New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Vibe Research Workflow

by HKUSTDial in HKUSTDial/Supervisor-Skills

Orchestrates AI-assisted research across coding, figure production and writing, picking the right tool for each stage while keeping academic judgment with the researcher.

CC-BY-4.0Auto-check passedResearch & Science

Install Vibe Research Workflow

skills CLI
$ npx skills add HKUSTDial/Supervisor-Skills --skill vibe-research-workflow -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install HKUSTDial/Supervisor-Skills vibe-research-workflow --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/HKUSTDial/Supervisor-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/vibe-research-workflow .claude/skills/vibe-research-workflow && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
vibe-research-workflow
GitHub stars
8.7k
Token cost
~1.9k tokens
SKILL.md length
919 words
Files
6 (incl. references)
Skills in repo
12
Repo updated
First seen
Licence
CC-BY-4.0

At a glance

Orchestrates AI-assisted research across coding, figure production and writing, picking the right tool for each stage while keeping academic judgment with the researcher.

  • Works in 12 steps: Phase classification → Behavioural rules recap → Phase-specific procedure → …
  • Starting an AI-assisted coding, figure, or writing session for a research project
  • SKILL.md covers Overview, When to use this skill, When NOT to use this skill and Core procedure, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Three sub-flows are covered: Vibe Coding for AI-assisted implementation, Vibe Figure for AI-assisted figure production, and Vibe Writing for AI-assisted prose polish. Each is governed by six behavioral rules that separate acceptable use, such as mechanical acceleration, auxiliary suggestions and style correction, from academic misconduct, such as fabricated citations, outsourced scientific judgment or hidden AI authorship. The skill recommends a specific tool for the current stage among Cursor, Claude Code, Codex, Figma and Gemini.

It positions itself as a meta-skill that orchestrates tool selection and integrity enforcement across a session rather than doing the drafting or implementation itself, consolidating a curriculum's Vibe Research section into one procedure. It explicitly defers actual prose drafting to separate paper-writer or intro-drafter skills, actual code implementation to the coding tools it recommends, and research-direction evaluation to an idea-evaluator skill, while reminding users that venue and school AI-disclosure policies still apply and that they remain responsible for verifying drafted or figure output against their own research.

When your agent uses it

  • Starting an AI-assisted coding, figure, or writing session for a research project
  • Deciding which AI tool fits the current stage of a research task
  • Checking whether AI-assisted research output has drifted into academic misconduct

Example prompts

  • “How should I use AI for coding up this experiment without crossing into misconduct?”
  • “Which tool should I use to turn these raw results into a publication figure?”
  • “Give me a vibe research plan for a multi-day data analysis and writing sprint.”

Workflow steps

12 steps, taken from the step headings in SKILL.md.

  1. Phase classification
  2. Behavioural rules recap
  3. Phase-specific procedure
  4. Tool selection
  5. Integrity gate
  6. Output
  7. Phase
  8. Behavioural rules recap
  9. Workflow plan
  10. Tool recommendations
  11. Red-line reminders
  12. Integrity gate plan

What it can do on your machine

Read from SKILL.md and the folder at commit 207bc6f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Vibe Research Workflow loads about 1.9k tokens when it runs, and up to ~8.2k if it reads all its reference files. Until then it costs about 124 tokens; SKILL.md has 919 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~124
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~8.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from HKUSTDial/Supervisor-Skills at commit 207bc6f, republished under its CC-BY-4.0 licence (© HKUSTDial). 919 words, ~1,863 tokens.

Download SKILL.mdSave it as .claude/skills/vibe-research-workflow/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
vibe-research-workflow
description
Guides AI-assisted research across three sub-flows, Vibe Coding, Vibe Figure, and Vibe Writing, with behavioural rules that keep the user in charge of academic judgment while delegating mechanical work to AI. Recommends the right tool (Cursor, Claude Code, Codex, Figma, Gemini) for the current stage. Use when the user asks 'how to use AI for research', 'Vibe Coding tips', 'AI-assisted writing workflow', 'which AI tool for this', or starts an AI-assisted work session.
license
CC-BY-4.0

Vibe Research Workflow

Overview

Vibe Research is the modern research workflow where large language models and AI coding tools handle mechanical tasks (implementation, figure rendering, language polish) while the researcher retains full ownership of research direction, problem framing, experimental design, and factual accuracy. The goal is a two-to-five times productivity gain on routine tasks without compromising academic integrity.

