Model or dataset
HKUSTDial/Supervisor-Skills avatar
HKUSTDial/Supervisor-Skills

Supervisor-Skills: HKUST(GZ) research skills packaged for Claude and GPT-4

Distills a decade of a PhD advisor's research experience into directly usable AI skills — an AI research co-advisor from idea generation to paper submission.

12,586 stars745 forksPythonNOASSERTION

At a glance

What is it?
Supervisor-Skills is a repository of executable AI skills and a handbook that distils a decade of supervision experience at HKUST(GZ) into prompts for idea evaluation, paper writing and pre-submission review. It is a prompt library, not a runtime, and that shapes who can use it.
Who is it for?
Adopt Supervisor-Skills if you are a PhD student or early-career researcher who already works inside a chat model such as Claude or GPT-4 and wants structured, opinionated checklists for idea evaluation, drafting and pre-submission review. Skip it if you need a runnable pipeline, an API or a self-hosted service, because the repository is mainly Markdown skills and a handbook rather than a service.
Can I use it commercially?
Check first. The repository uses a licence we do not classify automatically, so read its LICENSE file before any commercial use.
Is it still maintained?
Yes. The repository last received commits 10 days ago.
What is it written in?
Mainly Python, according to GitHub's language statistics.

Answers come from the project's GitHub data, last synced on November 15, 2026, and from our analysis. They are not legal advice.

From daily snapshots

Star history

  • HKUSTDial/Supervisor-Skills12,586 ★ · +5,069
Star history
Repository2026-09-242026-11-15
HKUSTDial/Supervisor-Skills7.5k12.6k

5,069 Stars in the last 52 days, measured from the daily GitHub snapshot. Compare with other projects

Editorial analysis

The last-mile problem Supervisor-Skills targets

The README frames the project around what it calls the "last-mile problem" in research: a student can read every methodology guide and still not know how to evaluate their own idea, structure an Introduction, or judge whether a figure meets a top-conference standard. The author, Luo Yuyu, an assistant professor at HKUST(GZ), states that the skills distil ten years of publishing and reviewing experience from venues such as SIGMOD, VLDB, ICML and NeurIPS into prompts a large language model can execute. The intended user is a graduate student who already has a topic but lacks timely feedback. The project is explicit that a generic prompt does not produce research taste, which is why it ships a handbook alongside the skills rather than prompts alone. That pairing is the actual product: theory in handbook/, executable checklists in skills/.

How the skills and handbook are organised

The repository has two tracks. The handbook/ directory holds Markdown chapters in six groups, from evaluating paper quality through idea generation, writing, plotting, Vibe Research and case studies of specific papers (Alpha-SQL at ICML 2025, AFlow at ICLR 2025, LEAD at VLDB 2026). The skills/ directory holds twelve named skill folders, including idea-evaluator, deep-research, intro-drafter, paper-writer, paper-polish, pre-submission-reviewer, figure-designer, rebuttal-guidance and drawio-reconstruction. The v2.1 news entry in the README says paper-writer, paper-polish and deep-research were added, that intro-drafter was upgraded to produce body text, and that evaluation and review skills gained subject-paradigm routing. Each skill is a directory of instructions the model reads; the model does the work, and the repository supplies the structure, the checklist and the routing logic.

Installing Supervisor-Skills and running idea-evaluator

The README's skills section says to copy a skill's contents into your AI assistant. The repository is consumed by cloning it and pointing your model at the relevant skill directory. The README's own layout shows the two directories you need:

code
Supervisor-Skills/
├── handbook/                          # 科研与写作系统指南
├── skills/                            # 提炼出的可执行 AI Skills
│   ├── idea-evaluator/                
│   ├── deep-research/
│   ├── paper-writer/
│   └── pre-submission-reviewer/
└── assets/

Once the repository is on disk, open the skill you want and load its instructions into your model session. The README says you can copy a skill's contents directly into your AI assistant (Claude, DeepSeek and Kimi are named), so the mechanics depend on your client. The README also points to a companion PDF, handbook/01_Preliminary/博士生科研入门辅导.pdf, for offline reading, and to the matching handbook chapters under handbook/02_Idea_Generation/ for idea work and handbook/03_Paper_Writing/ for drafting.

