Literature Review
Overview
Conduct systematic, comprehensive literature reviews following rigorous academic methodology. Search multiple literature databases, synthesize findings thematically, verify all citations for accuracy, and generate professional output documents in markdown and PDF formats.
This skill integrates with multiple scientific skills for database access (gget, bioservices, datacommons-client) and provides specialized tools for citation verification, result aggregation, and document generation.
When to Use This Skill
Use this skill when:
- Conducting a systematic literature review for research or publication
- Synthesizing current knowledge on a specific topic across multiple sources
- Performing meta-analysis or scoping reviews
- Writing the literature review section of a research paper or thesis
- Investigating the state of the art in a research domain
- Identifying research gaps and future directions
- Requiring verified citations and professional formatting
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:
- Generate at minimum ONE schematic or diagram (e.g., PRISMA flow diagram for systematic reviews)
- 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
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)?"
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)
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
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
Multi-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
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.
Export and Aggregate Results:
Phase 3: Screening and Selection
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
Title Screening:
- Review all titles against inclusion/exclusion criteria
- Exclude obviously irrelevant studies
- Document number excluded at this stage
Abstract Screening:
- Read abstracts of remaining studies
- Apply inclusion/exclusion criteria rigorously
- Document reasons for exclusion
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
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
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
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
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
Create Review Document from template:
cp assets/review_template.md my_literature_review.md
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^.
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
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.
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
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
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
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
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
Quality Checklist:
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:
Forward citations (papers citing key papers):
- Use Google Scholar "Cited by"
- Use Semantic Scholar or OpenAlex APIs
- Identifies newer research building on seminal work
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
Prioritizing High-Impact Papers (CRITICAL)
Always prioritize influential, highly-cited papers from reputable authors and top venues. Quality matters more than quantity in literature reviews.
Citation Count Thresholds
Use citation counts to identify the most impactful papers:
| Paper Age |
Citation Threshold |
Classification |
| 0-3 years |
20+ citations |
Noteworthy |
| 0-3 years |
100+ citations |
Highly Influential |
| 3-7 years |
100+ citations |
Significant |
| 3-7 years |
500+ citations |
Landmark Paper |
| 7+ years |
500+ citations |
Seminal Work |
| 7+ years |
1000+ citations |
Foundational |
Journal and Venue Tiers
Prioritize papers from higher-tier venues:
- Tier 1 (Always Prefer): Nature, Science, Cell, NEJM, Lancet, JAMA, PNAS, Nature Medicine, Nature Biotechnology
- Tier 2 (Strong Preference): High-impact specialized journals (IF>10), top conferences (NeurIPS, ICML for ML/AI)
- Tier 3 (Include When Relevant): Respected specialized journals (IF 5-10)
- Tier 4 (Use Sparingly): Lower-impact peer-reviewed venues
Author Reputation Assessment
Prefer papers from:
- Senior researchers with high h-index (>40 in established fields)
- Leading research groups at recognized institutions (Harvard, Stanford, MIT, Oxford, etc.)
- Authors with multiple Tier-1 publications in the relevant field
- Researchers with recognized expertise (awards, editorial positions, society fellows)
Identifying Seminal Papers
For any topic, identify foundational work by:
- High citation count (typically 500+ for papers 5+ years old)
- Frequently cited by other included studies (appears in many reference lists)
- Published in Tier-1 venues (Nature, Science, Cell family)
- Written by field pioneers (often cited as establishing concepts)
Search Strategy
