Literature Review

Visual Enhancement with Scientific Schematics

⚠️ MANDATORY: Every literature review MUST include at least 1-2 AI-generated figures using the scientific-schematics skill.

This is not optional. Literature reviews without visual elements are incomplete. Before finalizing any document:

1. Generate at minimum ONE schematic or diagram (e.g., PRISMA flow diagram for systematic reviews)
2. Prefer 2-3 figures for comprehensive reviews (search strategy flowchart, thematic synthesis diagram, conceptual framework)

How to generate figures:

• Use the scientific-schematics skill to generate AI-powered publication-quality diagrams
• Simply describe your desired diagram in natural language
• Nano Banana Pro will automatically generate, review, and refine the schematic

How to generate schematics:

python scripts/generate_schematic.py "your diagram description" -o figures/output.png

The AI will automatically:

• Create publication-quality images with proper formatting
• Review and refine through multiple iterations
• Ensure accessibility (colorblind-friendly, high contrast)
• Save outputs in the figures/ directory

When to add schematics:

• PRISMA flow diagrams for systematic reviews
• Literature search strategy flowcharts
• Thematic synthesis diagrams
• Research gap visualization maps
• Citation network diagrams
• Conceptual framework illustrations
• Any complex concept that benefits from visualization

For detailed guidance on creating schematics, refer to the scientific-schematics skill documentation.

Core Workflow

Literature reviews follow a structured, multi-phase workflow:

Phase 1: Planning and Scoping

1. Define Research Question: Use PICO framework (Population, Intervention, Comparison, Outcome) for clinical/biomedical reviews

   • Example: "What is the efficacy of CRISPR-Cas9 (I) for treating sickle cell disease (P) compared to standard care (C)?"

2. Establish Scope and Objectives:

   • Define clear, specific research questions
   • Determine review type (narrative, systematic, scoping, meta-analysis)
   • Set boundaries (time period, geographic scope, study types)

3. Develop Search Strategy:

   • Identify 2-4 main concepts from research question
   • List synonyms, abbreviations, and related terms for each concept
   • Plan Boolean operators (AND, OR, NOT) to combine terms
   • Select minimum 3 complementary databases

4. Set Inclusion/Exclusion Criteria:

   • Date range (e.g., last 10 years: 2015-2024)
   • Language (typically English, or specify multilingual)
   • Publication types (peer-reviewed, preprints, reviews)
   • Study designs (RCTs, observational, in vitro, etc.)
   • Document all criteria clearly

Phase 2: Systematic Literature Search

1. Multi-Database Search with paper_search.py:

   Use the integrated paper_search.py script to search multiple databases simultaneously:

   # Basic search across all sources
   python scripts/paper_search.py "CRISPR gene editing" --max 20 --dedupe
   
   # Search with year filter (Semantic Scholar)
   python scripts/paper_search.py "machine learning" --year "2020-2024" --max 15
   
   # Only show papers with PDF links
   python scripts/paper_search.py "deep learning" --pdf-only --format markdown
   
   # Search specific sources
   python scripts/paper_search.py "neural networks" --sources semantic,arxiv --output results.md
   
   # JSON output for further processing
   python scripts/paper_search.py "quantum computing" --format json --output papers.json
   

   Options:

   • --sources LIST: Comma-separated sources (semantic, arxiv, crossref)
   • --max N: Max results per source (default: 10)
   • --year YEAR: Year filter for Semantic Scholar (e.g., '2020', '2020-2024')
   • --format FORMAT: Output format (markdown, json)
   • --output FILE: Save results to file
   • --dedupe: Remove duplicate papers
   • --pdf-only: Only show papers with PDF links

   Supported Databases:

   • Semantic Scholar: 200M+ papers, cross-disciplinary, citation graphs
   • arXiv: Preprints in physics, math, CS, q-bio
   • CrossRef: DOI database with metadata for 100M+ works

2. Individual Database Search:

   Select databases appropriate for the domain:

   Biomedical & Life Sciences:

   • Use gget skill: gget search pubmed "search terms" for PubMed/PMC
   • Use gget skill: gget search biorxiv "search terms" for preprints
   • Use bioservices skill for ChEMBL, KEGG, UniProt, etc.

