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

AI Scientist V2 Guide

by wentorai in wentorai/research-plugins

Automated scientific discovery via agentic tree search by Sakana AI

MITAuto-check: notesResearch & Science

Install AI Scientist V2 Guide

skills CLI
$ npx skills add wentorai/research-plugins --skill ai-scientist-v2-guide -a claude-code

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

GitHub CLI
$ gh skill install wentorai/research-plugins ai-scientist-v2-guide --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/wentorai/research-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/research/automation/ai-scientist-v2-guide .claude/skills/ai-scientist-v2-guide && 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
ai-scientist-v2-guide
GitHub stars
298
Used in
1 other repo
Token cost
~2.4k tokens
SKILL.md length
560 words
Files
1
Skills in repo
405
Repo updated
First seen
Licence
MIT

At a glance

Automated scientific discovery via agentic tree search by Sakana AI

  • Works in 4 steps: Idea Generation → Agentic Tree Search → Experiment Execution → …
  • Research & Science work in your project
  • SKILL.md covers Overview, Installation and Setup, Core Research Pipeline and Research Templates, plus 3 more sections
  • Calls conda, python and git; reaches github.com; needs OPENAI_API_KEY and ANTHROPIC_API_KEY

What it does

AI Scientist V2 Guide is an agent skill from wentorai/research-plugins. Automated scientific discovery via agentic tree search by Sakana AI

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Research & Science. The repository describes itself as: 350+ academic research skills, MCP configs, and plugins for Research-Claw and AI agents. The licence is MIT.

When your agent uses it

  • Research & Science work in your project

Example prompts

  • “/ai-scientist-v2-guide”

Requirements

  • Python 3
  • A credential in OPENAI_API_KEY
  • A credential in ANTHROPIC_API_KEY

Workflow steps

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

  1. Idea Generation
  2. Agentic Tree Search
  3. Experiment Execution
  4. Paper Generation

What it can do on your machine

Read from SKILL.md and the folder at commit bf44b3c. 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

    Shell commands in SKILL.md call:

    • conda
    • python
    • git
    • pip
    • apt-get
    • brew

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    Also links to:

    • arxiv.org
    • sakana.ai

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

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • OPENAI_API_KEY
    • ANTHROPIC_API_KEY

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

Context cost

AI Scientist V2 Guide loads about 2.4k tokens when it runs. Until then it costs about 22 tokens; SKILL.md has 560 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~22
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteRuns commands with sudoSKILL.md:53
    sudo apt-get install texlive-full

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 wentorai/research-plugins at commit bf44b3c, republished under its MIT licence (© wentorai). 560 words, ~2,400 tokens.

Download SKILL.mdSave it as .claude/skills/ai-scientist-v2-guide/SKILL.md (or your agent's skills folder).
name
ai-scientist-v2-guide
description
Automated scientific discovery via agentic tree search by Sakana AI

AI Scientist v2 Guide

Overview

AI-Scientist-v2 is an open-source system developed by Sakana AI with over 2,000 GitHub stars that automates the full scientific research pipeline -- from idea generation through experimentation to paper writing. Building on the original AI Scientist, version 2 introduces an agentic tree search approach that systematically explores the space of research ideas, designs and runs experiments, analyzes results, and produces workshop-level scientific papers with minimal human intervention.

The key innovation in v2 is the tree search mechanism. Rather than pursuing a single research direction linearly, the system maintains a tree of possible research trajectories. At each node, the agent can branch into multiple experimental variations, evaluate the results, and prune unpromising directions while doubling down on successful ones. This mirrors how experienced researchers navigate the research landscape -- exploring broadly at first, then focusing resources on the most promising leads.

AI-Scientist-v2 has demonstrated the ability to generate novel, valid research papers in machine learning subfields including diffusion models, language model training, and optimization. While the generated papers are currently at workshop acceptance level, the system represents a significant step toward autonomous scientific discovery and is an invaluable tool for researchers looking to automate the more mechanical aspects of their research workflow.

