学术写作

01 tizzy916/humanities-writing-companion 端到端人文学科写作助手——一个 Agent Skill（开放的 SKILL.md 格式）。提供 11 种模式，从苏格拉底式研究问题打磨到 AI 使用披露。中英双语（EN/中文），具备学科感知能力（文学/历史/哲学/艺术/宗教/语言学+跨学科）。四层批评、可校准的魔鬼辩护人、声音保留。End-to-end humanities writing assistant — an Agent Skill (open SKILL.md format). 11 modes from Socratic research-question sharpening through AI-use disclosure. Bilingual (EN/中文), discipline-aware (literature/history/philosophy/art/religion/linguistics + cross-disciplinary). Four-layer critique, calibratable devils advocate, voice preservation. 论文写作 大纲与论文起草 选题与研究问题 Skill写作 Agent 智能体 Python 415 ★ 02 Rimagination/good-question 一个用于打磨研究问题的可移植 agent Skill。A portable agent skill for sharpening research questions. 文献发现 选题与研究问题 Skill Agent 智能体 PowerShell 301 ★ 03 socai-io/jev-social Jev × socai 将社交研究问题转化为来自 Instagram、TikTok 与 LinkedIn 的真实证据，并附带来源链接的报告。Jev × socai turns a social research question into real Instagram, TikTok, and LinkedIn evidence plus a source-linked report. 文献发现 选题与研究问题 Agent 智能体 JavaScript +21/周 88 ★ 04 Rogo-Technologies/big-finance-benchmark 针对工作流落地型金融研究问题的 Big Finance 基准测试的参考实现 harness。Reference harness for the Big Finance benchmark of workflow-grounded financial-research questions 文献发现 选题与研究问题 评测基准 Python 20 ★ 05 rohanprichard/claude-overnight 全天排队研究问题，醒来即可获得答案，在睡眠时利用闲置的 Claude Code 配额工作。Queue research questions all day. Wake up to answers. Puts your idle Claude Code quota to work while you sleep. 文献发现 选题与研究问题 Agent 智能体 Python 13 ★ 06 GiaSip/giasip-skills 将研究问题转化为带源链接和开放问题的报告：面向 Codex 和 Claude Code 的 Research 工具，以及 Claude Code 的多模型调度工具。Turn research questions into reports with source links and open questions: Research for Codex and Claude Code, plus multi-model dispatch tooling for Claude Code. 文献发现 选题与研究问题 Agent 智能体 Shell 12 ★ 07 ISARICResearch/VERTEX ISARIC VERTEX 是一个基于 Web 的应用，用于呈现基于暴发期间需快速回答的相关研究问题的图表，作为通过 ISARIC ARC 与 ISARIC BRIDGE 等配套工具所采集数据的分析工具。ISARIC VERTEX is a web-based application designed to present graphs and tables based on relevant research questions that need to be quickly answered during an outbreak. It serves as an analysis tool for data captured through our complementary tools: ISARIC ARC and ISARIC BRIDGE. 文献发现 选题与研究问题 工程化 Python 8 ★ 08 w3c/rqtf Research Questions Task Force 交付物Research Questions Task Force deliverables 文献发现 选题与研究问题 工程化 HTML 3 ★ 09 SudeshDahale/AI-Research-Copilot 自主 AI 平台，提供端到端的学术研究辅助——从论文发现到生成结构化文献综述，以及识别研究空白。An autonomous AI platform that performs end-to-end academic research assistance — from discovering papers to generating structured literature reviews and identifying research gaps. 文献发现 选题与研究问题 系统综述 Agent 智能体 TypeScript 3 ★ 10 NIAID-BRC-Codeathons/federated-data-ecosystem-assistant 一个研究问题，一套跨 BV-BRC、BRC Analytics、PDN、NIAID Data Ecosystem、NCBI 资源及其他参与仓库的协同计划。One research question, one coordinated plan spanning BV-BRC, BRC Analytics, PDN, the NIAID Data Ecosystem, NCBI resources, and other participating repositories. 文献发现 选题与研究问题 Agent 智能体 Python +7/周 2 ★ 11 Luckyenough64/black-box-revelations 实验性 Python 库：基于 dataframe 导航至研究问题，并内置统计与因果安全闸门Experimental Python library for dataframe-to-research-question navigation with statistical and causal safety gates. 文献发现 选题与研究问题 安全与风险 Python 2 ★ 12 yishaik/web-terrarium 输入一个研究问题，获取阅读指南与持续更新的源信息地图 — 基于 Cloudflare Durable Objects 构建的公共研究花园，保留成长历史Seed a research question, get a reading guide and a living source map — public research gardens with saved growth history, on Cloudflare Durable Objects. 文献发现 选题与研究问题 Agent 智能体 TypeScript +2/周 1 ★ 13 SUSHANTHgit/veriRAG 一套面向 LLM-based RTL 验证开放研究问题的架构：分块多表征记忆（BM25 / HNSW / 结构化事实）、基于本地 7B LLM 的多 Agent 编排器，以及具备漂移保护的反馈驱动优化。