- Use multiple databases (minimum 3): Ensures comprehensive coverage
- Include preprint servers: Captures latest unpublished findings
- Document everything: Search strings, dates, result counts for reproducibility
- Test and refine: Run pilot searches, review results, adjust search terms
- Sort by citations: When available, sort search results by citation count to surface influential work first
Screening and Selection
- Use clear criteria: Document inclusion/exclusion criteria before screening
- Screen systematically: Title → Abstract → Full text
- Document exclusions: Record reasons for excluding studies
- Consider dual screening: For systematic reviews, have two reviewers screen independently
- Prioritize Tier-1 venues: Include all relevant papers from top venues before considering lower-tier sources
Synthesis
- Organize thematically: Group by themes, NOT by individual studies
- Synthesize across studies: Compare, contrast, identify patterns
- Be critical: Evaluate quality and consistency of evidence
- Identify gaps: Note what's missing or understudied
- Lead with high-impact work: Start each theme with the most influential/cited papers
Quality and Reproducibility
- Assess study quality: Use appropriate quality assessment tools
- Verify all citations: Run verify_citations.py script
- Document methodology: Provide enough detail for others to reproduce
- Follow guidelines: Use PRISMA for systematic reviews
Writing
- Be objective: Present evidence fairly, acknowledge limitations
- Be systematic: Follow structured template
- Be specific: Include numbers, statistics, effect sizes where available
- Be clear: Use clear headings, logical flow, thematic organization
- Cite impact indicators: When relevant, mention citation counts and venue prestige
Common Pitfalls to Avoid
- Single database search: Misses relevant papers; always search multiple databases
- No search documentation: Makes review irreproducible; document all searches
- Study-by-study summary: Lacks synthesis; organize thematically instead
- Unverified citations: Leads to errors; always run verify_citations.py
- Too broad search: Yields thousands of irrelevant results; refine with specific terms
- Too narrow search: Misses relevant papers; include synonyms and related terms
- Ignoring preprints: Misses latest findings; include bioRxiv, medRxiv, arXiv
- No quality assessment: Treats all evidence equally; assess and report quality
- Publication bias: Only positive results published; note potential bias
- 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
- venue-templates: Access venue-specific writing style guides when preparing reviews for publication
Venue-Specific Writing Styles
When preparing a literature review for a specific journal, consult the venue-templates skill for writing style guidance:
venue_writing_styles.md: Master style comparison across venues
nature_science_style.md: Nature/Science flowing abstract style, story-driven structure
cell_press_style.md: Cell Press graphical abstracts, Highlights format
medical_journal_styles.md: NEJM/Lancet/JAMA structured abstracts, PRISMA compliance
These guides help adapt your review's tone, abstract format, and structure to match the target venue's expectations.
Resources
Bundled Resources
Scripts:
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:
Tools:
Citation Styles:
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
Summary
This literature-review skill provides:
- Systematic methodology following academic best practices
- Multi-database integration via existing scientific skills
- Citation verification ensuring accuracy and credibility
- Professional output in markdown and PDF formats
- Comprehensive guidance covering the entire review process
- Quality assurance with verification and validation tools
- Reproducibility through detailed documentation requirements
Conduct thorough, rigorous literature reviews that meet academic standards and provide comprehensive synthesis of current knowledge in any domain.
1---2name: literature-review3description: Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).4allowed-tools: [Read, Write, Edit, Bash]5metadata:6 source: https://skillmd.com/skills/tools-only/literature-review7---89# Literature Review1011## Overview1213Conduct systematic, comprehensive literature reviews following rigorous academic methodology. Search multiple literature databases, synthesize findings thematically, verify all citations for accuracy, and generate professional output documents in markdown and PDF formats.1415This skill integrates with multiple scientific skills for database access (gget, bioservices, datacommons-client) and provides specialized tools for citation verification, result aggregation, and document generation.1617## When to Use This Skill1819Use this skill when:20- Conducting a systematic literature review for research or publication21- Synthesizing current knowledge on a specific topic across multiple sources22- Performing meta-analysis or scoping reviews23- Writing the literature review section of a research paper or thesis24- Investigating the state of the art in a research domain25- Identifying research gaps and future directions26- Requiring verified citations and professional formatting2728## Visual Enhancement with Scientific Schematics2930**⚠️ MANDATORY: Every literature review MUST include at least 1-2 AI-generated figures using the scientific-schematics skill.