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 <path-to-scientific-schematics-skill>/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.). Use 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.).45allowed-tools: [Read, Write, Edit, Bash]6metadata:7 source: https://skillmd.com/skills/stanfish06/literature-review8---910# Literature Review1112## Overview1314Conduct 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.1516This 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.1718## When to Use This Skill1920Use this skill when:21- Conducting a systematic literature review for research or publication22- Synthesizing current knowledge on a specific topic across multiple sources23- Performing meta-analysis or scoping reviews24- Writing the literature review section of a research paper or thesis25- Investigating the state of the art in a research domain26- Identifying research gaps and future directions27- Requiring verified citations and professional formatting2829## Visual Enhancement with Scientific Schematics3031**⚠️ MANDATORY: Every literature review MUST include at least 1-2 AI-generated figures using the scientific-schematics skill.**3233This is not optional. Literature reviews without visual elements are incomplete. Before finalizing any document:341. Generate at minimum ONE schematic or diagram (e.g., PRISMA flow diagram for systematic reviews)352. Prefer 2-3 figures for comprehensive reviews (search strategy flowchart, thematic synthesis diagram, conceptual framework)3637**How to generate figures:**38- Use the **scientific-schematics** skill to generate AI-powered publication-quality diagrams39- Simply describe your desired diagram in natural language40- Nano Banana Pro will automatically generate, review, and refine the schematic4142**How to generate schematics:**43```bash44python <path-to-scientific-schematics-skill>/scripts/generate_schematic.py "your diagram description" -o figures/output.png45```4647The AI will automatically:48- Create publication-quality images with proper formatting49- Review and refine through multiple iterations50- Ensure accessibility (colorblind-friendly, high contrast)51- Save outputs in the figures/ directory5253**When to add schematics:**54- PRISMA flow diagrams for systematic reviews55- Literature search strategy flowcharts56- Thematic synthesis diagrams57- Research gap visualization maps58- Citation network diagrams59- Conceptual framework illustrations60- Any complex concept that benefits from visualization6162For detailed guidance on creating schematics, refer to the scientific-schematics skill documentation.6364---6566## Core Workflow6768Literature reviews follow a structured, multi-phase workflow:6970### Phase 1: Planning and Scoping71721. **Define Research Question**: Use PICO framework (Population, Intervention, Comparison, Outcome) for clinical/biomedical reviews73 - Example: "What is the efficacy of CRISPR-Cas9 (I) for treating sickle cell disease (P) compared to standard care (C)?"74752. **Establish Scope and Objectives**:76 - Define clear, specific research questions77 - Determine review type (narrative, systematic, scoping, meta-analysis)78 - Set boundaries (time period, geographic scope, study types)79803. **Develop Search Strategy**:81 - Identify 2-4 main concepts from research question82 - List synonyms, abbreviations, and related terms for each concept83 - Plan Boolean operators (AND, OR, NOT) to combine terms84 - Select minimum 3 complementary databases85864. **Set Inclusion/Exclusion Criteria**:87 - Date range (e.g., last 10 years: 2015-2024)88 - Language (typically English, or specify multilingual)89 - Publication types (peer-reviewed, preprints, reviews)90 - Study designs (RCTs, observational, in vitro, etc.)91 - Document all criteria clearly9293### Phase 2: Systematic Literature Search94951. **Multi-Database Search**:9697 Select databases appropriate for the domain:9899 **Biomedical & Life Sciences:**100 - Use `gget` skill: `gget search pubmed "search terms"` for PubMed/PMC101 - Use `gget` skill: `gget search biorxiv "search terms"` for preprints102 - Use `bioservices` skill for ChEMBL, KEGG, UniProt, etc.103104 **General Scientific Literature:**105 - Search arXiv via direct API (preprints in physics, math, CS, q-bio)106 - Search Semantic Scholar via API (200M+ papers, cross-disciplinary)107 - Use Google Scholar for comprehensive coverage (manual or careful scraping)108109 **Specialized Databases:**110 - Use `gget alphafold` for protein structures111 - Use `gget cosmic` for cancer genomics112 - Use `datacommons-client` for demographic/statistical data113 - Use specialized databases as appropriate for the domain1141152. **Document Search Parameters**:116 ```markdown117 ## Search Strategy118119 ### Database: PubMed120 - **Date searched**: 2024-10-25121 - **Date range**: 2015-01-01 to 2024-10-25122 - **Search string**:123 ```124 ("CRISPR"[Title] OR "Cas9"[Title])125 AND ("sickle cell"[MeSH] OR "SCD"[Title/Abstract])126 AND 2015:2024[Publication Date]127 ```128 - **Results**: 247 articles129 ```130131 Repeat for each database searched.1321333. **Export and Aggregate Results**:134 - Export results in JSON format from each database135 - Combine all results into a single file136 - Use `scripts/search_databases.py` for post-processing:137 ```bash138 python search_databases.py combined_results.json \139 --deduplicate \140 --format markdown \141 --output aggregated_results.md142 ```143144### Phase 3: Screening and Selection1451461. **Deduplication**:147 ```bash148 python search_databases.py results.json --deduplicate --output unique_results.json149 ```150 - Removes duplicates by DOI (primary) or title (fallback)151 - Document number of duplicates removed1521532. **Title Screening**:154 - Review all titles against inclusion/exclusion criteria155 - Exclude obviously irrelevant studies156 - Document number excluded at this stage1571583. **Abstract Screening**:159 - Read abstracts of remaining studies160 - Apply inclusion/exclusion criteria rigorously161 - Document reasons for exclusion1621634. **Full-Text Screening**:164 - Obtain full texts of remaining studies165 - Conduct detailed review against all criteria166 - Document specific reasons for exclusion167 - Record final number of included studies1681695. **Create PRISMA Flow Diagram**:170 ```171 Initial search: n = X172 ├─ After deduplication: n = Y173 ├─ After title screening: n = Z174 ├─ After abstract screening: n = A175 └─ Included in review: n = B176 ```177178### Phase 4: Data Extraction and Quality Assessment1791801. **Extract Key Data** from each included study:181 - Study metadata (authors, year, journal, DOI)182 - Study design and methods183 - Sample size and population characteristics184 - Key findings and results185 - Limitations noted by authors186 - Funding sources and conflicts of interest1871882. **Assess Study Quality**:189 - **For RCTs**: Use Cochrane Risk of Bias tool190 - **For observational studies**: Use Newcastle-Ottawa Scale191 - **For systematic reviews**: Use AMSTAR 2192 - Rate each study: High, Moderate, Low, or Very Low quality193 - Consider excluding very low-quality studies1941953. **Organize by Themes**:196 - Identify 3-5 major themes across studies197 - Group studies by theme (studies may appear in multiple themes)198 - Note patterns, consensus, and controversies199200### Phase 5: Synthesis and Analysis2012021. **Create Review Document** from template:203 ```bash204 cp assets/review_template.md my_literature_review.md205 ```2062072. **Write Thematic Synthesis** (NOT study-by-study summaries):208 - Organize Results section by themes or research questions209 - Synthesize findings across multiple studies within each theme210 - Compare and contrast different approaches and results211 - Identify consensus areas and points of controversy212 - Highlight the strongest evidence213214 Example structure:215 ```markdown216 #### 3.3.1 Theme: CRISPR Delivery Methods217218 Multiple delivery approaches have been investigated for therapeutic219 gene editing. Viral vectors (AAV) were used in 15 studies^1-15^ and220 showed high transduction efficiency (65-85%) but raised immunogenicity221 concerns^3,7,12^. In contrast, lipid nanoparticles demonstrated lower222 efficiency (40-60%) but improved safety profiles^16-23^.223 ```2242253. **Critical Analysis**:226 - Evaluate methodological strengths and limitations across studies227 - Assess quality and consistency of evidence228 - Identify knowledge gaps and methodological gaps229 - Note areas requiring future research2302314. **Write Discussion**:232 - Interpret findings in broader context233 - Discuss clinical, practical, or research implications234 - Acknowledge limitations of the review itself235 - Compare with previous reviews if applicable236 - Propose specific future research directions237238### Phase 6: Citation Verification239240**CRITICAL**: All citations must be verified for accuracy before final submission.2412421. **Verify All DOIs**:243 ```bash244 python scripts/verify_citations.py my_literature_review.md245 ```246247 This script:248 - Extracts all DOIs from the document249 - Verifies each DOI resolves correctly250 - Retrieves metadata from