SkillsAdd

lingzhi227/agent-research-skills

self-review

Automatically review an academic paper using the NeurIPS review form with three reviewer personas, ensemble scoring, and reflection refinement.

All-time #9268 First seen Feb 20, 2026
8-week activity · all time api

Installation

$ npx skills add lingzhi227/agent-research-skills --skill self-review
View on skills.sh ↗ GitHub repository ↗
Feature your product here Skill page unit · reach builders installing agent skills View pricing →

Summary

  • 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.

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

find-skills Same topic
vercel-labs/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "fi…

18.6K installs
agent-browser Same topic
vercel-labs/agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, includ…

11.9K installs
vercel-react-best-practices Same topic
vercel-labs/agent-skills

React and Next.js performance optimization guidelines from Vercel Engineering. This skill shoul…

3.7K installs
web-design-guidelines Same topic
vercel-labs/agent-skills

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "chec…

4.7K installs
microsoft-foundry Same topic
microsoft/azure-skills

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and …

1.7K installs
azure-prepare Same topic
microsoft/azure-skills

Prepare azd-based Azure projects for deployment: generates azure.yaml, infrastructure (Bicep/Te…

1.5K installs

Also in this package

Other skills from lingzhi227/agent-research-skills · top by installs.

npx skills add lingzhi227/agent-research-skills
literature-review 3.9K literature-search 2.6K figure-generation 2.2K latex-formatting 7 math-reasoning 2.1K citation-management 2.1K backward-traceability 14 data-analysis 1.9K deep-research 1.8K idea-generation 1.8K

Browse all from lingzhi227/agent-research-skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 317
Default branch main
Open issues 3
Status Active

Skill metadata

Parsed from SKILL.md frontmatter.

Declared agents claude-code

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 3,514 B
  • docs SUMMARY.md 331 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 1,400 installs

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

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 extractpdftext.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):

  1. Harsh but fair reviewer: Expects good experiments that lead to insights
  2. Harsh and critical reviewer: Looking for impactful ideas in the field
  3. 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/extractpdftext.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](../paper-compilation/)
  • Downstream: [paper-revision](../paper-revision/), [rebuttal-writing](../rebuttal-writing/)
  • See also: [slide-generation](../slide-generation/)