An architecture answering open research questions on LLM-based RTL verification: chunked multi-representation memory (BM25 / HNSW / structured facts), a multi-agent orchestrator over a local 7B LLM, and feedback-driven refinement with drift protection. 文献发现 选题与研究问题 Agent 智能体 Python 1 ★ 14 shreyaheelesh29/ScholarMind AI 驱动的学术研究助手，使用 RAG 与 LLM 进行论文分析、生成文献综述、识别研究空白、产出深度解读，并生成带来源引用的演示文稿。AI-powered academic research assistant that uses RAG and LLMs to analyze research papers, generate literature reviews, identify research gaps, create deep explanations, and generate presentations with source citations. 文献发现 选题与研究问题 系统综述研究设计与方法 RAG 检索增强 JavaScript 1 ★ 15 Jiawang1209/SciPlot-Agent 一个只读 MCP 服务器，根据研究问题或参考图像，为 Claude 和 Codex 推荐真实可复现的 R/Python 科学图表案例。Read-only MCP server that recommends real, reproducible R/Python scientific figure cases to Claude and Codex — by research question or reference image. 文献发现 选题与研究问题 可视化MCP Agent 智能体 Python 1 ★ 16 JayPat2003/AI-Research-Agent 给系统一个复杂的研究问题，它可自主搜索你的知识库和 Web，检索相关来源，分析与交叉验证证据，并生成结构化、带引用的研究报告。Give the system a complex research question, and it autonomously searches your knowledge base and the web, retrieves relevant sources, analyzes and cross-checks evidence, and produces a structured, citation-backed research report. 文献发现 选题与研究问题 引用 Agent 智能体 Python 1 ★ 17 bita06/Paperclaw PaperClaw 是面向公共管理学者的 AI 研究助手，可帮助用户检索相关文献、定位文本关键概念、获取全文证据、回答研究问题并提出潜在想法，覆盖从检索到洞察的全流程。PaperClaw is an AI research assistant for public administration scholars. It helps users find relevant literature, locate key concepts in texts, retrieve full-text evidence, answer research questions, and suggest potential ideas, improving efficiency from search to insight. 文献发现 选题与研究问题 RAG 检索增强 Python 1 ★ 18 apollosbangalu/Research_Group_Work Researcher's Decision Pattern Matrix 仓库，一套用于辅助研究人员（硕士与博士）在选题、研究问题类型、研究设计与方法论方面做决策的文件集合。This is a repository an Researcher's Decision Pattern Matrix, a collection of files to assit researchers (MSc and PhD) in making decisions concerning topic selection, research question type, research design and methodology. 研究执行 研究设计与方法 选题与研究问题 工程化 HTML 1 ★ 19 Zyphronix-space/ai-research-agent 多 Agent AI 研究团队——Planner、并发 Workers、Reviewer 与 Synthesizer 实时协作，基于引用来源回答研究问题。FastAPI + React，Gemini 结构化输出。Multi-agent AI research crew — Planner, concurrent Workers, Reviewer, and Synthesizer collaborate live to answer research questions with cited sources. FastAPI + React, Gemini structured output. 文献发现 选题与研究问题 Agent 智能体 Python 0 ★ 20 Yujin-Kim-Postech/llm_project 研究问题系统Research Question system 文献发现 选题与研究问题 Agent 智能体 Python 0 ★ 21 yifeifelix/cite-and-commit 可移植 LLM Skill，像答题引擎一样回答研究问题：先给结论、每条事实附来源，并给出真实推荐。A portable LLM skill that answers research questions like an answer engine: verdict first, a source on every fact, and a real recommendation. 文献发现 选题与研究问题 Skill RAG 检索增强 0 ★ 22 Yarra319/reproducible--research--preregistration 可复现的研究问题与预注册Reproducible research question,preregistration 研究执行 实验与代码复现 选题与研究问题 工程化 0 ★ 23 whomimohshukla/langgraph-research-assistant 一个 TypeScript LangGraph agent，通过搜索、摘要和 human approval 回答 research questions，使用 LangSmith 完整 trace 并可直接用于评估。A TypeScript LangGraph agent that answers research questions with search, summarization, and human approval – fully traced with LangSmith and ready for evaluation 文献发现 选题与研究问题 Agent 智能体 TypeScript 0 ★ 24 varshaanbu3107-afk/agentic-ai-research-decision-system Agentic 多 Agent AI 系统，通过 RAG 检索、来源质量评分，以及 planning → research → verification → decision 流水线，将研究问题转化为有证据支持、可验证的决策。