   General Scientific Literature:

   • Search arXiv via direct API (preprints in physics, math, CS, q-bio)
   • Search Semantic Scholar via API (200M+ papers, cross-disciplinary)
   • Use Google Scholar for comprehensive coverage (manual or careful scraping)

   Specialized Databases:

   • Use gget alphafold for protein structures
   • Use gget cosmic for cancer genomics
   • Use datacommons-client for demographic/statistical data
   • Use specialized databases as appropriate for the domain

3. Document Search Parameters:

   ## Search Strategy
   
   ### Database: PubMed
   - **Date searched**: 2024-10-25
   - **Date range**: 2015-01-01 to 2024-10-25
   - **Search string**:
   

   ("CRISPR"[Title] OR "Cas9"[Title]) AND ("sickle cell"[MeSH] OR "SCD"[Title/Abstract]) AND 2015:2024[Publication Date]

   - **Results**: 247 articles
   

   Repeat for each database searched.

4. Export and Aggregate Results:

   • Export results in JSON format from each database
   • Combine all results into a single file
   • Use scripts/search_databases.py for post-processing:

     python search_databases.py combined_results.json \
       --deduplicate \
       --format markdown \
       --output aggregated_results.md
     

Phase 3: Screening and Selection

1. Deduplication:

   python search_databases.py results.json --deduplicate --output unique_results.json
   

   • Removes duplicates by DOI (primary) or title (fallback)
   • Document number of duplicates removed

2. Title Screening:

   • Review all titles against inclusion/exclusion criteria
   • Exclude obviously irrelevant studies
   • Document number excluded at this stage

3. Abstract Screening:

   • Read abstracts of remaining studies
   • Apply inclusion/exclusion criteria rigorously
   • Document reasons for exclusion

4. Full-Text Screening:

   • Obtain full texts of remaining studies
   • Conduct detailed review against all criteria
   • Document specific reasons for exclusion
   • Record final number of included studies

5. Create PRISMA Flow Diagram:

   Initial search: n = X
   ├─ After deduplication: n = Y
   ├─ After title screening: n = Z
   ├─ After abstract screening: n = A
   └─ Included in review: n = B
   

Phase 4: Data Extraction and Quality Assessment

1. Extract Key Data from each included study:

   • Study metadata (authors, year, journal, DOI)
   • Study design and methods
   • Sample size and population characteristics
   • Key findings and results
   • Limitations noted by authors
   • Funding sources and conflicts of interest

2. Assess Study Quality:

   • For RCTs: Use Cochrane Risk of Bias tool
   • For observational studies: Use Newcastle-Ottawa Scale
   • For systematic reviews: Use AMSTAR 2
   • Rate each study: High, Moderate, Low, or Very Low quality
   • Consider excluding very low-quality studies

3. Organize by Themes:

   • Identify 3-5 major themes across studies
   • Group studies by theme (studies may appear in multiple themes)
   • Note patterns, consensus, and controversies

Phase 5: Synthesis and Analysis

1. Create Review Document from template:

   cp assets/review_template.md my_literature_review.md
   

2. Write Thematic Synthesis (NOT study-by-study summaries):

   • Organize Results section by themes or research questions
   • Synthesize findings across multiple studies within each theme
   • Compare and contrast different approaches and results
   • Identify consensus areas and points of controversy
   • Highlight the strongest evidence

   Example structure:

   #### 3.3.1 Theme: CRISPR Delivery Methods
   
   Multiple delivery approaches have been investigated for therapeutic
   gene editing. Viral vectors (AAV) were used in 15 studies^1-15^ and
   showed high transduction efficiency (65-85%) but raised immunogenicity
   concerns^3,7,12^. In contrast, lipid nanoparticles demonstrated lower
   efficiency (40-60%) but improved safety profiles^16-23^.
   

