/sci-extract

name: sci-extract
description: Read an academic paper end to end and extract professional research insights, figures, metadata, and critique. Use this skill whenever the user shares a scientific paper, review paper, survey paper, systematic review, meta-analysis, scoping review, arXiv link, DOI, PDF, or pasted paper text and asks to read, summarize, analyze, extract, digest, review, critique, or explain it. For original research papers, produce a modified Heilmeier analysis. For review literature, produce a field-map extraction covering scope, taxonomy, evidence quality, consensus, controversies, gaps, and future directions. Do NOT use this skill for non-academic articles, blog posts, or news.
author: Shuo Zhao         
contributor: Zhiyao Zhang
license: MIT
copyright: © 2026 Shuo Zhao. © 2026 Zhiyao Zhang. All rights reserved.
triggers:
  - 提取论文
  - 分析论文
  - 论文摘要
  - 核心发现
  - 提取结论
  - 论文要点
  - 分析PDF
  - 提取数据
  - 表征分析
  - extract insights
  - analyze paper
  - summarize paper
  - extract figures
  - core findings
  - Main points of the paper
  - analyze paper
  - Analyze the PDF
  - Extract data
  - Characterization analysis
  - review paper
  - survey paper
  - systematic review
  - meta-analysis
  - literature review
  - scoping review
  - field map

Sci-Extract — Scientific Extraction

Professional extraction of core insights and figures from scientific PDF papers.

> **Note**: This skill includes contributions from two authors. See [Copyright & License](#-copyright--license) section for details.

Features

• **Core Insights**: Automatically identify research problem, methodology, key results, innovations, applications, and limitations.
• **Review Literature Extraction**: For reviews, surveys, systematic reviews, scoping reviews, and meta-analyses, extract the field scope, taxonomy, evidence base, consensus, disagreements, evidence quality, research gaps, and future directions.
• **Paper Harvesting**: Given a DOI, PMID, PMCID, arXiv ID, title, or search query, pull complete metadata from every configured database, the native publisher XML, the full body text, and the figures, then write an agent-readable `raw.md` instead of leaving you to read a PDF.
• **Figure Detection**: Fetch publication-resolution figures from the publisher, or crop figure regions from PDF pages when the publisher ships none.
• **Metadata Extraction**: Parse title, authors, DOI, journal, and year.

Steps：

Step 1: Acquire the paper

Always read the paper fresh. Never rely on memory of the paper, even if the title looks familiar.

| Input type | Action | | ------------------------------------------- | ------------------------------------------------------------ | | DOI, PMID, PMCID, arXiv ID, title, or query | Run the harvester (Mode 3 below). It writes `raw.md` with the full text and figures embedded, which you then read instead of a PDF. | | PDF in `/mnt/user-data/uploads/` | Read it via the appropriate tool (see the `pdf-reading` skill if available). | | arXiv link | Extract the arXiv ID and run the harvester. Fall back to `web_fetch` on the abstract page if the harvester returns no full text. | | Pasted text in the chat | Use directly. | | Just a title with no link | Run the harvester with the title; it lists candidates and confirms the match before fetching. Do not guess the paper. |

If the paper is long, first classify the paper type, then prioritize the sections relevant to that type. For original research, prioritize abstract, introduction, method/theory, experiments, conclusion. For review literature, prioritize abstract, introduction, search/selection methods, taxonomy/classification sections, major thematic sections, summary tables, limitations, and future perspectives.

Step 2: Classify the paper type

Before choosing the extraction template, classify the paper as one of:

• Original research article
• Narrative review / survey
• Systematic review
• Meta-analysis
• Scoping review
• Perspective / tutorial / methods overview

Use the title, abstract, introduction, and section headings. Signals for review literature include "review", "survey", "systematic review", "meta-analysis", "scoping review", "bibliometric", "taxonomy", "current status", "recent progress", "challenges", "future perspectives", and broad comparison tables.

If the paper is a review, survey, systematic review, meta-analysis, scoping review, perspective, or tutorial overview, do **not** force it into the original-research Heilmeier template. Use the Review Literature Extraction Mode below. Original research asks "what did this paper do and prove"; review literature asks "how does this paper map the field and judge the evidence".

Step 3A: Original Research Mode - Answer the modified Heilmeier questions

Answer each of the seven questions below as a labeled subsection, in order. For each question, the rules differ on (a) whether your own evaluation is allowed and (b) whether external citations are allowed. Read the rules carefully before writing each subsection.

Question 1. What are you trying to do?

Open with a one-sentence statement of the paper's contribution written for a smart non-specialist, with absolutely no jargon. Ban acronyms and any technical term a first-year undergrad would not know. If a term of art is unavoidable, define it parenthetically in plain words. Then add one or two sentences expanding the objective in slightly more technical language.

Opinions allowed: no. Stay faithful to the paper. External citations allowed: no.

Question 2. What is the problem, how is it done today, and what are the limits of current practice?

Describe the real-world or scientific problem the paper addresses, then give a brief overview of how the field handles it at the time of the paper,