The skill has three sub-flows: Vibe Coding (AI-assisted code), Vibe Figure (AI-assisted figure production), Vibe Writing (AI-assisted prose polish). Each is governed by six behavioural rules that draw a hard line between acceptable use (mechanical acceleration, auxiliary suggestions, style correction) and academic misconduct (fabricated citations, outsourced scientific judgment, hidden AI authorship).

This skill is a meta-skill that orchestrates tool selection, flow design, and integrity enforcement across a research session. It consolidates the the curriculum's Vibe Research section into a single invocable procedure.

When to use this skill

  • Starting a new AI-assisted work block (a morning of coding, a figure day, a writing session).
  • The user asks 'how to use AI for research', 'Vibe Coding tips', 'AI-assisted writing workflow', 'which AI tool for this'.
  • The user is choosing between Cursor, Claude Code, Codex, Figma, Gemini, or other tools.
  • The user wants a workflow plan for a multi-day project involving AI.
  • The user suspects AI output has drifted into unacceptable territory (fabricated citations, outsourced reasoning).

When NOT to use this skill

  • The user wants paper prose drafted. That is legitimate under this plugin's evidence discipline and belongs to the drafting skills: route to paper-writer (any section) or intro-drafter (Introductions), whose rules forbid fabricated substance (every factual claim traces to the user's materials, verified retrieval, or field common knowledge). Remind the user that venue and school AI-disclosure policies still apply, and that they remain responsible for verifying every drafted passage against their actual research. What stays forbidden is fabrication, not drafting.
  • The user wants a code implementation done. This skill guides the process; it does not replace the implementation itself.
  • The user wants to evaluate research direction. Use idea-evaluator (see handbook 2.3 for disruptive-innovation deep-dive).

Core procedure

Step 1: Phase classification

Decide which phase the user is in: coding, figure, writing, or mixed.

Step 2: Behavioural rules recap

See: references/behavior-guidelines.md for the full six-rule set.

State the six rules succinctly at the start of the session:

  1. AI-assisted work is permitted for literature search and organisation, code and debugging support, language and expression polish.
  2. Research ideas, problems, designs, technical paths, experimental plans, core conclusions, and novelty must be the user's own and fully understood. Drafting assistance is legitimate within that boundary: the substance belongs to the user; the linguistic realization may be AI-assisted; the verification duty (rule 3) is unchanged.
  3. Every AI-generated or AI-assisted passage is verified by the user against the actual research process, experimental results, and facts.
  4. No fabricated citations; references come from the user's own reading and confirmation.
  5. No academic misconduct, including fabricated data, experimental results, or plagiarism concealment.
  6. Venue or school AI-disclosure requirements are honoured.

These rules are non-negotiable and enforced in the integrity gate.

Step 3: Phase-specific procedure

For Vibe Coding, see: references/vibe-coding.md.

For Vibe Figure, see: references/vibe-figure.md.

For Vibe Writing, see: references/vibe-writing.md.

Each phase has its own core techniques (Plan Mode, Small Steps, Clear Requirements for coding; four-step figure workflow; red-line rules for writing).

Show full SKILL.md (369 more words)Show less
Step 4: Tool selection

See: references/tool-selection.md for the tool matrix.

Match tool to phase:

  • Coding: Cursor (IDE-native) or Claude Code (agentic CLI) or Codex.
  • Figure: PowerPoint plus Figma for static figures; Matplotlib plus Seaborn for experimental results; Gemini for first-draft sketches.
  • Writing: Claude or ChatGPT for language polish; Grammarly for grammar; Overleaf for LaTeX.
Step 5: Integrity gate

Before closing the session, run the checks in the Integrity gate section below.

Step 6: Output

Emit the workflow plan in the Output format below.

Integrity gate

This skill is a behavioural nudge, not a verification engine. Most bullets are tagged [user-attest] because the LLM cannot actually observe the user's private verification work. [inspection] tags apply only to checks the LLM can confirm from its own outputs and the user's session history.

Before ending the session:

  1. [inspection] The six behavioural rules have been stated at the start of the session.
  2. [user-attest] No fabricated citation has been introduced or accepted. (The LLM cannot verify citations without web access; the user confirms via DBLP or arXiv.)
  3. [user-attest] The user's research direction, framing, and contributions are owned by the user, not by AI.
  4. [user-attest] Every AI-generated code block has been reviewed and tested by the user.
  5. [user-attest] Every AI-drafted paragraph has been rewritten or at minimum sentence-by-sentence verified by the user.
  6. [attestation] Venue or school AI-disclosure rules have been checked. The skill asks the user to name the venue and surfaces known policy types; the user confirms compliance.
  7. [user-attest] The user's own expertise is still driving the project; AI is an accelerator, not a replacement.