3. Critical Analysis:

   • Evaluate methodological strengths and limitations across studies
   • Assess quality and consistency of evidence
   • Identify knowledge gaps and methodological gaps
   • Note areas requiring future research

4. Write Discussion:

   • Interpret findings in broader context
   • Discuss clinical, practical, or research implications
   • Acknowledge limitations of the review itself
   • Compare with previous reviews if applicable
   • Propose specific future research directions

Phase 6: Citation Verification

CRITICAL: All citations must be verified for accuracy before final submission.

1. Verify All DOIs:

   python scripts/verify_citations.py my_literature_review.md
   

   This script:

   • Extracts all DOIs from the document
   • Verifies each DOI resolves correctly
   • Retrieves metadata from CrossRef
   • Generates verification report
   • Outputs properly formatted citations

2. Review Verification Report:

   • Check for any failed DOIs
   • Verify author names, titles, and publication details match
   • Correct any errors in the original document
   • Re-run verification until all citations pass

3. Format Citations Consistently:

   • Choose one citation style and use throughout (see references/citation_styles.md)
   • Common styles: APA, Nature, Vancouver, Chicago, IEEE
   • Use verification script output to format citations correctly
   • Ensure in-text citations match reference list format

Phase 7: Document Generation

1. Generate PDF:

   python scripts/generate_pdf.py my_literature_review.md \
     --citation-style apa \
     --output my_review.pdf
   

   Options:

   • --citation-style: apa, nature, chicago, vancouver, ieee
   • --no-toc: Disable table of contents
   • --no-numbers: Disable section numbering
   • --check-deps: Check if pandoc/xelatex are installed

2. Review Final Output:

   • Check PDF formatting and layout
   • Verify all sections are present
   • Ensure citations render correctly
   • Check that figures/tables appear properly
   • Verify table of contents is accurate

3. Quality Checklist:

   • All DOIs verified with verify_citations.py
   • Citations formatted consistently
   • PRISMA flow diagram included (for systematic reviews)
   • Search methodology fully documented
   • Inclusion/exclusion criteria clearly stated
   • Results organized thematically (not study-by-study)
   • Quality assessment completed
   • Limitations acknowledged
   • References complete and accurate
   • PDF generates without errors

Database-Specific Search Guidance

PubMed / PubMed Central

Access via gget skill:

# Search PubMed
gget search pubmed "CRISPR gene editing" -l 100

# Search with filters
# Use PubMed Advanced Search Builder to construct complex queries
# Then execute via gget or direct Entrez API

Search tips:

• Use MeSH terms: "sickle cell disease"[MeSH]
• Field tags: [Title], [Title/Abstract], [Author]
• Date filters: 2020:2024[Publication Date]
• Boolean operators: AND, OR, NOT
• See MeSH browser: https://meshb.nlm.nih.gov/search

bioRxiv / medRxiv

Access via gget skill:

gget search biorxiv "CRISPR sickle cell" -l 50

Important considerations:

• Preprints are not peer-reviewed
• Verify findings with caution
• Check if preprint has been published (CrossRef)
• Note preprint version and date

arXiv

Access via direct API or WebFetch:

# Example search categories:
# q-bio.QM (Quantitative Methods)
# q-bio.GN (Genomics)
# q-bio.MN (Molecular Networks)
# cs.LG (Machine Learning)
# stat.ML (Machine Learning Statistics)

# Search format: category AND terms
search_query = "cat:q-bio.QM AND ti:\"single cell sequencing\""

Semantic Scholar

Access via direct API (requires API key, or use free tier):

• 200M+ papers across all fields
• Excellent for cross-disciplinary searches
• Provides citation graphs and paper recommendations
• Use for finding highly influential papers

Specialized Biomedical Databases

Use appropriate skills:

• ChEMBL: bioservices skill for chemical bioactivity
• UniProt: gget or bioservices skill for protein information
• KEGG: bioservices skill for pathways and genes
• COSMIC: gget skill for cancer mutations
• AlphaFold: gget alphafold for protein structures
• PDB: gget or direct API for experimental structures

Citation Chaining

Expand search via citation networks:

1. Forward citations (papers citing key papers):

   • Use Google Scholar "Cited by"
   • Use Semantic Scholar or OpenAlex APIs
   • Identifies newer research building on seminal work

