No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by caofan85-lab · Codex Skill · ★ 62
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is research-paper-daily-push safe to install? View the security audit →
research-paper-daily-push：每日科研文献雷达 这是一个开源的 Codex Skill。用户可以把3–10篇代表性论文放入本地目录，由 Skill 提取论文内容、生成带证据映射的研究画像草案，并在用户确认后据此检索近期论文。候选论文经过初筛、证据复核、评分、去重和中文总结后，只推荐真正值得阅读的少量论文。项目也支持专业术语双重解释、微信推送、本地推送历史和研究记忆。 公开模板不包含任何预设研究主题、访问凭据、推送历史或学习记录。在完成研究配置前，程序会停止检索，避免返回无关论文。 第一次接触 Python、Git 或 Codex Skill？请直接阅读小白安装与使用指南。 主要功能 优先检索近24小时论文；高分候选不足时自动扩展到最近7天。 从 PDF、DOCX、TXT 或 Markdown 代表性论文中生成可追溯的研究画像草案。 激活画像前必须由用户确认；已有正式画像不会因新增论文而静默改变。 使用 Europe PMC、Crossref、Semantic Scholar、OpenAlex 和 bioRxiv 等稳定学术接口。 按研究相关性、创新性、论文质量、方法学价值和研究启发进行透明初筛。 要求 Codex 阅读可用证据后重新评分，避免仅凭关键词或题名推荐。 默认只推荐评分不低于70分的5–10篇论文，允许少于5篇或零推荐。 按 DOI 优先、规范化题名兜底的方式去重，已经推送的论文不会作为新论文重复发送。 生成中文每日文献雷达、前三名推荐、研究灵感和专业术语双重解释。 支持 WxPusher、Server酱和企业微信机器人，并在未配置推送时继续生成本地报告。 运行环境 Python 3.10 或更高版本。 PDF 文本提取使用 ；DOCX、TXT 和 Markdown 提取及其余核心流程使用 Python 标准库。 联网检索和消息推送需要运行环境能够访问相应学术接口与通知服务。 OpenAlex API 支持匿名基础检索；需要更高调用额度时，可申请 API Key 并存入 环境变量，也可用 提供联系邮箱。OpenAlex 检索使用游标翻页，每条查询最多读取600条近期记录。 安装 下面是快速安装方式。需要逐步截图式文字说明、安装检查、首次配置和常见问题时，请阅读小白安装与使用指南。 可以克隆仓库： powershell git clone https://github.com/caofan85-lab/research-paper-daily-push.git cd research-pap
| Stars | 62 |
| Forks | 0 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 54.8546981242714/100 |
| Last Updated | 2026-09-04 |
| Created | 2026-09-01 |
| Platforms | codex, python |
| Est. Tokens | ~9k |
Looking for a research-paper-daily-push alternative? If you're comparing research-paper-daily-push with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
De-Anthropocentric Research Engine — AI-powered academic research automation with deep literature survey, gap
A curated list of research-oriented skills usable in OpenAI Codex, covering writing, literature review, evalua
AI驱动的系统性学术文献回顾工具 | AI-Powered Literature Survey Tool with 8-Phase Workflow & Agent Swarm Architecture
Skills and tools for scientific research with LLM agents. 给 Agent（如 Claude Code、Openclaw）提供的科研 skills
AI-operable research workspace for Zotero, Obsidian, and NotebookLM. Use any two, or all three, through CLI, M
Turn Google Search, Papers, and Codebases into an Automatic Local Knowledge Graph for AI Agents.
Explore other popular codex skill tools:
research-paper-daily-push is 可配置的 Codex Skill：每日检索、证据复核、评分、中文总结、微信推送、去重与研究记忆。. It is categorized as a Codex Skill with 62 GitHub stars.
research-paper-daily-push is primarily written in Python. It covers topics such as academic-research, codex-skill, literature-review.
You can find installation instructions and usage details in the research-paper-daily-push GitHub repository at github.com/caofan85-lab/research-paper-daily-push. The project has 62 stars and 0 forks, indicating an active community.
research-paper-daily-push is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to research-paper-daily-push on Agent Skills Hub include De-Anthropocentric-Research-Engine, Codex-Academic-Skills, AI-Powered-Literature-Review-Skills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: