lingzhi227/claude-research-skills · Archived
Automatically review an academic paper using the NeurIPS review form with three reviewer personas, ensemble scoring, and reflection refinement.
npx skills add lingzhi227/claude-research-skills --skill self-review
This repository is archived — consider an actively maintained alternative.
Programmatic canvas toolkit for creating, editing, and refining Excalidraw diagrams via MCP too…
1 installsAssess research idea novelty through systematic literature search. Multi-round search-evaluate …
1 installsCompile LaTeX papers to PDF with automatic error detection, chktex style checking, and citation…
1 installsGenerate publication-quality LaTeX tables from experimental results. Convert JSON/CSV data to b…
1 installsRelated neighbors and high-traction skills in the same topics — useful to compare before installing.
Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybr…
568.2K installsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or bot…
216.8K installsUse this skill whenever the user wants to do anything with PDF files. This includes reading or …
192.4K installsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.do…
184.5K installsUse this skill any time a spreadsheet file is the primary input or output. This means any task …
165K installsOther skills from lingzhi227/claude-research-skills · top by installs.
npx skills add lingzhi227/claude-research-skills
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
main
Parsed from SKILL.md frontmatter.
Files included with this skill beyond the listing page.
SKILL.md
3,514 B
SUMMARY.md
331 B
Review an academic paper using a structured review form with multiple reviewer personas.
$ARGUMENTS — Path to PDF file or .tex filepython ~/.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 markdownTries pymupdf4llm (best) → pymupdf → pypdf. Install: pip install pymupdf4llm pymupdf pypdf
python ~/.claude/skills/self-review/scripts/parse_pdf_sections.py \
--pdf paper.pdf --output sections.jsonExtracts title (via font size), section headings, and section text. Requires: pip install pymupdf Key flags: --format text, --verbose
extractpdftext.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:
## 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 | ... | ... | ... | ... |
| ... | ... | ... | ... | ... |~/.claude/skills/self-review/references/review-form.md~/.claude/skills/self-review/scripts/extractpdftext.pyYou MUST verify that all required sections are present: Abstract, Introduction, Methods/Approach, Experiments/Results, Discussion/Conclusion. Reduce scores if any are missing.