Agentic multi-agent AI system that turns research questions into evidence-backed, verifiable decisions using RAG retrieval, source-quality scoring, and a planning → research → verification → decision pipeline. 文献发现 选题与研究问题 Agent 智能体 Python 0 ★ 25 uvKogan/Memristor-based-dram 课程 "046265 – Circuits and Architectures with Memristors" 的期末项目，研究问题为"基于忆阻器的存储器能否取代 DRAM 作为主存储器？"Final project in the course "046265 – Circuits and Architectures with Memristors". The research question is "Can Memristor-based Memory Replace DRAM as Main Memory?" 文献发现 选题与研究问题 工程化 HTML 0 ★ 26 UnsoundMouse/flyrankaiw01_research_question 文献发现 选题与研究问题 Agent 智能体 Jupyter Notebook 0 ★ 27 therealtimex/qspec Question Spec：研究问题的选择契约，配套 qspec 工具和 RealTimeX 插件。与 Paperforge 配对使用。Question Spec: a selection contract for research questions, with the qspec tool and RealTimeX plugin. Pairs with Paperforge. 文献发现 选题与研究问题 工程化 JavaScript 0 ★ 28 synnahh/cs-research 研究问题、论文、研究发现和实验。Research questions, papers, findings, and experiments 文献发现 选题与研究问题 工程化 0 ★ 29 Synectic-Research/research-scan 找出对某个研究问题、主题或项目影响最大的 5–10 篇近期论文。Find the 5–10 recent papers with the highest impact on a research question, topic or project. 文献发现 选题与研究问题 RAG 检索增强 Python 0 ★ 30 Sp2736/data-mind 由 LLM 编排的自主 EDA 与数据预处理框架 — 自动生成面向特定数据集的研究问题，编写并自我修正分析代码，自动选择可视化。基于 Claude/GPT 构建。LLM-orchestrated framework for autonomous EDA and data pre-processing — generates dataset-specific research questions, writes and self-corrects analysis code, and auto-selects visualizations. Built with Claude/GPT. 文献发现 选题与研究问题 Agent 智能体 TypeScript 0 ★ 31 SlideRuleEarth/sliderule-claude-managed-agent 一个 Claude Managed Agent，可回答 SlideRule 研究问题并返回独立的 HTML 仪表板；每个用户需在其自己的 Anthropic 账号中部署专属 AgentA Claude Managed Agent that answers SlideRule research questions and returns a self-contained HTML dashboard. Each user provisions their own agent in their own Anthropic account. 文献发现 选题与研究问题 Agent 智能体 Python 0 ★ 32 simonkd-spec/SepsisPrediction 研究问题：在脓毒症发生前检测患者 — 使用分类算法实现脓毒症的早期检测Research Question: Detect Sepsis in Patients Before it Emerges - Early Detection of Sepsis using Classification algorithms 文献发现 选题与研究问题 工程化 Jupyter Notebook 0 ★ 33 shravaniwadgaonkar/ai-research-agent 使用工具研究问题并生成答案的 AI AgentAn AI agent that uses tools to research questions and generate answers. 文献发现 选题与研究问题 Agent 智能体 0 ★ 34 shokrydev/master 本仓库最初是我毕设项目的 PyTorch Lightning 模板，后来演进为包含完整项目实现本身。研究问题是地理定位如何影响遥感视觉-语言模型的训练与推理。注：仓库名称与描述可能变化。This repo originally was a PyTorch Lightning template for my thesis project. It has since evolved to contain the full project implementation itself. The research question is how geolocation influences the training and inference of vision-language models for remote sensing. Note: The repository name and description may change 文献发现 选题与研究问题 模板 多模态 Python 0 ★ 35 ScottSavaiano/project-mentor 面向苏格拉底式导师的 Hermes 人设：研究问题开发、文献综合与项目脚手架。属于 Bronx Science 社会科学研究课程的一部分。Hermes profile for Socratic mentorship: research question development, literature synthesis, and project scaffolding. Part of the Bronx Science Social Science Research curriculum. 文献发现 选题与研究问题 Agent 智能体 Python 0 ★ 36 sanjayy0612/iam_literature 面向研究的 Skill 定义精选集合，覆盖文献综述、证据综合与研究空白分析；汇总多个社区驱动的 Skill，便于在 Codex 或 Copilot 工作流中对比、审阅与按需安装A curated collection of research-focused skill definitions for literature review, evidence synthesis, and research-gap analysis. It brings together multiple community-driven skills so they can be compared, reviewed, and selectively installed for use in Codex or Copilot workflows. 证据综述 系统综述 选题与研究问题Meta 分析与证据综合 Skill Agent 智能体 Python 0 ★