下了一本 300 页的 PDF 想系统读一遍，让 AI 总结出来的东西又不敢全信，哪句是书里写的、哪句是它自己补的分不清。
This is a vibe coding post classified by Jev as Skills & agent setups (a tool drop), kept by the Vibe Coding Radar because it carries real work, not commentary.
下了一本 300 页的 PDF 想系统读一遍，让 AI 总结出来的东西又不敢全信，哪句是书里写的、哪句是它自己补的分不清。 learn-from-materials 是一个学习用的 Agent Skill，把 PDF、EPUB、Word、PPT、网页这些材料变成一个能交互的学习网页，Claude Code、Codex、Copilot 命令行都能装。 它先完整读完材料建一个知识库，页面里每条内容都标出处，PDF 精确到页码，PPT 精确到第几张，EPUB 精确到章节。 GitHub：http://github.com/dmoshehun-prog/learn-from-materials 生成的页面有核心框架、内容导学、术语大全、行动规则几个板块，还带自检题和笔记，学到哪不明白直接在页面上记。 我最看重的是它把「材料里有的」「材料没写的」「模型补充的」分开标，读的时候心里有底，这个设计比多数 AI 读书工具老实。 分「快速了解」和「系统学习」两档深度，生成完还会审计一遍有没有漏读的章节。 默认不联网，笔记和错题只存在自己浏览器里，README 和页面都是中文。 手里堆着几本电子书和论文一直没读的，可以让它先啃一遍。
Posted by GitHubDaily (84.5k followers) 5 days ago · 247 likes · 15.6k views · view the original post on X. Kept by the Vibe Coding Radar as Skills & agent setups.
More vibe coding work like this
- Adds small, composable skills to agents for opening apps, browsing the web, and creating… — @tom_doerr
- imo jev has one massive implication for agents - sifting. — @kushbhuwalka
- I was the biggest skeptic of AI video editing. Until recently. — @businessbarista
- Agent skills are spreading across orgs faster than anyone can secure them 🔒 — @chainguard_dev
- obsidian-second-brain provides persistent memory for Claude Code and Grok Bot using an… — @tom_doerr
- Anthropic wrote a 32-page guide to building Claude skills. — @godofprompt
- Generates market research, competitive battle cards, positioning, financial projections,… — @tom_doerr
- Edits video files locally using AI coding agents like Claude Code, Cursor, and Codex… — @tom_doerr
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 1.8k posts from 1.8k X accounts over the last 14 days, 141 tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 01:18 UTC. Full method.