Where Supervisor-Skills stops being the right tool

The repository is a knowledge artefact, not a system. If your requirement is an automated review step in a submission system, or a service your team calls over HTTP, the repository itself is a set of skill files rather than a service. The second limit is model dependence: the skills assume a capable chat model such as Claude or GPT-4, and their output quality tracks that model's judgement. Third, the project is early. The README says so directly, and the News entries run from April 2026 to September 2026, with the last push on 2026-10-16. The repository has no GitHub releases, so upgrade tracking is manual.

How it differs from a literature tool or a paper generator

The closest familiar alternative is a literature-search or paper-generation tool, and the difference is where the judgement sits. A search tool retrieves and summarises; a generation tool produces text from a prompt. Supervisor-Skills inserts an explicit evaluative layer between the two, with named skills such as idea-evaluator and pre-submission-reviewer that evaluate and review drafts. The handbook chapter on evaluating paper quality, which takes the reviewer's view across Novel Problem, Novel Method, Nice Story and Nice Presentation, is the clearest expression of that stance. The deep-research skill does cover survey-level literature research, with multi-perspective search and per-citation verification, though it runs inside your own AI assistant. If you want something that tells you your motivation figure does not land, the figure-designer and pre-submission-reviewer skills are aimed at exactly that, though the README does not quantify how well they do it.

Licence, maintenance and upgrade cost

The repository metadata reports NOASSERTION and the README text in source names no licence, so the LICENSE file is the one to read before you rely on anything. If it is a non-commercial licence such as CC BY-NC-SA 4.0, commercial use is restricted; that matters if you plan to embed these skills in a paid product or an institutional service. This is a description of the licence text, not legal advice. On maintenance, the last push was on 2026-10-16, and the repository is not archived, so the project is current as of that date. There is no release artefact to pin, so your upgrade path is a fresh copy of the repository and a diff against skills/ and handbook/, plus a read of CHANGELOG.md. Budget time for that after any update, because a changed skill file changes model behaviour; the README's News and CHANGELOG.md record versions such as v2.1.

Editorial conclusion

Adopt Supervisor-Skills if you are a PhD student or early-career researcher who already works inside a chat model such as Claude or GPT-4 and wants structured, opinionated checklists for idea evaluation, drafting and pre-submission review. Skip it if you need a runnable pipeline, an API or a self-hosted service, because the repository is mainly Markdown skills and a handbook rather than a service. Before you commit, read the LICENSE file, since GitHub reports the licence as NOASSERTION, and check that its terms fit your institution, then open one skill directory under skills/ and confirm its prompt structure matches the model you plan to use.

Frequently asked questions

What is Supervisor-Skills and who is it for?

It is a repository of AI skills and a handbook that packages research methodology for idea evaluation, paper writing, plotting and pre-submission review. The README describes it as aimed at graduate students who need structured feedback between supervisor meetings.

Does Supervisor-Skills work with Claude and GPT-4?

The README states that the skills are structured to be executed by large language models such as Claude and GPT-4. There is no runtime in the repository, so the model you use supplies the execution.

How do I set up Supervisor-Skills?

The README's skills section says to copy the skill content into your AI assistant. In practice that means obtaining the repository and loading the relevant skill under skills/ into your model session.

What licence does Supervisor-Skills use?

The repository metadata reports NOASSERTION, so the LICENSE file is the authoritative source; check its terms for your use case.

Official sources

  1. HKUSTDial/Supervisor-Skills on GitHub
  2. Issues
  3. README
Add this badge to your README

If you maintain this project, the badge below links readers to this analysis and shows its maintenance status from the daily GitHub snapshot. Paste the markdown into your README; add ?metric=license or ?metric=stars to the image URL for a different field.

Add this badge to your README

markdown
[![Hysen Labs](https://hysenlabs.com/badge/hkustdial-supervisor-skills.svg)](https://hysenlabs.com/projects/hkustdial-supervisor-skills)

Star history chart for your README

markdown
[![Star history](https://hysenlabs.com/chart/hkustdial-supervisor-skills.svg)](https://hysenlabs.com/projects/hkustdial-supervisor-skills)

Was this useful?