CrossRef251 - Generates verification report252 - Outputs properly formatted citations2532542. **Review Verification Report**:255 - Check for any failed DOIs256 - Verify author names, titles, and publication details match257 - Correct any errors in the original document258 - Re-run verification until all citations pass2592603. **Format Citations Consistently**:261 - Choose one citation style and use throughout (see `references/citation_styles.md`)262 - Common styles: APA, Nature, Vancouver, Chicago, IEEE263 - Use verification script output to format citations correctly264 - Ensure in-text citations match reference list format265266### Phase 7: Document Generation2672681. **Generate PDF**:269 ```bash270 python scripts/generate_pdf.py my_literature_review.md \271 --citation-style apa \272 --output my_review.pdf273 ```274275 Options:276 - `--citation-style`: apa, nature, chicago, vancouver, ieee277 - `--no-toc`: Disable table of contents278 - `--no-numbers`: Disable section numbering279 - `--check-deps`: Check if pandoc/xelatex are installed2802812. **Review Final Output**:282 - Check PDF formatting and layout283 - Verify all sections are present284 - Ensure citations render correctly285 - Check that figures/tables appear properly286 - Verify table of contents is accurate2872883. **Quality Checklist**:289 - [ ] All DOIs verified with verify_citations.py290 - [ ] Citations formatted consistently291 - [ ] PRISMA flow diagram included (for systematic reviews)292 - [ ] Search methodology fully documented293 - [ ] Inclusion/exclusion criteria clearly stated294 - [ ] Results organized thematically (not study-by-study)295 - [ ] Quality assessment completed296 - [ ] Limitations acknowledged297 - [ ] References complete and accurate298 - [ ] PDF generates without errors299300## Database-Specific Search Guidance301302### PubMed / PubMed Central303304Access via `gget` skill:305```bash306# Search PubMed307gget search pubmed "CRISPR gene editing" -l 100308309# Search with filters310# Use PubMed Advanced Search Builder to construct complex queries311# Then execute via gget or direct Entrez API312```313314**Search tips**:315- Use MeSH terms: `"sickle cell disease"[MeSH]`316- Field tags: `[Title]`, `[Title/Abstract]`, `[Author]`317- Date filters: `2020:2024[Publication Date]`318- Boolean operators: AND, OR, NOT319- See MeSH browser: https://meshb.nlm.nih.gov/search320321### bioRxiv / medRxiv322323Access via `gget` skill:324```bash325gget search biorxiv "CRISPR sickle cell" -l 50326```327328**Important considerations**:329- Preprints are not peer-reviewed330- Verify findings with caution331- Check if preprint has been published (CrossRef)332- Note preprint version and date333334### arXiv335336Access via direct API or WebFetch:337```python338# Example search categories:339# q-bio.QM (Quantitative Methods)340# q-bio.GN (Genomics)341# q-bio.MN (Molecular Networks)342# cs.LG (Machine Learning)343# stat.ML (Machine Learning Statistics)344345# Search format: category AND terms346search_query = "cat:q-bio.QM AND ti:\"single cell sequencing\""347```348349### Semantic Scholar350351Access via direct API (requires API key, or use free tier):352- 200M+ papers across all fields353- Excellent for cross-disciplinary searches354- Provides citation graphs and paper recommendations355- Use for finding highly influential papers356357### Specialized Biomedical Databases358359Use appropriate skills:360- **ChEMBL**: `bioservices` skill for chemical bioactivity361- **UniProt**: `gget` or `bioservices` skill for protein information362- **KEGG**: `bioservices` skill for pathways and genes363- **COSMIC**: `gget` skill for cancer mutations364- **AlphaFold**: `gget alphafold` for protein structures365- **PDB**: `gget` or direct API for experimental structures366367### Citation Chaining368369Expand search via citation networks:3703711. **Forward citations** (papers citing key papers):372 - Use Google Scholar "Cited by"373 - Use Semantic Scholar or OpenAlex APIs374 - Identifies newer research building on seminal work3753762. **Backward citations** (references from key papers):377 - Extract references from included papers378 - Identify highly cited foundational work379 - Find papers cited by multiple included studies380381## Citation Style Guide382383Detailed formatting guidelines are in `references/citation_styles.md`. Quick reference:384385### APA (7th Edition)386- In-text: (Smith et al., 2023)387- Reference: Smith, J. D., Johnson, M. L., & Williams, K. R. (2023). Title. *Journal*, *22*(4), 301-318. https://doi.org/10.xxx/yyy388389### Nature390- In-text: Superscript numbers^1,2^391- Reference: Smith, J. D., Johnson, M. L. & Williams, K. R. Title. *Nat. Rev. Drug Discov.