Installation and Setup

bash
# Clone the repository
git clone https://github.com/SakanaAI/AI-Scientist-v2.git
cd AI-Scientist-v2

# Create a conda environment
conda create -n ai-scientist python=3.11
conda activate ai-scientist

# Install dependencies
pip install -r requirements.txt
Prerequisites

AI-Scientist-v2 requires several components:

bash
# LLM API access (required for ideation, analysis, and writing)
export OPENAI_API_KEY=$OPENAI_API_KEY
# Or Anthropic
export ANTHROPIC_API_KEY=$ANTHROPIC_API_KEY

# GPU access for running ML experiments
# Recommended: at least one NVIDIA GPU with 24GB+ VRAM

# LaTeX installation for paper compilation
# Ubuntu/Debian
sudo apt-get install texlive-full

# macOS
brew install --cask mactex
Configuration

Set up your research configuration:

python
# config.yaml
llm:
  provider: "openai"
  model: "gpt-4o"
  temperature: 0.7

search:
  max_depth: 5          # Maximum tree depth
  branching_factor: 3   # Number of branches per node
  pruning_threshold: 0.3  # Prune branches below this score

experiment:
  gpu_ids: [0, 1]       # Available GPUs
  timeout_hours: 2      # Max time per experiment
  num_seeds: 3          # Random seeds per experiment

paper:
  template: "icml"      # Paper template (icml, neurips, iclr)
  max_pages: 8          # Maximum paper length

Core Research Pipeline

Phase 1: Idea Generation

The system generates research ideas by analyzing existing literature and identifying gaps or extensions:

python
from ai_scientist import IdeaGenerator

generator = IdeaGenerator(
    research_area="efficient_transformers",
    seed_papers=[
        "path/to/related_paper_1.pdf",
        "path/to/related_paper_2.pdf",
    ],
    num_ideas=10,
)

ideas = generator.generate()
for idea in ideas:
    print(f"Title: {idea.title}")
    print(f"Hypothesis: {idea.hypothesis}")
    print(f"Novelty score: {idea.novelty_score}")
    print(f"Feasibility score: {idea.feasibility_score}")

The tree search mechanism explores the research space systematically:

python
from ai_scientist import TreeSearchResearcher

researcher = TreeSearchResearcher(
    idea=ideas[0],  # Start with the top-ranked idea
    base_code="templates/efficient_transformer/",
    config="config.yaml",
)

# Run the tree search
result = researcher.run()

# The search tree tracks all explorations
print(f"Tree depth reached: {result.max_depth}")
print(f"Total experiments run: {result.total_experiments}")
print(f"Best result: {result.best_node.metrics}")

The tree search works as follows:

  1. Root node: The initial research idea and baseline implementation
  2. Expansion: At each node, the agent proposes 2-4 modifications (hyperparameter changes, architectural tweaks, new training strategies)
  3. Evaluation: Each modification is implemented and evaluated experimentally
  4. Selection: Promising branches are selected for further exploration using UCB (Upper Confidence Bound) or similar strategies
  5. Pruning: Branches that underperform the baseline or show diminishing returns are pruned
Show full SKILL.md (235 more words)Show less
Phase 3: Experiment Execution

Experiments are executed in isolated environments with proper controls:

python
# Each experiment node contains:
class ExperimentNode:
    hypothesis: str          # What we're testing
    code_changes: list       # Specific code modifications
    config_changes: dict     # Hyperparameter changes
    results: dict            # Experimental results
    analysis: str            # LLM-generated analysis
    children: list           # Branch experiments

The system automatically handles experiment boilerplate including random seed management, metric logging, checkpoint saving, and result visualization. Each experiment is run with multiple seeds to ensure statistical significance.

Phase 4: Paper Generation

After the tree search completes, the system generates a scientific paper:

python
from ai_scientist import PaperWriter

writer = PaperWriter(
    research_result=result,
    template="neurips",
    sections=[
        "introduction",
        "related_work",
        "method",
        "experiments",
        "analysis",
        "conclusion",
    ],
)

# Generate the paper
paper = writer.write()

# Compile to PDF
paper.compile_latex("output/paper.pdf")

# The paper includes:
# - Abstract summarizing key findings
# - Introduction with motivation and contributions
# - Related work section with citations
# - Method description with equations
# - Experiment section with tables and figures
# - Analysis of results with ablation studies
# - Conclusion with future work directions

Research Templates

AI-Scientist-v2 includes several research templates that define the experimental domain:

NanoGPT Template

Train and evaluate small language models with various architectural modifications:

bash
python run_scientist.py \
  --template nanoGPT \
  --idea "Investigate the effect of rotary position embeddings on small-scale language model training" \
  --max_experiments 20
Diffusion Model Template

Experiment with diffusion model architectures and training strategies:

bash
python run_scientist.py \
  --template diffusion \
  --idea "Compare noise schedules for conditional image generation"
Creating Custom Templates

