agentleFS
Sign inStart free
astoreyaiastoreyai/claude-skills/paper-reviewer/SKILL.md

paper-reviewer

Skill3 starsChanged 12 months agoMITView on GitHub

Comprehensive pre-submission review orchestrator. Coordinates methodology checks, bias detection, AI text detection, statistical validation, and reporting guideline compliance for journal submissions.

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 10 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 10

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before submitting papers to journals

    line 14
  2. Distinctive:

    After completing systematic reviews

    line 15
  3. Distinctive:

    When preparing dissertation chapters for committee

    line 16
  4. Distinctive:

    Methodology Assessment: - Verify research design rigor

    line 22
  5. Distinctive:

    Statistical Validation: - Check assumptions, effect sizes, power analysis

    line 24
  6. Distinctive:

    Citation Integrity: - Verify references, check for retractions

    line 26
  7. Distinctive:

    Check randomization/blinding (if applicable)

    line 51
  8. Distinctive:

    Check effect size reporting

    line 60
  9. Distinctive:

    Default thresholds (can override):

    line 117
  10. Distinctive:

    All 8 phases enabled by default

    line 120

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Paper Reviewer

Comprehensive pre-submission review for journal manuscripts. Orchestrates multiple specialized skills from research-assistant to ensure publication readiness.

When to Use

  • Before submitting papers to journals
  • After completing systematic reviews
  • When preparing dissertation chapters for committee
  • For quality assurance on research manuscripts

Features

  1. AI Text Detection - Identify LLM-generated patterns
  2. Methodology Assessment - Verify research design rigor
  3. Bias Detection - Apply RoB 2, ROBINS-I, QUADAS-2 frameworks
  4. Statistical Validation - Check assumptions, effect sizes, power analysis
  5. Reporting Compliance - Validate CONSORT, PRISMA, STROBE guidelines
  6. Citation Integrity - Verify references, check for retractions
  7. Reproducibility Audit - Assess code/data availability

Usage

Review the manuscript at ~/Documents/submissions/AffectivePrompting/ for journal submission.
This is a systematic review targeting IEEE Transactions.

Review Pipeline

Phase 1: Triage

  • Classify paper type (RCT, systematic review, observational, etc.)
  • Identify target journal requirements
  • List available files

Phase 2: AI Detection

  • Run ai-check skill
  • Flag sections with AI patterns >30%
  • Generate authenticity report

Phase 3: Methodology

  • Assess study design appropriateness
  • Verify protocol adherence
  • Check randomization/blinding (if applicable)

Phase 4: Risk of Bias

  • Apply appropriate RoB tool
  • Document domain-by-domain assessment
  • Generate traffic light visualization

Phase 5: Statistical Validation

  • Verify assumption testing
  • Check effect size reporting
  • Validate power analysis

Phase 6: Reporting Compliance

  • Apply appropriate checklist (CONSORT/PRISMA/STROBE)
  • Calculate compliance percentage
  • List missing items

Phase 7: Citation Audit

  • Verify all references
  • Check for retractions
  • Validate DOIs

Phase 8: Reproducibility

  • Check code availability
  • Verify data accessibility
  • Assess documentation completeness

Output

Generates comprehensive review report:

  • Executive summary with overall assessment
  • Section-by-section findings
  • Priority-ranked revision checklist
  • Detailed appendices

Paper Type-Specific Workflows

Systematic Reviews

  • PRISMA 2020 compliance
  • AMSTAR 2 quality assessment
  • Meta-analysis validation

RCTs

  • CONSORT compliance
  • RoB 2 bias assessment
  • ITT/per-protocol analysis check

Observational Studies

  • STROBE compliance
  • ROBINS-I bias assessment
  • Confounding control verification

Integration

Uses research-assistant skills:

  • ai-check
  • risk-of-bias
  • hypothesis-test
  • effect-size
  • power-analysis
  • publication-prep
  • citation-format
  • prisma-diagram

Configuration

Default thresholds (can override):

  • AI detection: 30% (flag if higher)
  • Reporting compliance: 85% minimum
  • All 8 phases enabled by default

Part of ai_scientist research workflow automation

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free