* **22**, 301-318 (2023).392393### Vancouver394- In-text: Superscript numbers^1,2^395- Reference: Smith JD, Johnson ML, Williams KR. Title. Nat Rev Drug Discov. 2023;22(4):301-18.396397**Always verify citations** with verify_citations.py before finalizing.398399## Best Practices400401### Prioritizing High-Impact Papers (CRITICAL)402403**Always prioritize influential, highly-cited papers from reputable authors and top venues.** Quality matters more than quantity in literature reviews.404405#### Citation Count Thresholds406407Use citation counts to identify the most impactful papers:408409| Paper Age | Citation Threshold | Classification |410|-----------|-------------------|----------------|411| 0-3 years | 20+ citations | Noteworthy |412| 0-3 years | 100+ citations | Highly Influential |413| 3-7 years | 100+ citations | Significant |414| 3-7 years | 500+ citations | Landmark Paper |415| 7+ years | 500+ citations | Seminal Work |416| 7+ years | 1000+ citations | Foundational |417418#### Journal and Venue Tiers419420Prioritize papers from higher-tier venues:421422- **Tier 1 (Always Prefer):** Nature, Science, Cell, NEJM, Lancet, JAMA, PNAS, Nature Medicine, Nature Biotechnology423- **Tier 2 (Strong Preference):** High-impact specialized journals (IF>10), top conferences (NeurIPS, ICML for ML/AI)424- **Tier 3 (Include When Relevant):** Respected specialized journals (IF 5-10)425- **Tier 4 (Use Sparingly):** Lower-impact peer-reviewed venues426427#### Author Reputation Assessment428429Prefer papers from:430- **Senior researchers** with high h-index (>40 in established fields)431- **Leading research groups** at recognized institutions (Harvard, Stanford, MIT, Oxford, etc.)432- **Authors with multiple Tier-1 publications** in the relevant field433- **Researchers with recognized expertise** (awards, editorial positions, society fellows)434435#### Identifying Seminal Papers436437For any topic, identify foundational work by:4381. **High citation count** (typically 500+ for papers 5+ years old)4392. **Frequently cited by other included studies** (appears in many reference lists)4403. **Published in Tier-1 venues** (Nature, Science, Cell family)4414. **Written by field pioneers** (often cited as establishing concepts)442443### Search Strategy4441. **Use multiple databases** (minimum 3): Ensures comprehensive coverage4452. **Include preprint servers**: Captures latest unpublished findings4463. **Document everything**: Search strings, dates, result counts for reproducibility4474. **Test and refine**: Run pilot searches, review results, adjust search terms4485. **Sort by citations**: When available, sort search results by citation count to surface influential work first449450### Screening and Selection4511. **Use clear criteria**: Document inclusion/exclusion criteria before screening4522. **Screen systematically**: Title → Abstract → Full text4533. **Document exclusions**: Record reasons for excluding studies4544. **Consider dual screening**: For systematic reviews, have two reviewers screen independently4555. **Prioritize Tier-1 venues**: Include all relevant papers from top venues before considering lower-tier sources456457### Synthesis4581. **Organize thematically**: Group by themes, NOT by individual studies4592. **Synthesize across studies**: Compare, contrast, identify patterns4603. **Be critical**: Evaluate quality and consistency of evidence4614. **Identify gaps**: Note what's missing or understudied4625. **Lead with high-impact work**: Start each theme with the most influential/cited papers463464### Quality and Reproducibility4651. **Assess study quality**: Use appropriate quality assessment tools4662. **Verify all citations**: Run verify_citations.py script4673. **Document methodology**: Provide enough detail for others to reproduce4684. **Follow guidelines**: Use PRISMA for systematic reviews469470### Writing4711. **Be objective**: Present evidence fairly, acknowledge limitations4722. **Be systematic**: Follow structured template4733. **Be specific**: Include numbers, statistics, effect sizes where available4744. **Be clear**: Use clear headings, logical flow, thematic organization4755. **Cite impact indicators**: When relevant, mention citation counts and venue prestige476477## Common Pitfalls to Avoid4784791. **Single database search**: Misses relevant papers; always search multiple databases4802. **No search documentation**: Makes review irreproducible; document all searches4813. **Study-by-study summary**: Lacks