**3132This is not optional. Literature reviews without visual elements are incomplete. Before finalizing any document:331. Generate at minimum ONE schematic or diagram (e.g., PRISMA flow diagram for systematic reviews)342. Prefer 2-3 figures for comprehensive reviews (search strategy flowchart, thematic synthesis diagram, conceptual framework)3536**How to generate figures:**37- Use the **scientific-schematics** skill to generate AI-powered publication-quality diagrams38- Simply describe your desired diagram in natural language39- Nano Banana Pro will automatically generate, review, and refine the schematic4041**How to generate schematics:**42```bash43python scripts/generate_schematic.py "your diagram description" -o figures/output.png44```4546The AI will automatically:47- Create publication-quality images with proper formatting48- Review and refine through multiple iterations49- Ensure accessibility (colorblind-friendly, high contrast)50- Save outputs in the figures/ directory5152**When to add schematics:**53- PRISMA flow diagrams for systematic reviews54- Literature search strategy flowcharts55- Thematic synthesis diagrams56- Research gap visualization maps57- Citation network diagrams58- Conceptual framework illustrations59- Any complex concept that benefits from visualization6061For detailed guidance on creating schematics, refer to the scientific-schematics skill documentation.6263---6465## Core Workflow6667Literature reviews follow a structured, multi-phase workflow:6869### Phase 1: Planning and Scoping70711. **Define Research Question**: Use PICO framework (Population, Intervention, Comparison, Outcome) for clinical/biomedical reviews72 - Example: "What is the efficacy of CRISPR-Cas9 (I) for treating sickle cell disease (P) compared to standard care (C)?"73742. **Establish Scope and Objectives**:75 - Define clear, specific research questions76 - Determine review type (narrative, systematic, scoping, meta-analysis)77 - Set boundaries (time period, geographic scope, study types)78793. **Develop Search Strategy**:80 - Identify 2-4 main concepts from research question81 - List synonyms, abbreviations, and related terms for each concept82 - Plan Boolean operators (AND, OR, NOT) to combine terms83 - Select minimum 3 complementary databases84854. **Set Inclusion/Exclusion Criteria**:86 - Date range (e.g., last 10 years: 2015-2024)87 - Language (typically English, or specify multilingual)88 - Publication types (peer-reviewed, preprints, reviews)89 - Study designs (RCTs, observational, in vitro, etc.)90 - Document all criteria clearly9192### Phase 2: Systematic Literature Search93941. **Multi-Database Search**:9596 Select databases appropriate for the domain:9798 **Biomedical & Life Sciences:**99 - Use `gget` skill: `gget search pubmed "search terms"` for PubMed/PMC100 - Use `gget` skill: `gget search biorxiv "search terms"` for preprints101 - Use `bioservices` skill for ChEMBL, KEGG, UniProt, etc.102103 **General Scientific Literature:**104 - Search arXiv via direct API (preprints in physics, math, CS, q-bio)105 - Search Semantic Scholar via API (200M+ papers, cross-disciplinary)106 - Use Google Scholar for comprehensive coverage (manual or careful scraping)107108 **Specialized Databases:**109 - Use `gget alphafold` for protein structures110 - Use `gget cosmic` for cancer genomics111 - Use `datacommons-client` for demographic/statistical data112 - Use specialized databases as appropriate for the domain1131142. **Document Search Parameters**:115 ```markdown116 ## Search Strategy117118 ### Database: PubMed119 - **Date searched**: 2024-10-25120 - **Date range**: 2015-01-01 to 2024-10-25121 - **Search string**:122 ```123 ("CRISPR"[Title] OR "Cas9"[Title])124 AND ("sickle cell"[MeSH] OR "SCD"[Title/Abstract])125 AND 2015:2024[Publication Date]126 ```127 - **Results**: 247 articles128 ```129130 Repeat for each database searched.1311323. **Export and Aggregate Results**:133 - Export results in JSON format from each database134 - Combine all results into a single file135 - Use `scripts/search_databases.py` for post-processing:136 ```bash137 python search_databases.py combined_results.json \138 --deduplicate \139 --format