# 论文精读

论文精读 is a Claude Code prompt for reading English academic papers paragraph by paragraph, preserving the original text and providing a scholarly Chinese translation and analytical commentary.

- prompt · `type=prompt` · Claude Code, ChatGPT · ★ 475 repo stars
- Author: cnfjlhj
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/cnfjlhj/ai-collab-playbook/tree/HEAD/prompts/论文精读.md
- Updated: 2026-10-13
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/prompts/item-036ec3b0

## What it does

The prompt structures academic reading into a synchronized, step-by-step review process. It works through the source material strictly one paragraph at a time, halting until the user sends an explicit command to proceed. Long passages are divided into smaller reasoning units without altering, compressing, or omitting original words.

Every segmented unit follows a three-part structure. First comes the verbatim English excerpt with formulas and tables intact. Next is a scholarly translation into Chinese. The final section delivers commentary on underlying hypotheses, methodology, structural flow, and potential flaws in the argument.

External browsing is turned off, so the assistant works strictly with text pasted directly into the session.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/commands/item-036ec3b0.md`

### ChatGPT

**How to use**
- Paste the text at the start of a chat or into project instructions

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/cnfjlhj/ai-collab-playbook/tree/HEAD/prompts/论文精读.md

## When to use it
- Read difficult English academic papers paragraph by paragraph
- Inspect formulas, tables, and pseudocode without losing original notation
- Spot implicit assumptions and methodology flaws in study claims
- Generate a structural roadmap and key terminology list before reading

## Example prompts
- Begin reviewing this paper and provide an initial structural overview
- Here is the first paragraph from the Methodology section, analyze it
- Continue to the next paragraph

## Similar
- [academic-search](https://affpapa.org/en/nevibecode/skills/academic-search.md) — skill · 6300 installs
- [analyzing-research-papers](https://affpapa.org/en/nevibecode/skills/analyzing-research-papers.md) — skill · 564 installs
- [semanticscholar-skill](https://affpapa.org/en/nevibecode/skills/semanticscholar-skill.md) — skill · 3500 installs
- [ArXiv Scout](https://affpapa.org/en/nevibecode/mcp/arxiv-scout.md) — MCP server · 3426 installs
- [paper-reading-research-question](https://affpapa.org/en/nevibecode/skills/paper-reading-research-question.md) — skill · ★ 240 repo stars
- [nature-reader](https://affpapa.org/en/nevibecode/skills/nature-reader.md) — skill · 16600 installs

From the same set: [cnfjlhj/ai-collab-playbook](https://affpapa.org/en/nevibecode/by/cnfjlhj/ai-collab-playbook.md) — 18 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
