This repository is a Claude Code/Pi skills framework for academic research and writing. It packages markdown skills, agent definitions, and Python tooling that together support the full research pipeline: topic discovery, deep research, paper writing, review, citation verification, and meta-analysis. The dominant character is application/tooling: it has CLI entry points, a Pi wrapper, dozens of lint/check scripts, and a large test suite. It is not a data pipeline, though it includes network-backed citation lookup scripts and research-oriented data-integrity checks.
GPT Academic is a comprehensive Gradio-based web application that provides a unified interface for interacting with 30+ large language models (both commercial APIs and locally-hosted models) with specialized tools for academic research workflows. The system's core architecture revolves around a plugin-based extensible framework where functionality is organized into 'basic functions' (simple text transformations) and 'crazy functions' (complex multi-step plugins for PDF translation, LaTeX processing, code analysis, internet search, etc.). The main entry point (main.py) initializes a Gradio Blocks interface with a modular layout, dynamic plugin loading, and a custom FastAPI server wrapper that adds authentication, file access controls, and WebSocket streaming capabilities. The codebase demonstrates sophisticated multi-threading patterns for concurrent LLM requests, with a bridge abstraction layer (request_llms/bridge_all.py) that normalizes communication across diverse model providers including OpenAI, Azure, Anthropic, Qwen, ChatGLM, Spark, and many others. The plugin system supports both simple function-based plugins and class-based plugins with configurable argument menus, state management via cookies, and hot-reloading. Notable architectural components include a vector database integration for RAG workflows, a multi-agent system built on AutoGen, real-time audio processing with Alibaba ASR, and a Docker-as-a-Service pattern for delegating media processing tasks. The repository contains extensive documentation (MkDocs-based), comprehensive test coverage for plugins, CI/CD pipelines for Docker image builds, and support for multiple deployment modes (pip, conda, Docker, HuggingFace Spaces). The codebase exhibits high craftsmanship in its LLM integration layer, with features like automatic key rotation, model-specific parameter handling, streaming response management, and sophisticated error handling with watchdog timers. The plugin template system and dynamic UI generation demonstrate good software engineering practices for extensibility.
ZotLit is a dual-plugin system (Obsidian plugin + Zotero addon) that bridges Zotero's reference management with Obsidian's note-taking environment. It enables users to create literature notes from Zotero items, insert formatted citations, import annotations, and export documents via Pandoc — all within Obsidian. The system is a monorepo with three main applications: an Obsidian plugin (apps/obsidian) that provides views (annotation sidebar, references panel, citation popover, template data explorer), services (citation indexing, live updates from Zotero, Pandoc integration, note creation/update), and a settings tab; a Zotero addon (apps/zotero) that extends Zotero's menus, database status, and freshness signaling; and a documentation site (apps/docs) built with TanStack Router and Fumadocs on Cloudflare Workers. The architecture is service-oriented on the Obsidian side, with approximately 20 services wired in a service container (build.ts) using AsyncDisposableStack for lifecycle management. Shared packages (@zotlit/db, @zotlit/templates, @zotlit/protocol, @zotlit/obsidian-i18n, @zotlit/item-lookup) provide database queries over Zotero's SQLite via Drizzle ORM, template rendering with Eta/Liquid engines, a versioned HTTP wire protocol between Zotero and Obsidian, i18n Language Pack compilation, and a search index for item lookup. The codebase is well-tested with Vitest, employs modern TypeScript patterns, and maintains a comprehensive typed contract system for template data. Key workflows include: bidirectional citation linking (pandoc-style and wikilink), live preview of citations in reading view, annotation import from PDF/EPUB/snapshots with turndown HTML-to-Markdown conversion, Pandoc export with a bundled Lua filter and pinned WASM engine, batch note creation from collection selections, and a template workbench CLI for debugging and authoring templates. The system relies on Zotero's local SQLite database as the authoritative source, with a freshness detection mechanism (WAL checkpoint polling) to trigger updates in Obsidian.
The academic-skills repository is a collection of prompt engineering assets designed to assist with academic research workflows when used with large language models like ChatGPT. It provides eight distinct skills, each encapsulated in a self-contained directory containing a skill description (SKILL.md), platform-specific metadata (agents/openai.yaml), and optional reference templates or scripts. The skills cover tasks such as reading and noting papers, writing literature surveys, monitoring arXiv for new publications, analyzing reviewer comments, summarizing experiment logs, extracting benchmark information, identifying research gaps, and generating weekly lab updates. The repository emphasizes reliability and reproducibility by constraining LLM outputs to avoid hallucination, providing clear input processing rules, and offering structured templates for consistent results. One skill (paper-feishu-digest) includes a deterministic Python script for fetching and filtering arXiv papers, demonstrating a hybrid approach that combines LLM assistance with traditional data processing. Additional tools for validating the repository structure and packaging skills for distribution are included, all written using only the Python standard library to minimize dependencies. The codebase exhibits strong modularity, with each skill following a uniform structure that facilitates maintenance and extension. The arxiv_digest.py script stands out as a reusable component for arXiv data processing, featuring robust error handling, keyword-based ranking, and conservative inference of paper contributions and limitations from abstracts. Overall, the repository represents a well-crafted toolkit for enhancing academic productivity through LLM augmentation, balancing prompt engineering with selective use of deterministic scripts where appropriate.
This repository is a comprehensive plugin and skill set for Claude Code (and compatible CLI assistants like Codex CLI and OpenCode), designed to transform the AI into a semi-automated research assistant for academic and software development workflows. It is not a standalone application but a configuration package that installs skills, commands, agents, hooks, and rules into the user's Claude environment. The architecture follows a skill-based pattern: each skill is a directory with a SKILL.md entry point, references, examples, and optional scripts, all consumed by the AI at runtime. The repository covers the full research lifecycle—ideation, literature review (via Zotero MCP and arXiv APIs), experiment analysis, ML paper writing with conference-specific LaTeX templates (NeurIPS, ICLR, ICML, ACL, AAAI), reviewer response drafting, publication chart creation, and post-acceptance promotion. It also integrates deeply with Obsidian for project knowledge management and includes a meta-toolchain for developing and QA-ing skills themselves. While primarily an application configuration, it contains substantial research-oriented content (Kaggle competition analyses, citation verification workflows, writing pattern references), making it a hybrid tool that bridges software engineering and data science research. The codebase is actively maintained, well-documented, and demonstrates strong craftsmanship in its script utilities and hook infrastructure.