markdown \140 --output aggregated_results.md141 ```142143### Phase 3: Screening and Selection1441451. **Deduplication**:146 ```bash147 python search_databases.py results.json --deduplicate --output unique_results.json148 ```149 - Removes duplicates by DOI (primary) or title (fallback)150 - Document number of duplicates removed1511522. **Title Screening**:153 - Review all titles against inclusion/exclusion criteria154 - Exclude obviously irrelevant studies155 - Document number excluded at this stage1561573. **Abstract Screening**:158 - Read abstracts of remaining studies159 - Apply inclusion/exclusion criteria rigorously160 - Document reasons for exclusion1611624. **Full-Text Screening**:163 - Obtain full texts of remaining studies164 - Conduct detailed review against all criteria165 - Document specific reasons for exclusion166 - Record final number of included studies1671685. **Create PRISMA Flow Diagram**:169 ```170 Initial search: n = X171 ├─ After deduplication: n = Y172 ├─ After title screening: n = Z173 ├─ After abstract screening: n = A174 └─ Included in review: n = B175 ```176177### Phase 4: Data Extraction and Quality Assessment1781791. **Extract Key Data** from each included study:180 - Study metadata (authors, year, journal, DOI)181 - Study design and methods182 - Sample size and population characteristics183 - Key findings and results184 - Limitations noted by authors185 - Funding sources and conflicts of interest1861872. **Assess Study Quality**:188 - **For RCTs**: Use Cochrane Risk of Bias tool189 - **For observational studies**: Use Newcastle-Ottawa Scale190 - **For systematic reviews**: Use AMSTAR 2191 - Rate each study: High, Moderate, Low, or Very Low quality192 - Consider excluding very low-quality studies1931943. **Organize by Themes**:195 - Identify 3-5 major themes across studies196 - Group studies by theme (studies may appear in multiple themes)197 - Note patterns, consensus, and controversies198199### Phase 5: Synthesis and Analysis2002011. **Create Review Document** from template:202 ```bash203 cp assets/review_template.md my_literature_review.md204 ```2052062. **Write Thematic Synthesis** (NOT study-by-study summaries):207 - Organize Results section by themes or research questions208 - Synthesize findings across multiple studies within each theme209 - Compare and contrast different approaches and results210 - Identify consensus areas and points of controversy211 - Highlight the strongest evidence212213 Example structure:214 ```markdown215 #### 3.3.1 Theme: CRISPR Delivery Methods216217 Multiple delivery approaches have been investigated for therapeutic218 gene editing. Viral vectors (AAV) were used in 15 studies^1-15^ and219 showed high transduction efficiency (65-85%) but raised immunogenicity220 concerns^3,7,12^. In contrast, lipid nanoparticles demonstrated lower221 efficiency (40-60%) but improved safety profiles^16-23^.222 ```2232243. **Critical Analysis**:225 - Evaluate methodological strengths and limitations across studies226 - Assess quality and consistency of evidence227 - Identify knowledge gaps and methodological gaps228 - Note areas requiring future research2292304. **Write Discussion**:231 - Interpret findings in broader context232 - Discuss clinical, practical, or research implications233 - Acknowledge limitations of the review itself234 - Compare with previous reviews if applicable235 - Propose specific future research directions236237### Phase 6: Citation Verification238239**CRITICAL**: All citations must be verified for accuracy before final submission.2402411. **Verify All DOIs**:242 ```bash243 python scripts/verify_citations.py my_literature_review.md244 ```245246 This script:247 - Extracts all DOIs from the document248 - Verifies each DOI resolves correctly249 - Retrieves metadata from CrossRef250 - Generates verification report251 - Outputs properly formatted citations2522532. **Review Verification Report**:254 - Check for any failed DOIs255 - Verify author names, titles, and publication details match256 - Correct any errors in the original document257 - Re-run verification until all citations pass2582593. **Format Citations Consistently**:260 - Choose one citation style and use throughout (see `references/citation_styles.md`)261 - Common styles: APA, Nature, Vancouver, Chicago, IEEE262 - Use verification script output to format citations correctly263 - Ensure in-text citations match reference list format264265### Phase 7: Document Generation2662671. **Generate PDF**:268 ```bash269 python scripts/generate_pdf.py my_literature_review.md \270 --citation-style apa \271 --output my_review.pdf272 ```273274 Options:275 - `--citation-style`: apa, nature, chicago, vancouver, ieee276 - `--no-toc`: Disable table of contents277 - `--no-numbers`: Disable section numbering278 - `--check-deps`: Check if pandoc/xelatex are installed2792802. **Review Final Output**:281 - Check PDF formatting and layout282 - Verify all sections are present283 - Ensure citations render correctly284 - Check that figures/tables appear properly285 - Verify table of contents is accurate2862873. **Quality Checklist**:288 - [ ] All DOIs verified with verify_citations.py289 - [ ] Citations formatted consistently290 - [ ] PRISMA flow diagram included (for systematic reviews)291 - [ ] Search methodology fully documented292 - [ ] Inclusion/exclusion criteria clearly stated293 - [ ] Results organized thematically (not study-by-study)294 - [ ] Quality assessment completed295 - [ ] Limitations acknowledged296 - [ ] References complete and accurate297 - [ ] PDF generates without errors298299## Database-Specific Search Guidance300301### PubMed / PubMed Central302303Access via `gget` skill:304```bash305# Search PubMed306gget search pubmed "CRISPR gene editing" -l 100307308# Search with filters309# Use PubMed Advanced Search Builder to construct complex queries310# Then execute via gget or direct Entrez API311```312313**Search tips**:314- Use MeSH terms: `"sickle cell disease"[MeSH]`315- Field tags: `[Title]`, `[Title/Abstract]`, `[Author]`316- Date filters: `2020:2024[Publication Date]`317- Boolean operators: AND, OR, NOT318- See MeSH browser: https://meshb.nlm.nih.gov/search319320### bioRxiv / medRxiv321322Access via `gget` skill:323```bash324gget search biorxiv "CRISPR sickle cell" -l 50325```326327**Important considerations**:328- Preprints are not peer-reviewed329- Verify findings with caution330- Check if preprint has been published (CrossRef)331- Note preprint version and date332333### arXiv334335Access via direct API or WebFetch:336```python337# Example search categories:338# q-bio.QM (Quantitative Methods)339# q-bio.GN (Genomics)340# q-bio.MN (Molecular Networks)341# cs.LG (Machine Learning)342# stat.ML (Machine Learning Statistics)343344# Search format: category AND terms345search_query = "cat:q-bio.QM AND ti:\"single cell sequencing\""346```347348### Semantic Scholar349350Access via direct API (requires API key, or use free tier):351- 200M+ papers across all fields352- Excellent for cross-disciplinary searches353- Provides citation graphs and paper recommendations354- Use for finding highly influential papers355356### Specialized Biomedical Databases357358Use appropriate skills:359- **ChEMBL**: `bioservices` skill for chemical bioactivity360- **UniProt**: `gget` or `bioservices` skill for protein information361- **KEGG**: `bioservices` skill for pathways and genes362- **COSMIC**: `gget` skill for cancer mutations363- **AlphaFold**: `gget alphafold` for protein structures364- **PDB**: `gget` or direct API for experimental structures365366### Citation Chaining367368Expand search via citation networks:3693701. **Forward citations** (papers citing key papers):371 - Use Google Scholar "Cited by"372 - Use Semantic Scholar or OpenAlex APIs373 - Identifies newer research building on seminal work3743752. **Backward citations** (references from key papers):376 - Extract references from included papers377 - Identify highly cited foundational work378 - Find papers cited by multiple included studies379380## Citation Style Guide381382Detailed formatting guidelines are in `references/citation_styles.md`. Quick reference:383384### APA (7th Edition)385- In-text: (Smith et al., 2023)386- Reference: Smith, J. D., Johnson, M. L., & Williams, K. R. (2023). Title. *Journal*, *22*(4), 301-318. https://doi.org/10.xxx/yyy387388### Nature389- In-text: Superscript numbers^1,2^390- Reference: Smith, J. D., Johnson, M. L. & Williams, K. R. Title. *Nat. Rev. Drug Discov.* **22**, 301-318 (2023).391392### Vancouver393- In-text: Superscript numbers^1,2^394- Reference: Smith JD, Johnson ML, Williams KR. Title. Nat Rev Drug Discov. 2023;22(4):301-18.395396**Always verify citations** with verify_citations.py before finalizing.397398## Best Practices399400### Prioritizing High-Impact Papers (CRITICAL)401402**Always prioritize influential, highly-cited papers from reputable authors and top venues.