self-review

The self-review skill automates the academic paper review process by applying three distinct reviewer personas to a provided PDF or LaTeX file. It extracts text, parses sections, generates structured reviews based on the NeurIPS format, performs reflection-based refinement, and produces an aggregated report with consensus feedback and weighted scores.

826
Installs
4
Use cases
5/10
Quality

Is self-review safe to install?

Review the source first

Review the source first: our audit of self-review's source files found 5 shell commands, 0 external URLs, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill executes local Python scripts and shell commands to process files, which involves reading and writing files on the local filesystem.

How we audit skills: our security review methodology.

Who is this skill for?

Academic researchers and authors preparing papers for submission who require structured feedback on drafts.

What can you do with it?

  • Reviewing academic papers before submission
  • Generating actionable feedback on research drafts
  • Simulating peer review using multiple reviewer personas
  • Identifying missing sections in research manuscripts

How good is this skill?

Quality score: 5/10. The skill documentation is clear, provides specific file paths for scripts and references, and outlines a logical multi-step workflow for the review process.

What does the skill file contain?

SKILL.md
# 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
```bash
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
```bash
python ~/.claude/skills/self-review/scripts/parse_pdf...

Frequently asked questions

What file formats does the skill support?

The skill supports PDF files and LaTeX (.tex) source files.

How does the skill determine the review criteria?

It uses the NeurIPS review form, scoring weights, personas, and reflection prompts defined in ~/.claude/skills/self-review/references/review-form.md.

Can the skill verify if a paper is complete?

Yes, it checks for the presence of Abstract, Introduction, Methods/Approach, Experiments/Results, and Discussion/Conclusion sections.

Data sourced from lingzhi227/agent-research-skills on GitHub. Install counts from skills.sh. The summary and security audit are derived from the skill's source files: every command and URL listed appears verbatim in the source.

Related skills