# read_paper

The read_paper prompt for Claude Code and ChatGPT reviews a paper in light of a research idea. It checks the abstract against the full text and rates the work by paper type.

- prompt · `type=prompt` · Claude Code, ChatGPT · ★ 159 repo stars
- Author: saideao
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/saideao/research-idea-review/tree/HEAD/src/idea_review/prompts/en/read_paper.md
- Updated: 2026-11-02
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/prompts/read-paper

## What it does

The prompt guides a paper review tied to a research idea. It has the model read the methods and experiments before checking the abstract, then compare each abstract claim with evidence in the paper. It separates overclaims or contradictions from limits left out of the abstract, and asks for page references such as `[p.6]` when citing the text.

The model identifies the paper type before applying its rating criteria. Empirical work is judged by the support for its conclusions and the quality of its experiments; surveys by coverage and synthesis, while theory is assessed through its assumptions and derivations. Author-stated limitations stay separate from observations made during review. The notes must use the required JSON format, and uncertainty should be stated rather than filled with invented details.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/commands/read_paper.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/saideao/research-idea-review/tree/HEAD/src/idea_review/prompts/en/read_paper.md

## When to use it
- check abstract claims against the paper's evidence
- distinguish overclaims from omitted scope limits
- rate a paper using criteria for its type
- separate author-stated limitations from reviewer observations

## Example prompts
- Review this paper against my research idea: [idea and full text].
- /read_paper: assess the paper by its type and return the notes as JSON.
- Check whether the abstract's conclusions match the full text, with page references.

## Similar
- [read-arxiv-paper](https://affpapa.org/en/nevibecode/skills/read-arxiv-paper.md) — skill · 2900 installs
- [read-only-auditor](https://affpapa.org/en/nevibecode/agents/read-only-auditor.md) — subagent · 434 installs
- [academic-paper-review](https://affpapa.org/en/nevibecode/skills/academic-paper-review.md) — skill · 2800 installs
- [gws-sheets-read](https://affpapa.org/en/nevibecode/skills/gws-sheets-read.md) — skill · 52800 installs
- [gws-gmail-read](https://affpapa.org/en/nevibecode/skills/gws-gmail-read.md) — skill · 42800 installs
- [read](https://affpapa.org/en/nevibecode/skills/read.md) — skill · 14600 installs

From the same set: [saideao/research-idea-review](https://affpapa.org/en/nevibecode/by/saideao/research-idea-review.md) — 8 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
