AI Research Engineering Skills Library
The most comprehensive open-source library of AI research engineering skills for AI agents.
Quick Start ⚡
Get up and running in under 2 minutes
1
2
Download and Copy a Skill
Open any skill page and click Download SKILL.md, then place it in your local skills directory:
# Example for Claude Code
mkdir -p ~/.claude/skills/claude-writer
# Move downloaded SKILL.md here:
~/.claude/skills/claude-writer/SKILL.md
3
Use the Skill
Invoke the skill via slash command or natural language:
/claude-writer Draft a social science paper outline on AI governance.
AI Skills 🛠️
Task instructions you can execute directly in agents
Using Claude Code with Stata
Aniket Panjwani introduces how to use Claude Code with Stata for economic research.
STATA Accounting Research
A Claude Code skill providing STATA syntax patterns from 126 peer-reviewed JAR replication files (2017-2025).
Open Science Skills
Reproducible research workflows and open-science best practices for social science.
How do LLMs actually work? LLMs power AI applications like ChatGPT, Grok, and Claude to generate human-like text and assist with complex tasks. Here’s a simple to understand breakdown of how they wo
How do LLMs actually work? LLMs power AI applications like ChatGPT, Grok, and Claude to generate human-like text and assist with complex tasks. Here’s a simple to understand brea
I wrote an academic paper in 4 days using AI. Claude Code wrote the first draft overnight. I iterated with multiple AI agents as reviewers. AI made me faster, not smarter. The paper: "Investing in Ar
I wrote an academic paper in 4 days using AI. Claude Code wrote the first draft overnight. I iterated with multiple AI agents as reviewers. AI made me faster, not smarter. The pap
Karpathy 上周发了个项目，两天 860 万浏览——autoresearch。 原版是 ML 专用：630 行代码，一个 GPU，一晚上自动跑 100 个实验，失败自动回滚，成功自动提交。 有人把这套思路移植到了 Claude Code 里，做成了一个 Skill：uditgoenka/autoresearch。 核心逻辑极其简单： 设定一个可量化的目标 → AI 自己循环改→验证→
Karpathy 上周发了个项目，两天 860 万浏览——autoresearch。 原版是 ML 专用：630 行代码，一个 GPU，一晚上自动跑 100 个实验，失败自动回滚，成功自动提交。 有人把这套思路移植到了 Claude Code 里，做成了一个 Skill：uditgoenka/autoresearch。 核心逻辑极其简单： 设定一个可
AI-Research-SKILLs
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent...
分享一个科研论文全自动撰写Skill Academic Research Skills for Claude Code: research → write → review → revise → finalize。https://t.co/jCw1nEtBIb
分享一个科研论文全自动撰写Skill Academic Research Skills for Claude Code: research → write → review → revise → finalize。https://t.co/jCw1nEtBIb
Claude Scientific Writer
End-to-end academic paper writing solution for social science research.
Papers 📄
Evidence base for AI-enabled social science
Can Large Language Models Transform Computational Social Science?
Evaluates zero-shot LLM performance across 25 CSS benchmarks, proposing a roadmap for integrating LLMs into the computational social science pipeline.
Large Language Models as Social Science Assistants
A comprehensive review of how LLMs are transforming social science research methods.
Synthetic Replacements for Human Survey Data? The Perils of Large Language Models
Critically examines the reliability of LLM-generated survey data as substitutes for real human respondents, identifying systematic biases and failure modes.
Can Generative AI Improve Social Science?
Explores how generative AI can enhance survey research, online experiments, automated content analyses, and agent-based models — while warning of bias, ethics, and replication challenges.
AI and the Transformation of Social Science Research
A high-level perspective on how AI is reshaping the design, execution, and interpretation of social science research at scale.
Out of One, Many: Using Language Models to Simulate Human Samples
Demonstrates that LLMs can generate synthetic survey responses that closely match real human opinion distributions, opening doors for rapid prototyping of social science studies.
Tools & Resources 📦
Research platforms, datasets, and workflow assets
scattertext
Beautiful visualizations of how language differs among document types.
hate-speech-and-offensive-language
Repository for the paper "Automated Hate Speech Detection and the Problem of Offensive Language", ICWSM 2017
shifterator
Interpretable data visualizations for understanding how texts differ at the word level
causal-curve
A python package with tools to perform causal inference using observational data when the treatment of interest is continuous.
protest-detection-violence-estimation
Implementation of the model used in the paper Protest Activity Detection and Perceived Violence Estimation from Social Media Images (ACM Multimedia 2017)
AgentReview
Official Implementation for EMNLP 2024 (main) "AgentReview: Exploring Academic Peer Review with LLM Agent."
SHARE
SHARE is building a free, open, data set about research and scholarly activities across their life cycle.
HypotheSAEs
HypotheSAEs: hypothesizing interpretable relationships in text datasets using sparse autoencoders. https://arxiv.org/abs/2502.04382
comp_thinking_social_science
Computational Thinking for Social Scientists book project
lecture-python-intro
An Undergraduate Lecture Series for the Foundations of Computational Economics
llm_for_css
Guide on how to use LLMs for computational social science research
harmony
The Harmony Python library: a research tool for psychologists to harmonise data and questionnaire items. Open source.
research-public
This repository contains the code and data related to different research initiatives carried out at CARTO by the Data Science team
maia-individual
Modeling individual style in chess with Maia Chess.
CSS-Events
Summer/ winter schools, workshops and conferences in computational social science 🫂
STREAM
ACL Python package engineered for seamless topic modeling, topic evaluation, and topic visualization. Ideal for text analysis, natural language processing (NLP), and research in...
ECON_5314G_Big_Data_Economics
This intermediate applied econometrics course covers the theoretical, computational, and statistical underpinnings of the big data analysis. (first taught at Virginia Tech in 2018)
ECON526
Course materials for ECON526 MA Quantitative Economics; computational econ and data science with a focus on causal inference
InkVisitor
An open-source, browser-based front-end application for the collection of complex structured data from textual resources in history and the social sciences into a RethinkDB data...
Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools
Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools
Elicit
AI research assistant that automates literature reviews, extracts data from papers, and supports systematic reviews across 138M+ papers.
ICPSR Data Archive
The world's largest archive of social science data, hosting 16,000+ studies with documentation, metadata, and analysis tools.
ResearchRabbit
AI-powered literature discovery tool that learns your interests and recommends related papers through interactive citation networks.
Semantic Scholar
Free AI-powered research tool by Allen AI that surfaces key papers, extracts entities, and provides citation context across 200M+ papers.
Collections Architecture 🧭
A clean structure for AI + social science knowledge management.
Skills
Executable methods arranged by research workflow stage.
Papers
Methods, applications, ethics, and review papers for evidence-based decisions.
Tools & Resources
Research platforms, datasets, and workflow assets with direct links.
WeChat QR