agentsclimarketplace
Sign in

Nz phd supervisor list

Skill pengqianhan/NZ-life-skills/skills/nz-phd-supervisor-list

Build and maintain a source-grounded shortlist of New Zealand PhD supervisors, combining official university profile details, research-fit signals, supervision accreditation where available, and clearly labelled student-submitted mentoring anecdotes. Use when Codex needs to collect, compare, update, or answer questions about potential doctoral supervisors in New Zealand while avoiding unsupported reputational claims.From its SKILL.md

Install
npx -y skills add pengqianhan/NZ-life-skills --skill nz-phd-supervisor-list

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.4 KB, 542 tokens by cl100k_base, as published. Nobody here has run it

NZ PhD Supervisor List

Overview

Use this skill to collect and maintain a careful New Zealand PhD supervisor shortlist. Treat the list as a research-fit and mentoring-signal aid, not as a definitive ranking of people.

Workflow

  1. Clarify the user's research direction, target discipline, stage, and constraints such as city, university, funding, visa timeline, or preferred supervision style.
  2. Read references/current-guidance.md.
  3. Read references/supervisors.md when the user asks for existing candidates, additions, comparisons, or updates.
  4. Separate:
    • official public facts
    • research-fit interpretation
    • student-submitted anecdotes
    • unknowns that require checking
  5. Verify current official profile pages before giving current titles, contact details, supervision availability, recruitment status, or doctoral accreditation.
  6. When adding a supervisor, update references/supervisors.md using the existing entry schema.

Scope

  • collect public profile information, research areas, affiliation, contact URLs, and supervision eligibility signals
  • record positive mentoring signals from student reports as labelled anecdotes, not verified facts
  • compare supervisors only with explicit criteria such as research fit, supervision availability, responsiveness evidence, and funding context
  • avoid defamatory claims, private personal details, or unsupported rankings

Source Order

  1. official university profile pages and university doctoral-supervision pages
  2. official research group, lab, institute, ORCID, and institutional publication pages
  3. student-submitted anecdotes only as labelled qualitative leads that require corroboration

Answering Rules

  • Do not describe someone as an "excellent supervisor" as an objective fact unless the wording is explicitly framed as a shortlist label or user-maintained criterion.
  • Keep student reports short, attributed by source type only, and separated from official facts.
  • Do not include negative allegations, private student identities, private messages, or unverifiable personal details in the list.
  • If a user wants to compare supervisors, show the criteria first, then compare only the evidence available for those criteria.
  • If a user's research direction does not match the seed list, say so and suggest how to search beyond the current list.
  • Use Chinese when the user asks in Chinese, but preserve English names, official titles, and source URLs.

References

What ships with it: 3 files

7.1 KB alongside SKILL.md

agents/

references/

Gives 0 of the 12 instructions most education skills give in 542 tokens

Counted across 169 of the 171 authors here whose files we hold, read 2026-08-07

  • Search for existing resources before creating new onesin 7 of 169, across 3 files
  • Check tool responses for errors before proceedingin 7 of 169, across 3 files
  • Reduce request frequency on rate limit errorsin 7 of 169, across 3 files
  • Confirm connection status is ACTIVE before running workflowsin 7 of 169, across 3 files
  • Execute prerequisite steps first in workflowsin 7 of 169, across 3 files
  • Handle pagination by fetching until exhaustedin 7 of 169, across 3 files
  • Re-authenticate if the connection expiredin 6 of 169, across 2 files
  • Always call RUBE_SEARCH_TOOLS first to get schemasin 6 of 169, across 2 files
  • Pass strictly schema-compliant tool argumentsin 6 of 169, across 2 files
  • Run the skill generator if the shared file is missingin 6 of 169, across 3 files
  • Create the coursein 5 of 169, across 3 files
  • List enrolled studentsin 5 of 169, across 3 files

Said here and by no other author read

  • clarify user research direction and constraints
  • read current guidance before answering
  • read supervisor list for candidate requests
  • separate official facts from anecdotes
  • verify current official profile pages
  • update supervisor list using existing schema

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.