A blueprint-driven AutoResearch runtime for orchestrating AI research workflows from idea generation and experiments to paper writing and peer review.

A ready-to-fork Claude Code template for academics using LaTeX/Beamer + R. Multi-agent review, quality gates, adversarial QA, and replication protocols.

Scholar All-In-One: A research infrastructure for AI agents

Claude Code for academics — skills, agents, and setup guides

Practical AI collaboration playbook for research, writing, reading, and coding: article, prompts, agent rules, and reusable skills.

Research-paper workflow tool for literature triage and structured reading

Agent-native investment research workspace for evidence-tracked, refreshable investment theses across equities, earnings, macro, and portfolio review.

Universal SKILL.md catalog for research workflows: literature review, research design, project memory, manuscript writing, and cross-agent delegation for Claude Code, Codex, Gemini, Cursor, OpenClaw, and generic AI clients.

A curated list of research-oriented skills usable in OpenAI Codex, covering writing, literature review, evaluation, and research workflows.

📚 PaperFlow: Dynamic personalized scientific-paper recommendation, reading, and reporting

Shareable Claude Code + Codex infrastructure for PhD researchers — skills, agents, hooks, and rules for academic workflows

Research feedback grounded in the papers that define your field

Karpathy-style personal wiki for LLMs - markdown + frontmatter, no vector DB, no RAG. Built for Claude Code, works with any file-editing AI agent.

Semi-automated research assistant and local knowledge base for paper analysis, ideation, coding, experiments, writing, and publication workflows.

Turn vague research directions into falsifiable, evidence-grounded Research Idea Briefs with a six-stage Codex workflow.

End-to-end AI workflow for economic & finance research: 43 MCP data sources, 47 econometric methods (DID/IV/RD/PSM/GMM), 30 journal templates (JF/JFE/RFS/经济研究/金融研究/管理世界), HITL gates, 3-LLM adversarial review. MIT. Zenodo: 10.5281/zenodo.21262689

PaperSprint: Scrum-inspired paper agent skill for review, revision, and R&R

Markdown-first work-memory protocol for existing agents, with maintained knowledge, candidate notes, evals, and an example KB.

Reading copilot for Zotero powered by the DeepSeek API and scoped to your local papers, PDFs, and collections.

Local-first, evidence-controlled academic writing workflows for AI agents, with bounded revision, clean-room review, and release governance.