2. Backward citations (references from key papers):

   • Extract references from included papers
   • Identify highly cited foundational work
   • Find papers cited by multiple included studies

Citation Style Guide

Detailed formatting guidelines are in references/citation_styles.md. Quick reference:

APA (7th Edition)

• In-text: (Smith et al., 2023)
• Reference: Smith, J. D., Johnson, M. L., & Williams, K. R. (2023). Title. Journal, 22(4), 301-318. https://doi.org/10.xxx/yyy

Nature

• In-text: Superscript numbers^1,2^
• Reference: Smith, J. D., Johnson, M. L. & Williams, K. R. Title. Nat. Rev. Drug Discov. 22, 301-318 (2023).

Vancouver

• In-text: Superscript numbers^1,2^
• Reference: Smith JD, Johnson ML, Williams KR. Title. Nat Rev Drug Discov. 2023;22(4):301-18.

Always verify citations with verify_citations.py before finalizing.

Best Practices

Search Strategy

1. Use multiple databases (minimum 3): Ensures comprehensive coverage
2. Include preprint servers: Captures latest unpublished findings
3. Document everything: Search strings, dates, result counts for reproducibility
4. Test and refine: Run pilot searches, review results, adjust search terms

Screening and Selection

1. Use clear criteria: Document inclusion/exclusion criteria before screening
2. Screen systematically: Title → Abstract → Full text
3. Document exclusions: Record reasons for excluding studies
4. Consider dual screening: For systematic reviews, have two reviewers screen independently

Synthesis

1. Organize thematically: Group by themes, NOT by individual studies
2. Synthesize across studies: Compare, contrast, identify patterns
3. Be critical: Evaluate quality and consistency of evidence
4. Identify gaps: Note what's missing or understudied

Quality and Reproducibility

1. Assess study quality: Use appropriate quality assessment tools
2. Verify all citations: Run verify_citations.py script
3. Document methodology: Provide enough detail for others to reproduce
4. Follow guidelines: Use PRISMA for systematic reviews

Writing

1. Be objective: Present evidence fairly, acknowledge limitations
2. Be systematic: Follow structured template
3. Be specific: Include numbers, statistics, effect sizes where available
4. Be clear: Use clear headings, logical flow, thematic organization

Common Pitfalls to Avoid

1. Single database search: Misses relevant papers; always search multiple databases
2. No search documentation: Makes review irreproducible; document all searches
3. Study-by-study summary: Lacks synthesis; organize thematically instead
4. Unverified citations: Leads to errors; always run verify_citations.py
5. Too broad search: Yields thousands of irrelevant results; refine with specific terms
6. Too narrow search: Misses relevant papers; include synonyms and related terms
7. Ignoring preprints: Misses latest findings; include bioRxiv, medRxiv, arXiv
8. No quality assessment: Treats all evidence equally; assess and report quality
9. Publication bias: Only positive results published; note potential bias
10. Outdated search: Field evolves rapidly; clearly state search date

Example Workflow

Complete workflow for a biomedical literature review:

# 1. Create review document from template
cp assets/review_template.md crispr_sickle_cell_review.md

# 2. Search multiple databases using appropriate skills
# - Use gget skill for PubMed, bioRxiv
# - Use direct API access for arXiv, Semantic Scholar
# - Export results in JSON format

# 3. Aggregate and process results
python scripts/search_databases.py combined_results.json \
  --deduplicate \
  --rank citations \
  --year-start 2015 \
  --year-end 2024 \
  --format markdown \
  --output search_results.md \
  --summary

# 4. Screen results and extract data
# - Manually screen titles, abstracts, full texts
# - Extract key data into the review document
# - Organize by themes

# 5. Write the review following template structure
# - Introduction with clear objectives
# - Detailed methodology section
# - Results organized thematically
# - Critical discussion
# - Clear conclusions

