self-review
Automatically review an academic paper using the NeurIPS review form with three reviewer personas, ensemble scoring, and reflection refinement. Extracts text from PDF, runs structured review, and outputs actionable feedback. Use when the user wants to review a paper before submission or get feedback on a draft.
- Installs
- 1.6K
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/lingzhi227/agent-research-skills --skill self-review- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads self-review automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Self-Review
Review an academic paper using a structured review form with multiple reviewer personas.
Input
$ARGUMENTS— Path to PDF file or.texfile
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.pyto 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):
- Harsh but fair reviewer: Expects good experiments that lead to insights
- Harsh and critical reviewer: Looking for impactful ideas in the field
- Open-minded reviewer: Looking for novel ideas not proposed before
For each persona, generate a review following the NeurIPS review JSON format in references/review-form.md.
Step 3: Reflection Refinement (up to 3 rounds per reviewer)
After each review, apply the reflection prompt: re-evaluate accuracy and soundness, refine if needed. Stop when "I am done".
Step 4: Aggregate
- Combine all three reviews
- Average numerical scores (round to nearest integer)
- Synthesize a meta-review finding consensus
- Weight scores using AgentLaboratory weights: Overall (1.0), Contribution (0.4), Presentation (0.2), others (0.1 each)
Step 5: Actionable Report
Output format:
## Review Summary
- **Overall Score**: X/10 (Weighted: Y/10)
- **Decision**: Accept / Reject
- **Confidence**: Z/5
## Strengths (consensus across reviewers)
1. ...
2. ...
## Weaknesses (consensus across reviewers)
1. ...
2. ...
## Questions for Authors
1. ...
## Specific Suggestions for Improvement
1. [Section X, Page Y]: ...
2. [Section Z, Page W]: ...
## Score Breakdown
| Dimension | R1 | R2 | R3 | Avg |
|-----------|----|----|-----|-----|
| Overall | ... | ... | ... | ... |
| Contribution | ... | ... | ... | ... |
| ... | ... | ... | ... | ... |
References
- NeurIPS review form, scoring weights, personas, reflection prompts:
~/.claude/skills/self-review/references/review-form.md - PDF text extraction:
~/.claude/skills/self-review/scripts/extract_pdf_text.py
Missing Sections Check
You MUST verify that all required sections are present: Abstract, Introduction, Methods/Approach, Experiments/Results, Discussion/Conclusion. Reduce scores if any are missing.
Related Skills
- Upstream: paper-compilation
- Downstream: paper-revision, rebuttal-writing
- See also: slide-generation
FAQ
What does the self-review skill do?
Automatically review an academic paper using the NeurIPS review form with three reviewer personas, ensemble scoring, and reflection refinement. Extracts text from PDF, runs structured review, and outputs actionable feedback. Use when the user wants to review a paper before submission or get feedback on a draft.
How do I install self-review?
Run npx skills add https://github.com/lingzhi227/agent-research-skills --skill self-review in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/self-review/ (personal) or .claude/skills/self-review/ (project).
Which AI agents can use self-review?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is self-review safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains self-review?
It is published by lingzhi227 in lingzhi227/agent-research-skills. It has 1,629 recorded installs.
More from lingzhi227/agent-research-skills
literature-review
lingzhi227/agent-research-skills
Conduct comprehensive literature reviews using multi-perspective dialogue simulation. Generate diverse expert personas, conduct grounded Q&A conversations, and synthesize findings into structured knowledge. Use when starting a new research project or writing a survey section.
literature-search
lingzhi227/agent-research-skills
Search academic literature using Semantic Scholar, arXiv, and OpenAlex APIs. Returns structured JSONL with title, authors, year, venue, abstract, citations, and BibTeX. Use when the user needs to find papers, check related work, or build a bibliography.
figure-generation
lingzhi227/agent-research-skills
Generate publication-quality scientific figures using matplotlib/seaborn with a three-phase pipeline (query expansion, code generation with execution, VLM visual feedback). Handles bar charts, line plots, heatmaps, training curves, ablation plots, and more. Use when the user needs figures, plots, or visualizations for a paper.
latex-formatting
lingzhi227/agent-research-skills
Handle LaTeX formatting, templates, and styling for academic papers. Set up conference templates (ICML, ICLR, NeurIPS, AAAI, ACL), fix formatting issues, manage packages, and ensure venue-specific compliance. Use when the user needs to set up a paper template, fix LaTeX formatting, or prepare for submission.
math-reasoning
lingzhi227/agent-research-skills
Formal mathematical reasoning for research papers — derive equations, write proofs, formalize problem settings, select statistical tests, and generate LaTeX math notation. Use when the user needs mathematical derivations, theorem proofs, notation tables, or statistical analysis formalization.
backward-traceability
lingzhi227/agent-research-skills
Make every number in the final PDF traceable to the exact code line that produced it. Uses \hypertarget/\hyperlink LaTeX commands and \num{formula} evaluated at compile time. Use for reproducibility and data integrity verification.
Popular code quality & workflow skills
grill-me
mattpocock/skills
A relentless interview to sharpen a plan or design.
improve-codebase-architecture
mattpocock/skills
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
handoff
mattpocock/skills
Compact the current conversation into a handoff document for another agent to pick up.
domain-modeling
mattpocock/skills
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
codebase-design
mattpocock/skills
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
diagnosing-bugs
mattpocock/skills
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.