Any red-line violation (rules 1-6) stops the session. The user should fix the violation or consult an advisor before continuing. Because most bullets are [user-attest], the skill's effective value is the reminder at session start, not a runtime block.

Output format

1. Phase
  • Primary phase: <coding or figure or writing or mixed>
  • Secondary phases: <list>
2. Behavioural rules recap
  • Rule 1-6 (see references/behavior-guidelines.md): acknowledged
3. Workflow plan
Time blockPhaseActivityToolUser check
...............
4. Tool recommendations
PhasePrimary toolAlternativeReason
Coding.........
Figure.........
Writing.........
5. Red-line reminders
  • ... (from references/vibe-writing.md)
6. Integrity gate plan
  • Verification points: ...
  • AI-disclosure requirements for the target venue: ...

© HKUSTDial, CC-BY-4.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (references) in skills/vibe-research-workflow of HKUSTDial/Supervisor-Skills.

  • SKILL.md
  • references/behavior-guidelines.md
  • references/tool-selection.md
  • references/vibe-coding.md
  • references/vibe-figure.md
  • references/vibe-writing.md

Open the folder on GitHubat commit 207bc6f

Compare with similar skills

Vibe Research Workflow next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Vibe Research Workflow compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Vibe Research Workflow this skillHKUSTDial/Supervisor-Skills8.7k—~1.9kAutomated safety check: PassCC-BY-4.0
Peer ReviewK-Dense-AI/claude-scientific-writer2.4k2 repos~3.1kAutomated safety check: NotesMIT
CHARLS Paper Reproduction Guidexjtulyc/MedgeClaw6171 repos~1.8kAutomated safety check: PassNone
Compute Environment Setupaipoch/open-science5.5k—~2.6kAutomated safety check: PassApache-2.0
Figure Styleaipoch/open-science5.5k—~5.1kAutomated safety check: PassApache-2.0
Add Bactopia Toolbactopia/bactopia522—~4.1kAutomated safety check: PassMIT

Similar skills

  • Peer Review

    K-Dense-AI/claude-scientific-writer

    Prepare evidence-bounded, constructive peer-review drafts and structured manuscript assessments.

    2.4k GitHub starsUsed in 2 repos~3.1k tokens
    Research & ScienceAuto-check: notes

  • CHARLS Paper Reproduction Guide

    xjtulyc/MedgeClaw

    Guides an agent through reproducing papers built on the CHARLS health and retirement survey, from variable mapping to cognition, depression and isolation scores.

    617 GitHub starsUsed in 1 repo~1.8k tokens
    Research & ScienceAuto-check passed

  • Compute Environment Setup

    aipoch/open-science

    Prepares setup instructions and a named activation file for a user-managed software environment on an Open-Science SSH or Slurm compute host.

    5.5k GitHub stars~2.6k tokensUpdated today
    Research & ScienceAuto-check passed

  • Figure Style

    aipoch/open-science

    Publication-grade correctness and legibility rules for final-deliverable scientific figures, not exploratory plots.

    5.5k GitHub stars~5.1k tokensUpdated today
    Research & ScienceAuto-check passed

  • Add Bactopia Tool

    bactopia/bactopia

    Scaffold a complete Bactopia Tool across all three tiers -- module, subworkflow, and workflow entry point under workflows/bactopia-tools/.

    522 GitHub stars~4.1k tokensUpdated 2 mo ago
    Research & ScienceAuto-check passed

  • Modeling Code and Result Contracts

    yushui2022/MathModel-Skill

    Generates result-evidence contracts, tables and runnable q1 to q3 modeling code scaffolds for a math modeling paper from a model route, a data plan and cleaned data.

    453 GitHub stars~1.4k tokensUpdated 2 days ago
    Research & ScienceAuto-check passed

More from HKUSTDial/Supervisor-Skills

All 12 skills in this repo

  • Benchmark Paper Template

    HKUSTDial/Supervisor-Skills

    Structures benchmark and evaluation papers around five pillars, with a completeness audit, an Introduction logic chain, a section skeleton and a pre-submission checklist.