** Quality matters more than quantity in literature reviews.403404#### Citation Count Thresholds405406Use citation counts to identify the most impactful papers:407408| Paper Age | Citation Threshold | Classification |409|-----------|-------------------|----------------|410| 0-3 years | 20+ citations | Noteworthy |411| 0-3 years | 100+ citations | Highly Influential |412| 3-7 years | 100+ citations | Significant |413| 3-7 years | 500+ citations | Landmark Paper |414| 7+ years | 500+ citations | Seminal Work |415| 7+ years | 1000+ citations | Foundational |416417#### Journal and Venue Tiers418419Prioritize papers from higher-tier venues:420421- **Tier 1 (Always Prefer):** Nature, Science, Cell, NEJM, Lancet, JAMA, PNAS, Nature Medicine, Nature Biotechnology422- **Tier 2 (Strong Preference):** High-impact specialized journals (IF>10), top conferences (NeurIPS, ICML for ML/AI)423- **Tier 3 (Include When Relevant):** Respected specialized journals (IF 5-10)424- **Tier 4 (Use Sparingly):** Lower-impact peer-reviewed venues425426#### Author Reputation Assessment427428Prefer papers from:429- **Senior researchers** with high h-index (>40 in established fields)430- **Leading research groups** at recognized institutions (Harvard, Stanford, MIT, Oxford, etc.)431- **Authors with multiple Tier-1 publications** in the relevant field432- **Researchers with recognized expertise** (awards, editorial positions, society fellows)433434#### Identifying Seminal Papers435436For any topic, identify foundational work by:4371. **High citation count** (typically 500+ for papers 5+ years old)4382. **Frequently cited by other included studies** (appears in many reference lists)4393. **Published in Tier-1 venues** (Nature, Science, Cell family)4404. **Written by field pioneers** (often cited as establishing concepts)441442### Search Strategy4431. **Use multiple databases** (minimum 3): Ensures comprehensive coverage4442. **Include preprint servers**: Captures latest unpublished findings4453. **Document everything**: Search strings, dates, result counts for reproducibility4464. **Test and refine**: Run pilot searches, review results, adjust search terms4475. **Sort by citations**: When available, sort search results by citation count to surface influential work first448449### Screening and Selection4501. **Use clear criteria**: Document inclusion/exclusion criteria before screening4512. **Screen systematically**: Title → Abstract → Full text4523. **Document exclusions**: Record reasons for excluding studies4534. **Consider dual screening**: For systematic reviews, have two reviewers screen independently4545. **Prioritize Tier-1 venues**: Include all relevant papers from top venues before considering lower-tier sources455456### Synthesis4571. **Organize thematically**: Group by themes, NOT by individual studies4582. **Synthesize across studies**: Compare, contrast, identify patterns4593. **Be critical**: Evaluate quality and consistency of evidence4604. **Identify gaps**: Note what's missing or understudied4615. **Lead with high-impact work**: Start each theme with the most influential/cited papers462463### Quality and Reproducibility4641. **Assess study quality**: Use appropriate quality assessment tools4652. **Verify all citations**: Run verify_citations.py script4663. **Document methodology**: Provide enough detail for others to reproduce4674. **Follow guidelines**: Use PRISMA for systematic reviews468469### Writing4701. **Be objective**: Present evidence fairly, acknowledge limitations4712. **Be systematic**: Follow structured template4723. **Be specific**: Include numbers, statistics, effect sizes where available4734. **Be clear**: Use clear headings, logical flow, thematic organization4745. **Cite impact indicators**: When relevant, mention citation counts and venue prestige475476## Common Pitfalls to Avoid4774781. **Single database search**: Misses relevant papers; always search multiple databases4792. **No search documentation**: Makes review irreproducible; document all searches4803. **Study-by-study summary**: Lacks synthesis; organize thematically instead4814. **Unverified citations**: Leads to errors; always run verify_citations.py4825. **Too broad search**: Yields thousands of irrelevant results; refine with specific terms4836. **Too narrow search**: Misses relevant papers; include synonyms and related terms4847. **Ignoring preprints**: Misses latest findings; include bioRxiv, medRxiv, arXiv4858. **No quality assessment**: Treats all evidence equally; assess and report quality4869. **Publication bias**: Only positive results published; note potential bias48710. **Outdated search**: Field evolves rapidly; clearly state search date488489## Example Workflow490491Complete workflow for a biomedical literature review:492493```bash494# 1. Create review document from template495cp assets/review_template.md crispr_sickle_cell_review.md496497# 2. Search multiple databases using appropriate skills498# - Use gget skill for PubMed, bioRxiv499# - Use direct API access for arXiv, Semantic Scholar500# - Export results in JSON format501502# 3. Aggregate and process results503python scripts/search_databases.py combined_results.json \504 --deduplicate \505 --rank citations \506 --year-start 2015 \507 --year-end 2024 \508 --format markdown \509 --output search_results.md \510 --summary511512# 4. Screen results and extract data513# - Manually screen titles, abstracts, full texts514# - Extract key data into the review