mcpField
P
paper-analyzer

paper-analyzer

github.com/boom5426Productivity64188 installsUpdated 2w ago
Repository

About paper-analyzer

paper-analyzer is a skill for researchers who want structured, in-depth analysis of a specific paper. It accepts an arXiv ID, title, or file path and produces notes covering methods, evidence, limitations, and related work, with scripts for note generation and graph updates.

Key features

  1. 01Identify papers by ID, title, or path
  2. 02Analyze methods and experimental evidence
  3. 03Assess contributions and limitations
  4. 04Generate structured research notes
  5. 05Update a paper relationship graph

Use cases

  1. 01Reviewing an arXiv paper before citing it
  2. 02Comparing a paper’s methods and results
  3. 03Tracking links among related papers

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/boom5426/nature-paper-skills --skill paper-analyzer

After installing, type/paper-analyzerin Claude Code to confirm it loaded.

Bundled filesscripts/generate_note.pyscripts/update_graph.py

Details

From the project README

Paper Analyzer

Overview

Perform deep analysis of a specific paper, generating structured notes that cover claims, methodology, experiment evaluation, strengths and limitations, and links to adjacent work.

Workflow

Step 1: Identify Paper

Accept input: arXiv ID (e.g., "2402.12345"), full ID ("arXiv:2402.12345"), paper title, or file path.

Step 2: Fetch Paper Content

curl -L "https://arxiv.org/pdf/[PAPER_ID]" -o /tmp/paper_analysis/[PAPER_ID].pdf
curl -L "https://arxiv.org/e-print/[PAPER_ID]" -o /tmp/paper_analysis/[PAPER_ID].tar.gz
curl -s "https://arxiv.org/abs/[PAPER_ID]" > /tmp/paper_analysis/arxiv_page.html

Step 3: Deep Analysis

Analyze: abstract, methodology, experiments, results, contributions, limitations, future work, related papers.

Step 4: Generate Note

python scripts/generate_note.py --paper-id "$PAPER_ID" --title "$TITLE" --authors "$AUTHORS" --domain "$DOMAIN"

Step 5: Update Knowledge Graph

python scripts/update_graph.py --paper-id "$PAPER_ID" --title "$TITLE" --domain "$DOMAIN" --score $SCORE

Scripts

  • scripts/generate_note.py — Generate structured note template
  • scripts/update_graph.py — Update paper relationship graph

Note Structure

The generated note includes: core info, abstract (EN/CN), research background, method overview with architecture figures, experiment results with tables, deep analysis, related paper comparison, tech roadmap positioning, future work, and comprehensive evaluation (0-10 scoring).

Dependencies

  • Python 3.8+, PyYAML, requests
  • Network access (arXiv)

Based on evil-read-arxiv — an automated paper reading workflow. MIT License.

Comments

Markdown supported