Define your own research template for your specific domain:

python
# templates/my_domain/template.py
class MyDomainTemplate:
    name = "my_research_domain"
    base_metrics = ["accuracy", "f1_score", "inference_time"]

    def setup_baseline(self):
        """Set up the baseline experiment."""
        pass

    def evaluate(self, model, data):
        """Evaluate a model configuration."""
        pass

    def get_modification_space(self):
        """Define the space of possible modifications."""
        return {
            "architecture": ["transformer", "lstm", "mamba"],
            "learning_rate": [1e-4, 3e-4, 1e-3],
            "batch_size": [32, 64, 128],
        }

Automated Paper Review

AI-Scientist-v2 includes an automated reviewer that evaluates generated papers using criteria from top ML venues:

python
from ai_scientist import PaperReviewer

reviewer = PaperReviewer(
    venue="neurips",
    review_criteria=[
        "novelty",
        "significance",
        "clarity",
        "correctness",
        "reproducibility",
    ],
)

review = reviewer.review("output/paper.pdf")
print(f"Overall score: {review.overall_score}/10")
print(f"Strengths: {review.strengths}")
print(f"Weaknesses: {review.weaknesses}")
print(f"Questions: {review.questions}")

Ethical Considerations and Limitations

When using AI-Scientist-v2, keep these considerations in mind:

  • Human oversight: Always review generated papers for correctness before submission. The system can produce plausible-sounding but incorrect analyses.
  • Attribution: If using AI-Scientist-v2 outputs in publications, disclose the use of automated research tools per venue guidelines.
  • Scope: The system works best for incremental research within well-defined experimental frameworks. Breakthrough conceptual contributions still require human creativity.
  • Compute cost: Tree search with multiple seeds per experiment can require substantial GPU time. Set appropriate budgets and timeouts.
  • Reproducibility: All experiments are logged with seeds, configurations, and code versions for full reproducibility.

References

© wentorai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/research/automation/ai-scientist-v2-guide of wentorai/research-plugins.

Open the folder on GitHubat commit bf44b3c

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in wentorai/research-plugins, which our catalogue first saw on October 7, 2026.

Compare with similar skills

AI Scientist V2 Guide 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.

AI Scientist V2 Guide compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
AI Scientist V2 Guide this skillwentorai/research-plugins2981 repos~2.4kAutomated safety check: NotesMIT
Perplexity Web Searchdavila7/claude-code-templates33k11 repos~3.5kAutomated safety check: NotesMIT
Hugging Face Paper Publisherhuggingface/skills11k4 repos~4.2kAutomated safety check: PassApache-2.0
Read GitHubAgentTeam-TaichuAI/ScienceClaw6712 repos~638Automated safety check: PassNone
DeepdiveSocialpranker/deepdive372—~5.2kAutomated safety check: PassMIT
tangermeme Genomic Model Analysisjmschrei/tangermeme318—~1.6kAutomated safety check: PassMIT

Similar skills

  • Perplexity Web Search

    davila7/claude-code-templates

    Runs web-grounded searches through Perplexity's Sonar models over OpenRouter for current events, recent literature and cited facts beyond the model's training cutoff.

    33k GitHub starsUsed in 11 repos~3.5k tokens
    Research & ScienceAuto-check: notes

  • Hugging Face Paper Publisher

    huggingface/skills

    Official

    Indexes research papers on the Hugging Face Hub from arXiv, links them to models and datasets, claims authorship and generates markdown research articles from templates.

    11k GitHub starsUsed in 4 repos~4.2k tokens
    Research & ScienceAuto-check passed

  • Read GitHub

    AgentTeam-TaichuAI/ScienceClaw

    Read and search GitHub repository documentation via gitmcp.io MCP service.

    671 GitHub starsUsed in 2 repos~638 tokens
    Research & ScienceAuto-check passed

  • Deepdive

    Socialpranker/deepdive

    Meta-research под вопрос или решение: веб-поиск, источники, Q&A отчёт с цитатами по файлам для повторного использования.

    372 GitHub stars~5.2k tokensUpdated 7 days ago
    Research & ScienceAuto-check passed

  • tangermeme Genomic Model Analysis

    jmschrei/tangermeme

    Routes agents to the right tangermeme reference for analyzing trained genomic deep learning models, from attributions and motif experiments to variant effects and design.

