lecture-to-notes — security grade SAFE, quality 59/100

Security audit verdict: SAFE · quality 59/100

Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by ysyecust · Codex Skill · ★ 228

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is lecture-to-notes safe to install? View the security audit →

About lecture-to-notes

lecture-to-notes 在线预览所有讲义和论文解读 → 两个 AI 驱动的学习工具: lecture-to-notes:将 YouTube / Bilibili 讲座视频转换为专业的中文 LaTeX 课程笔记和 PDF paper-to-html:将学术论文转换为结构化的中文 HTML 解读页面 视频 URL → LaTeX PDF 讲义 | 论文 → 自包含 HTML 解读 特性 多平台支持:YouTube 和 Bilibili(自动识别 URL) 字幕四级回退:CC 字幕 → YouTube 自动字幕(自动去重)→ Whisper 语音转写 → 纯视觉模式 字幕清洗:YouTube auto-subs 自动去重(通常去除 50% 重复行) 密集帧采样:每 15 秒采样 + contact sheet 批量审查,不遗漏关键画面 图文三方验证:每个配图写入前必须通过「帧画面 + 字幕内容 + 描述文字」三方一致性检查,防止图文不匹配 高信息密度写作:结构化章节、教学信号盒(核心概念/背景知识/常见误区)、时间溯源脚注 数学公式支持:准确转写 PPT 中的数学公式为 LaTeX display math + 符号解释 完整交付: 源文件 + 配图 + 编译好的 PDF 仓库结构 text . ├── README.md ├── LICENSE ├── scripts/ │ ├── cleansubs.py # YouTube 自动字幕去重 │ ├── correctsrt.py # Whisper SRT 词典级修正(数据驱动,快) │ ├── llmcorrectsrt.py # Whisper SRT 段级修正(LLM + 多模态,慢但更准) │ ├── verifyfigures.py # 图文三方验证(时间戳 × 字幕 × 画面) │ ├── preparecover.sh # 封面格式转换(webp/png → jpg) │ ├── smartcrop.py # 课件区域检测(实验性,实际流程中通常直接用全帧) │ └── whisperprompts/ # Whisper --initialprompt 术语表 │ ├── glossarynjuos.json # 词典修正的 wrong→right 对 │ └── njuos.txt # 引导 Whisper 正确转写专业术语 ├── docs/ │ ├── index.html # GitHub Pages 首页(讲义 + 论文卡片网格) │ ├── pdfs/ # 已发布的讲义 PDF │ └── papers/ # 已发布的论文解读 HTML └── skills/ └── lecture-to-notes/ ├── SKILL.md # Skill 主定义(适

Quick Facts

Stars228
Forks23
LanguagePython
CategoryCodex Skill
Quality Score58.6329262696229/100
Last Updated2026-09-16
Created2026-03-24
Platformsclaude-code, codex, python
Est. Tokens~14k

lecture-to-notes alternative? Top 5 similar tools

Looking for a lecture-to-notes alternative? If you're comparing lecture-to-notes with other codex skill tools, these 5 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • Skills-Manager by jiweiyeah · ⭐ 991

    Free, open-source desktop manager for AI Agent Skills. Write a skill once, sync it to 32 AI coding tools (Clau

  • ai-maestro by 23blocks-OS · ⭐ 789

    AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agen

  • upskill by huggingface · ⭐ 747

    Generate and evaluate agent skills for code agents like Claude Code, Open Code, OpenAI Codex

  • skills by wlzh · ⭐ 607

    开源了Codex Skills等集合,大部分是自己实际需要搞得,需要的自取。欢迎star

  • solana-dev-skill by solana-foundation · ⭐ 559

    Skills for agentic development on Solana

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is lecture-to-notes?

lecture-to-notes is Turn YouTube/Bilibili lectures into smart-cropped LaTeX/PDF notes. Claude Code & Codex skill.. It is categorized as a Codex Skill with 228 GitHub stars.

What programming language is lecture-to-notes written in?

lecture-to-notes is primarily written in Python.

How do I install or use lecture-to-notes?

You can find installation instructions and usage details in the lecture-to-notes GitHub repository at github.com/ysyecust/lecture-to-notes. The project has 228 stars and 23 forks, indicating an active community.

What are the best alternatives to lecture-to-notes?

The top alternatives to lecture-to-notes on Agent Skills Hub include Skills-Manager, ai-maestro, upskill. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Codex Skill tools