# 6. Verify all citations
python scripts/verify_citations.py crispr_sickle_cell_review.md

# Review the citation report
cat crispr_sickle_cell_review_citation_report.json

# Fix any failed citations and re-verify
python scripts/verify_citations.py crispr_sickle_cell_review.md

# 7. Generate professional PDF
python scripts/generate_pdf.py crispr_sickle_cell_review.md \
  --citation-style nature \
  --output crispr_sickle_cell_review.pdf

# 8. Review final PDF and markdown outputs

Integration with Other Skills

This skill works seamlessly with other scientific skills:

Database Access Skills

• gget: PubMed, bioRxiv, COSMIC, AlphaFold, Ensembl, UniProt
• bioservices: ChEMBL, KEGG, Reactome, UniProt, PubChem
• datacommons-client: Demographics, economics, health statistics

Analysis Skills

• pydeseq2: RNA-seq differential expression (for methods sections)
• scanpy: Single-cell analysis (for methods sections)
• anndata: Single-cell data (for methods sections)
• biopython: Sequence analysis (for background sections)

Visualization Skills

• matplotlib: Generate figures and plots for review
• seaborn: Statistical visualizations

Writing Skills

• brand-guidelines: Apply institutional branding to PDF
• internal-comms: Adapt review for different audiences

Resources

Bundled Resources

Scripts:

• scripts/paper_search.py: Multi-database search (Semantic Scholar, arXiv, CrossRef) with PDF links. NEW: Full abstracts by default (no truncation)
• scripts/deep_read.py: NEW Full PDF text extraction and structured deep reading notes
• scripts/verify_citations.py: Verify DOIs and generate formatted citations
• scripts/generate_pdf.py: Convert markdown to professional PDF
• scripts/search_databases.py: Process, deduplicate, and format search results

References:

• references/citation_styles.md: Detailed citation formatting guide (APA, Nature, Vancouver, Chicago, IEEE)
• references/database_strategies.md: Comprehensive database search strategies

Assets:

• assets/review_template.md: Complete literature review template with all sections

External Resources

Guidelines:

• PRISMA (Systematic Reviews): http://www.prisma-statement.org/
• Cochrane Handbook: https://training.cochrane.org/handbook
• AMSTAR 2 (Review Quality): https://amstar.ca/

Tools:

• MeSH Browser: https://meshb.nlm.nih.gov/search
• PubMed Advanced Search: https://pubmed.ncbi.nlm.nih.gov/advanced/
• Boolean Search Guide: https://www.ncbi.nlm.nih.gov/books/NBK3827/

Citation Styles:

• APA Style: https://apastyle.apa.org/
• Nature Portfolio: https://www.nature.com/nature-portfolio/editorial-policies/reporting-standards
• NLM/Vancouver: https://www.nlm.nih.gov/bsd/uniform_requirements.html

Dependencies

Required Python Packages

pip install requests  # For citation verification

Required System Tools

# For PDF generation
brew install pandoc  # macOS
apt-get install pandoc  # Linux

# For LaTeX (PDF generation)
brew install --cask mactex  # macOS
apt-get install texlive-xetex  # Linux

Check dependencies:

python scripts/generate_pdf.py --check-deps

Continuous Literature Search (贯穿科研全流程)

Literature retrieval runs throughout all research phases — not just Phase 1:

Phase 1: Broad Search (Initial Literature Review)

• Broad search: 15–30 papers for literature review
• Autonomous PDF download: Attempt automatic retrieval (arXiv, open access, APIs)
• User assistance: Request help for paywalled papers

# Phase 1 broad search - full abstracts, no truncation
python scripts/paper_search.py "your research topic" --max 30 --dedupe --output phase1_results.md

# Filter for papers with PDF links only
python scripts/paper_search.py "topic" --pdf-only --max 20

Phase 1 Deep Thinking: On-Demand Verification

• Verify insights: Search to validate thinking strategies
• Cross-domain methods: Find techniques from other fields
• Contradiction search: Look for opposing views

# Verify specific hypothesis
python scripts/paper_search.py "specific hypothesis OR claim" --year "2022-2024" --max 10

Phase 3: Design-Driven Search

• New questions: Search when design raises new questions
• Baseline discovery: Find comparison methods
• Implementation details: Search for technical approaches

python scripts/paper_search.py "method OR technique name" --sources semantic,arxiv --max 15

