Self Review

This does a multi-reviewer simulation of your academic paper before you submit it. It extracts text from PDFs or LaTeX, then runs three independent reviews using different personas (harsh but fair, harsh and critical, open-minded) following the NeurIPS review format. Each reviewer goes through up to three reflection rounds to refine their scores, then all reviews get aggregated with weighted scoring borrowed from AgentLaboratory. You get a structured report with consensus strengths and weaknesses, actionable suggestions tagged to specific sections, and a score breakdown table. The workflow is thorough but the quality depends entirely on the paper text extraction working cleanly. Most useful when you want to stress test a draft before real submission and need specific feedback beyond what a single LLM pass would give you.

skills.sh installs: 1.7K
GitHub stars: 459
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add lingzhi227/agent-research-skills --skill self-review --agent claude-code

Installs into .claude/skills of the current project.

Files

Self-Review

Review an academic paper using a structured review form with multiple reviewer personas.

Input

$ARGUMENTS — Path to PDF file or .tex file

Scripts

Extract text from PDF

python ~/.claude/skills/self-review/scripts/extract_pdf_text.py paper.pdf --output paper_text.txt
python ~/.claude/skills/self-review/scripts/extract_pdf_text.py paper.pdf --format markdown

Tries pymupdf4llm (best) → pymupdf → pypdf. Install: pip install pymupdf4llm pymupdf pypdf

Parse PDF into structured sections

python ~/.claude/skills/self-review/scripts/parse_pdf_sections.py \
  --pdf paper.pdf --output sections.json

Extracts title (via font size), section headings, and section text. Requires: pip install pymupdf Key flags: --format text, --verbose

Workflow

Step 1: Load Paper

If PDF: use extract_pdf_text.py to extract text
If .tex: read the LaTeX source directly

Step 2: Three-Persona Review

Run three independent reviews using different personas (from references/review-form.md):

SKILL.md on GitHub

Details

Repository: github.com/lingzhi227/agent-research-skills
Categories: Git & Pull Requests, Code Review & Quality, AI & Agent Building, Data Science & ML, Office & Documents
First seen: Jun 3, 2026