    8.7k GitHub stars~2.8k tokensUpdated 1 mo ago
    Auto-check passed

  • Draw.io Diagram Reconstruction

    HKUSTDial/Supervisor-Skills

    Rebuilds a reference diagram image as an editable, high-fidelity Draw.io file, mixing native elements, SVG icons and cropped PNGs, with a batch workflow for a folder of images.

    8.7k GitHub stars~5.4k tokensUpdated 1 mo ago
    Auto-check passed

  • Paper Introduction Drafter

    HKUSTDial/Supervisor-Skills

    Drafts the Introduction of a technical paper as six paragraphs of flowing prose, positioning the work and matching contributions to challenges, with an outline on request.

    8.7k GitHub stars~2.4k tokensUpdated 1 mo ago
    Auto-check passed

  • Rebuttal Guidance

    HKUSTDial/Supervisor-Skills

    Turns pasted peer-review comments into a per-concern rebuttal plan, with reviewer mindset matching and strategy priorities, but not the final rebuttal text.

    8.7k GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed

  • Deep Research Literature Survey

    HKUSTDial/Supervisor-Skills

    Runs a survey-grade literature investigation: fixes the research questions, searches from adversarial angles, verifies citations and writes an evidence-first report.

    8.7k GitHub stars~2.4k tokensUpdated 1 mo ago
    Auto-check passed

  • Paper Figure Designer

    HKUSTDial/Supervisor-Skills

    Advises on designing the three core figures of a technical paper, then audits them against rules for format, fonts, color and captions.

    8.7k GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about Vibe Research Workflow

What does Vibe Research Workflow do?

Orchestrates AI-assisted research across coding, figure production and writing, picking the right tool for each stage while keeping academic judgment with the researcher. Three sub-flows are covered: Vibe Coding for AI-assisted implementation, Vibe Figure for AI-assisted figure production, and Vibe Writing for AI-assisted prose polish. Each is governed by six behavioral rules that separate acceptable use, such as mechanical acceleration, auxiliary suggestions and style correction, from academic misconduct, such as fabricated citations, outsourced scientific judgment or hidden AI authorship.

When should I use Vibe Research Workflow?

Vibe Research Workflow fits situations like: starting an AI-assisted coding, figure, or writing session for a research project; deciding which AI tool fits the current stage of a research task; checking whether AI-assisted research output has drifted into academic misconduct.

How do I install Vibe Research Workflow in Claude Code?

Run `npx skills add HKUSTDial/Supervisor-Skills --skill vibe-research-workflow -a claude-code`. Or copy the skill folder (skills/vibe-research-workflow in HKUSTDial/Supervisor-Skills) into .claude/skills/vibe-research-workflow in your project. Claude Code loads it when a task matches its description.

How do I install Vibe Research Workflow in Codex?

Run `npx skills add HKUSTDial/Supervisor-Skills --skill vibe-research-workflow -a codex`. Or copy the skill folder (skills/vibe-research-workflow in HKUSTDial/Supervisor-Skills) into .agents/skills/vibe-research-workflow in your project. Codex loads it when a task matches its description.

Can I use Vibe Research Workflow in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HKUSTDial/Supervisor-Skills --skill vibe-research-workflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vibe-research-workflow, .gemini/skills/vibe-research-workflow, .github/skills/vibe-research-workflow and .opencode/skills/vibe-research-workflow in your project.

What does Vibe Research Workflow need to run?

SKILL.md names no scripts, command-line tools or credentials: Vibe Research Workflow is instructions for the agent only.

Does Vibe Research Workflow access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Vibe Research Workflow safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Vibe Research Workflow use?

Vibe Research Workflow is published under the CC-BY-4.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Vibe Research Workflow use?

About 1.9k tokens (SKILL.md is roughly 7.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6.3k tokens, read only when the agent opens those files.

What are the alternatives to Vibe Research Workflow?

Skills that share tags, products or a category with Vibe Research Workflow: Peer Review (K-Dense-AI/claude-scientific-writer, 2.4k stars), CHARLS Paper Reproduction Guide (xjtulyc/MedgeClaw, 617 stars), Compute Environment Setup (aipoch/open-science, 5.5k stars) and Figure Style (aipoch/open-science, 5.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Vibe Research Workflow?

HKUSTDial (a GitHub organization) maintains it in HKUSTDial/Supervisor-Skills, which has 8,650 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on September 5, 2026.

Source: HKUSTDial/Supervisor-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.