Best Research Skills

lllllllama/RigorPilot-Skills

RigorPilot Skills provides a research-first suite of agent skills designed to keep AI-assisted deep learning experiments grounded in reproducibility, evidence, and auditable changes.

qinky1234-sys/chinese-academic-paper-skill

An academic assistant specialized in verifiable Chinese literature review workflows, CNKI/Wanfang/VIP data processing, and de-AI Chinese academic writing. It helps researchers build literature matrices, analyze relationships, discover research gaps, and generate fully traceable academic reviews without fabricating citations.

firecrawl/firecrawl

Firecrawl is an API and toolset designed to search, scrape, crawl, and interact with web pages at scale, converting them into clean Markdown or structured JSON for AI applications.

unclecode/crawl4ai

Crawl4AI is an open-source, LLM-friendly web crawler and scraper that converts web content into clean, structured Markdown for RAG and AI pipelines.

Egonex-AI/Understand-Anything

Understand Anything transforms complex codebases and knowledge bases into interactive knowledge graphs, enabling users to explore architecture, search semantic relationships, and query code logic efficiently.

LearnPrompt/ai-news-radar

AI News Radar is an automated intelligence aggregation system designed to filter, cluster, and evaluate AI-related news feeds using custom personas. It supports static site deployment via GitHub Pages and integrates with AI agents to provide concise daily briefings.

atomicstrata/llm-wiki-compiler

A knowledge compiler CLI tool that transforms raw source documents into interlinked, citation-traceable markdown wikis for humans and AI agents.

northword/zotero-format-metadata

Zotero-format-metadata is a Zotero plugin that automatically validates, cleans, and formats academic item metadata and references. It features rich-text title editing, automated rule-based corrections, and one-click metadata updates from external services.

atenreiro/opensquat

openSquat is an OSINT security tool designed to detect brand protection threats such as typosquatting, phishing, and IDN homograph attacks through newly registered domain feeds and similarity detection.

minihellboy/factorminer

FactorMiner is a governed research framework for discovering, evaluating, and combining interpretable alpha factors using typed domain-specific languages and LLM-guided workflows. It enables quantitative researchers to backtest portfolios, generate tearsheets, and manage factor libraries under strict transaction costs.

luongnv89/claude-howto

An interactive tutorial guide and blog post drafting skill for Claude Code that teaches advanced orchestration features and automates content creation from research.

zhnnky329/MathModeling-skills

MathModeling-skills is a rigorous framework for mathematical modeling tasks that strictly separates human modeling judgment from AI mechanical execution.

enjalot/moonshine

Helps users craft interactive, web-based technical explanations inspired by Distill.pub, transforming complex ideas into visual and explorable articles.

DechenZhang/VALG-ML-Theory-Agent

Reviews branch-local global proof diagnostics to evaluate theorem viability and determine if they should be accepted, rewritten, or rejected before step-level proof work.

yux1azhengye/BestSerenitySkillFromAT

An investment research framework that synthesizes supply chain bottleneck analysis based on methodology from legendary investors to identify asymmetric market opportunities.

DeepXiv/deepxiv_sdk

This skill builds a structured markdown baseline table for any research topic by leveraging the DeepXiv SDK to search arXiv papers, screen metadata, inspect structures, and extract experimental datasets and scores.

christopherkenny/skills

An academic editing skill that checks Quarto (.qmd) documents against the APSA Style Manual for Political Science, generating a structured markdown report of suggested edits.

Liunian06/ko-lesson

This skill generates comprehensive, structured, and interactive learning lesson packages from existing materials, providing personalized learning paths and continuous feedback loops.

AlphaGBM/investment-masters

This skill extracts and structures the investment philosophies, risk management styles, and holdings of 15 legendary fund managers to help users build systematic trading strategies.

K-Dense-AI/scientific-agent-skills

This repository provides standardized agent skills focused on scientific packages, databases, and research workflows adhering to the Agent Skills specification.

Rimagination/good-story

An expert scientific writing skill that extracts, calibrates, and structures compelling research narratives from scholarly materials without letting hype outrun the evidence.

Kappaemme-git/codex-first-customer-finder-skill

This skill analyzes a startup URL or product description to find, qualify, and rank evidence-backed potential first customers using public demand and pain signals.

HKUDS/DeepTutor

DeepTutor is an agent-native intelligent learning companion featuring a dual-layer architecture with dynamic single-shot tools and multi-stage learning capabilities.

jordan-gibbs/hyperresearch

Hyperresearch transforms Claude Code into a comprehensive deep research agent executing a rigorous 16-step pipeline with persistent source vaults and adversarial review. It produces verified, fully cited reports ranging from quick briefs to full dissertations.

opendatalab/MinerU-Ecosystem

The MinerU-Ecosystem skill integrates the MinerU open-source document parsing engine to convert complex PDFs, office documents, images, and web pages into clean Markdown or multi-format output. It supports two modes: a token-free flash extraction for quick tasks and a precision extraction mode with OCR, layout analysis, and batch processing.