    318 GitHub stars~1.6k tokensUpdated today
    Research & ScienceAuto-check passed

  • HypoGeniC Hypothesis Generation

    K-Dense-AI/scientific-agent-skills

    Plans and audits runs of the HypoGeniC and HypoRefine packages, which propose hypotheses from labeled text datasets, with local checks before any model call.

    48k GitHub starsUsed in 1 repo~3.6k tokens
    Research & ScienceAuto-check: notes

More from wentorai/research-plugins

All 405 skills in this repo

  • Abstract Writing Guide

    wentorai/research-plugins

    Craft structured research abstracts that maximize clarity and journal acceptance

    298 GitHub starsUsed in 1 repo~1.7k tokens
    Auto-check passed

  • Academic Citation Manager

    wentorai/research-plugins

    Manage academic citations across BibTeX, APA, MLA, and Chicago formats

    298 GitHub starsUsed in 1 repo~2.7k tokens
    Auto-check passed

  • Academic Paper Summarizer

    wentorai/research-plugins

    Summarize academic papers with structured extraction of key elements

    298 GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check passed

  • Academic Study Methods

    wentorai/research-plugins

    Evidence-based study techniques for academic learning and retention

    298 GitHub starsUsed in 1 repo~1.8k tokens
    Auto-check passed

  • Academic Tone Guide

    wentorai/research-plugins

    Adjust writing tone and register for academic audiences and venues

    298 GitHub starsUsed in 1 repo~1.9k tokens
    Auto-check passed

  • Academic Translation Guide

    wentorai/research-plugins

    Academic translation, post-editing, and Chinglish correction guide

    298 GitHub starsUsed in 1 repo~1.6k tokens
    Auto-check passed

Categories

Questions about AI Scientist V2 Guide

What does AI Scientist V2 Guide do?

Automated scientific discovery via agentic tree search by Sakana AI. AI Scientist V2 Guide is an agent skill from wentorai/research-plugins.

When should I use AI Scientist V2 Guide?

AI Scientist V2 Guide fits situations like: research & Science work in your project.

How do I install AI Scientist V2 Guide in Claude Code?

Run `npx skills add wentorai/research-plugins --skill ai-scientist-v2-guide -a claude-code`. Or copy the skill folder (skills/research/automation/ai-scientist-v2-guide in wentorai/research-plugins) into .claude/skills/ai-scientist-v2-guide in your project. Claude Code loads it when a task matches its description.

How do I install AI Scientist V2 Guide in Codex?

Run `npx skills add wentorai/research-plugins --skill ai-scientist-v2-guide -a codex`. Or copy the skill folder (skills/research/automation/ai-scientist-v2-guide in wentorai/research-plugins) into .agents/skills/ai-scientist-v2-guide in your project. Codex loads it when a task matches its description.

Can I use AI Scientist V2 Guide 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 wentorai/research-plugins --skill ai-scientist-v2-guide -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ai-scientist-v2-guide, .gemini/skills/ai-scientist-v2-guide, .github/skills/ai-scientist-v2-guide and .opencode/skills/ai-scientist-v2-guide in your project.

What does AI Scientist V2 Guide need to run?

Going by SKILL.md and its folder, AI Scientist V2 Guide needs the command-line tools its instructions call (conda, python, git, pip, apt-get and brew) and credentials named OPENAI_API_KEY and ANTHROPIC_API_KEY. Our summary lists: Python 3; A credential in OPENAI_API_KEY; A credential in ANTHROPIC_API_KEY.

Does AI Scientist V2 Guide access the network?

SKILL.md names 3 domains. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. As links in the text: arxiv.org and sakana.ai. This is read from the text; nothing was executed.

Is AI Scientist V2 Guide safe to install?

Our automated static check of SKILL.md found notes only (runs commands with sudo), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does AI Scientist V2 Guide use?

AI Scientist V2 Guide is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does AI Scientist V2 Guide use?

About 2.4k tokens (SKILL.md is roughly 9.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to AI Scientist V2 Guide?

Skills that share tags, products or a category with AI Scientist V2 Guide: Perplexity Web Search (davila7/claude-code-templates, 33k stars), Hugging Face Paper Publisher (huggingface/skills, 11k stars), Read GitHub (AgentTeam-TaichuAI/ScienceClaw, 671 stars) and Deepdive (Socialpranker/deepdive, 372 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains AI Scientist V2 Guide?

wentorai (a GitHub user) maintains it in wentorai/research-plugins, which has 298 GitHub stars. The repository holds 405 skills in this directory. The repository was last updated on June 19, 2026.

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