Evidence-first deep reading for AI agents

Key features

• Five modesquick key takeaways · deep in-depth reading · map knowledge map · feynman Feynman technique (11-step loop + spaced repetition) · book whole-book reading (see the comparison below)
• Portable Agent Skill for Codex, Claude Code, and other Agent Skills-compatible tools.
• deep modeClaude Code token optimization — claims, evidence, argument flow, concepts, and critical questions.
• Three inputsWeChat article URLs (mp.weixin.qq.com stable links) · files (.txt/.md/.html/.pdf, PDF via a built-in pure-JS extractor with Chinese ToUnicode mapping, page markers, and object-stream/xref-stream support) · pasted text
• Optional exportDisplayed in-session by default