins the label git:20260719.1748a98, 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_sinzvbgrd4d27w6c.svg)](https://markdownregistry.com/a/art_sinzvbgrd4d27w6c)

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

Versions

The registry has recorded 2 versions of this file, between Jul 9, 2026 and Jul 19, 2026, about one every 10 days.

version	committed	commit	size	audit
git:20260719.1748a98 latest	2026-07-19	1748a98	8,579 B	A	view · diff
git:20260709.437a2b1	2026-07-09	437a2b1	7,518 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 (8579 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_sinzvbgrd4d27w6c
GET https://markdownregistry.com/api/v1/resolve?ref=thecolab-ai/.skills/find-experts-nz
GET https://markdownregistry.com/api/v1/blob/e495512b1a30f59785028c0c80e50e156229599105c3edb774a2501d1f9688b4

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.