npx skills add ...
npx skills add lingzhi227/agent-research-skills --skill 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.
npx skills add lingzhi227/agent-research-skills --skill self-review
Review an academic paper using a structured review form with multiple reviewer personas.
$ARGUMENTS — Path to PDF file or .tex fileTries pymupdf4llm (best) → pymupdf → pypdf. Install: pip install pymupdf4llm pymupdf pypdf
Extracts title (via font size), section headings, and section text. Requires: pip install pymupdf
Key flags: --format text, --verbose
extract_pdf_text.py to extract text.tex: read the LaTeX source directlyRun three independent reviews using different personas (from references/review-form.md):
For each persona, generate a review following the NeurIPS review JSON format in references/review-form.md.
After each review, apply the reflection prompt: re-evaluate accuracy and soundness, refine if needed. Stop when "I am done".
Output format:
~/.claude/skills/self-review/references/review-form.md~/.claude/skills/self-review/scripts/extract_pdf_text.pyYou MUST verify that all required sections are present: Abstract, Introduction, Methods/Approach, Experiments/Results, Discussion/Conclusion. Reduce scores if any are missing.
## 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 | ... | ... | ... | ... |
| ... | ... | ... | ... | ... |