Phase 4: Context Search for Unexpected Results

• Explain anomalies: Find papers that explain unexpected results
• Method troubleshooting: Understand why something didn't work
• Alternative approaches: Find backup strategies

python scripts/paper_search.py "unexpected result explanation" --max 10

Phase 5–6: Citation Support for Paper Claims

• Support claims: Find citations for specific statements
• Related work: Comprehensive literature for Introduction
• Position findings: Locate papers for comparison

# Search for specific claims
python scripts/paper_search.py "specific claim keywords" --year "2020-2024" --max 10

Graceful Degradation Protocol

The system NEVER fabricates citations. When retrieval fails:

1. Autonomous retrieval first: Try arXiv, open access, APIs
2. Mark status: Track as abstract_only, download_failed, or user_provided
3. Request user help: Provide clear instructions for inaccessible papers

Literature retrieval report:
  Full text obtained: K papers ✅
  Abstract only / download failed: M papers ⚠️

Papers I could not access:
  1. [Author et al., Year] "Title" — URL: [link]
  2. ...

To help me read these, you can:
  A) Download PDFs manually
  B) Provide key findings summary
  C) Tell me which to skip

Deep Reading (精读功能)

Go beyond skimming abstracts to full paper comprehension.

Deep Read Command

# Full paper deep reading with structured notes
python scripts/deep_read.py paper.pdf --output reading_notes.md

# Extract only (no analysis)
python scripts/deep_read.py paper.pdf --extract-only

# Extract specific section
python scripts/deep_read.py paper.pdf --section abstract
python scripts/deep_read.py paper.pdf --section methods
python scripts/deep_read.py paper.pdf --section results

# JSON format output
python scripts/deep_read.py paper.pdf --format json --output paper_analysis.json

Deep Reading Output Structure

The deep_read.py script generates structured notes:

# Deep Reading Notes

## Paper Information
- **Title**: [extracted title]
- **DOI**: [verified DOI link]
- **Year**: [publication year]
- **Keywords**: [extracted keywords]

## Paper Structure
- **Sections**: [list of detected sections]
- **Figures**: [figure references]
- **Tables**: [table references]

## Abstract
[Full abstract text - NO TRUNCATION]

## Full Text Content
[Complete extracted text from PDF]

## Analysis Prompts
1. **Main Contribution**: What is the primary contribution?
2. **Methodology**: What methods are used?
3. **Key Findings**: Main results and support?
4. **Limitations**: Acknowledged and identified?
5. **Relevance**: How does this relate to your research?
6. **Future Work**: Suggested directions?
7. **Questions**: What questions does this raise?

## Citation
[Formatted citation placeholder]

Skim vs Deep Read Workflow

# Workflow: Skim → Select → Deep Read

# 1. Skim: Find relevant papers with full abstracts
python scripts/paper_search.py "topic" --max 30 --output skim_results.md

# 2. Select: Identify top 5-10 most relevant papers

# 3. Deep Read: For each selected paper
python scripts/deep_read.py paper1.pdf --output paper1_notes.md
python scripts/deep_read.py paper2.pdf --output paper2_notes.md
# ...

PDF Library Requirements

For deep reading, install one of:

pip install PyPDF2     # Basic extraction
pip install PyMuPDF    # Better quality (recommended)

Summary

This literature-review skill provides:

1. Systematic methodology following academic best practices
2. Multi-database integration via existing scientific skills
3. Citation verification ensuring accuracy and credibility
4. Professional output in markdown and PDF formats
5. Comprehensive guidance covering the entire review process
6. Quality assurance with verification and validation tools
7. Reproducibility through detailed documentation requirements
8. Continuous literature search across all research phases (Phase 1-6)
9. Deep reading capability with full PDF text extraction
10. Full abstracts - no truncation by default for complete information
11. Graceful degradation - never fabricates citations

Quick Reference

Conduct thorough, rigorous literature reviews that meet academic standards and provide comprehensive synthesis of current knowledge in any domain.