document515# - Organize by themes516517# 5. Write the review following template structure518# - Introduction with clear objectives519# - Detailed methodology section520# - Results organized thematically521# - Critical discussion522# - Clear conclusions523524# 6. Verify all citations525python scripts/verify_citations.py crispr_sickle_cell_review.md526527# Review the citation report528cat crispr_sickle_cell_review_citation_report.json529530# Fix any failed citations and re-verify531python scripts/verify_citations.py crispr_sickle_cell_review.md532533# 7. Generate professional PDF534python scripts/generate_pdf.py crispr_sickle_cell_review.md \535 --citation-style nature \536 --output crispr_sickle_cell_review.pdf537538# 8. Review final PDF and markdown outputs539```540541## Integration with Other Skills542543This skill works seamlessly with other scientific skills:544545### Database Access Skills546- **gget**: PubMed, bioRxiv, COSMIC, AlphaFold, Ensembl, UniProt547- **bioservices**: ChEMBL, KEGG, Reactome, UniProt, PubChem548- **datacommons-client**: Demographics, economics, health statistics549550### Analysis Skills551- **pydeseq2**: RNA-seq differential expression (for methods sections)552- **scanpy**: Single-cell analysis (for methods sections)553- **anndata**: Single-cell data (for methods sections)554- **biopython**: Sequence analysis (for background sections)555556### Visualization Skills557- **matplotlib**: Generate figures and plots for review558- **seaborn**: Statistical visualizations559560### Writing Skills561- **brand-guidelines**: Apply institutional branding to PDF562- **internal-comms**: Adapt review for different audiences563- **venue-templates**: Access venue-specific writing style guides when preparing reviews for publication564565### Venue-Specific Writing Styles566567When preparing a literature review for a specific journal, consult the **venue-templates** skill for writing style guidance:568- `venue_writing_styles.md`: Master style comparison across venues569- `nature_science_style.md`: Nature/Science flowing abstract style, story-driven structure570- `cell_press_style.md`: Cell Press graphical abstracts, Highlights format571- `medical_journal_styles.md`: NEJM/Lancet/JAMA structured abstracts, PRISMA compliance572573These guides help adapt your review's tone, abstract format, and structure to match the target venue's expectations.574575## Resources576577### Bundled Resources578579**Scripts:**580- `scripts/verify_citations.py`: Verify DOIs and generate formatted citations581- `scripts/generate_pdf.py`: Convert markdown to professional PDF582- `scripts/search_databases.py`: Process, deduplicate, and format search results583584**References:**585- `references/citation_styles.md`: Detailed citation formatting guide (APA, Nature, Vancouver, Chicago, IEEE)586- `references/database_strategies.md`: Comprehensive database search strategies587588**Assets:**589- `assets/review_template.md`: Complete literature review template with all sections590591### External Resources592593**Guidelines:**594- PRISMA (Systematic Reviews): http://www.prisma-statement.org/595- Cochrane Handbook: https://training.cochrane.org/handbook596- AMSTAR 2 (Review Quality): https://amstar.ca/597598**Tools:**599- MeSH Browser: https://meshb.nlm.nih.gov/search600- PubMed Advanced Search: https://pubmed.ncbi.nlm.nih.gov/advanced/601- Boolean Search Guide: https://www.ncbi.nlm.nih.gov/books/NBK3827/602603**Citation Styles:**604- APA Style: https://apastyle.apa.org/605- Nature Portfolio: https://www.nature.com/nature-portfolio/editorial-policies/reporting-standards606- NLM/Vancouver: https://www.nlm.nih.gov/bsd/uniform_requirements.html607608## Dependencies609610### Required Python Packages611```bash612pip install requests # For citation verification613```614615### Required System Tools616```bash617# For PDF generation618brew install pandoc # macOS619apt-get install pandoc # Linux620621# For LaTeX (PDF generation)622brew install --cask mactex # macOS623apt-get install texlive-xetex # Linux624```625626Check dependencies:627```bash628python scripts/generate_pdf.py --check-deps629```630631## Summary632633This literature-review skill provides:6346351. **Systematic methodology** following academic best practices6362. **Multi-database integration** via existing scientific skills6373. **Citation verification** ensuring accuracy and credibility6384. **Professional output** in markdown and PDF formats6395. **Comprehensive guidance** covering the entire review process6406. **Quality assurance** with verification and validation tools6417. **Reproducibility** through detailed documentation requirements642643Conduct thorough, rigorous literature reviews that meet academic standards and provide comprehensive synthesis of current knowledge in any domain.