synthesis; organize thematically instead4824. **Unverified citations**: Leads to errors; always run verify_citations.py4835. **Too broad search**: Yields thousands of irrelevant results; refine with specific terms4846. **Too narrow search**: Misses relevant papers; include synonyms and related terms4857. **Ignoring preprints**: Misses latest findings; include bioRxiv, medRxiv, arXiv4868. **No quality assessment**: Treats all evidence equally; assess and report quality4879. **Publication bias**: Only positive results published; note potential bias48810. **Outdated search**: Field evolves rapidly; clearly state search date489490## Example Workflow491492Complete workflow for a biomedical literature review:493494```bash495# 1. Create review document from template496cp assets/review_template.md crispr_sickle_cell_review.md497498# 2. Search multiple databases using appropriate skills499# - Use gget skill for PubMed, bioRxiv500# - Use direct API access for arXiv, Semantic Scholar501# - Export results in JSON format502503# 3. Aggregate and process results504python scripts/search_databases.py combined_results.json \505 --deduplicate \506 --rank citations \507 --year-start 2015 \508 --year-end 2024 \509 --format markdown \510 --output search_results.md \511 --summary512513# 4. Screen results and extract data514# - Manually screen titles, abstracts, full texts515# - Extract key data into the review document516# - Organize by themes517518# 5. Write the review following template structure519# - Introduction with clear objectives520# - Detailed methodology section521# - Results organized thematically522# - Critical discussion523# - Clear conclusions524525# 6. Verify all citations526python scripts/verify_citations.py crispr_sickle_cell_review.md527528# Review the citation report529cat crispr_sickle_cell_review_citation_report.json530531# Fix any failed citations and re-verify532python scripts/verify_citations.py crispr_sickle_cell_review.md533534# 7. Generate professional PDF535python scripts/generate_pdf.py crispr_sickle_cell_review.md \536 --citation-style nature \537 --output crispr_sickle_cell_review.pdf538539# 8. Review final PDF and markdown outputs540```541542## Integration with Other Skills543544This skill works seamlessly with other scientific skills:545546### Database Access Skills547- **gget**: PubMed, bioRxiv, COSMIC, AlphaFold, Ensembl, UniProt548- **bioservices**: ChEMBL, KEGG, Reactome, UniProt, PubChem549- **datacommons-client**: Demographics, economics, health statistics550551### Analysis Skills552- **pydeseq2**: RNA-seq differential expression (for methods sections)553- **scanpy**: Single-cell analysis (for methods sections)554- **anndata**: Single-cell data (for methods sections)555- **biopython**: Sequence analysis (for background sections)556557### Visualization Skills558- **matplotlib**: Generate figures and plots for review559- **seaborn**: Statistical visualizations560561### Writing Skills562- **brand-guidelines**: Apply institutional branding to PDF563- **internal-comms**: Adapt review for different audiences564- **venue-templates**: Access venue-specific writing style guides when preparing reviews for publication565566### Venue-Specific Writing Styles567568When preparing a literature review for a specific journal, consult the **venue-templates** skill for writing style guidance:569- `venue_writing_styles.md`: Master style comparison across venues570- `nature_science_style.md`: Nature/Science flowing abstract style, story-driven structure571- `cell_press_style.md`: Cell Press graphical abstracts, Highlights format572- `medical_journal_styles.md`: NEJM/Lancet/JAMA structured abstracts, PRISMA compliance573574These guides help adapt your review's tone, abstract format, and structure to match the target venue's expectations.575576## Resources577578### Bundled Resources579580**Scripts:**581- `scripts/verify_citations.py`: Verify DOIs and generate formatted citations582- `scripts/generate_pdf.py`: Convert markdown to professional PDF583- `scripts/search_databases.py`: Process, deduplicate, and format search results584585**References:**586- `references/citation_styles.md`: Detailed citation formatting guide (APA, Nature, Vancouver, Chicago, IEEE)587- `references/database_strategies.md`: Comprehensive database search strategies588589**Assets:**590- `assets/review_template.md`: Complete literature review template with all sections591592### External Resources593594**Guidelines:**595- PRISMA (Systematic Reviews): http://www.prisma-statement.org/596- Cochrane Handbook: https://training.cochrane.org/handbook597- AMSTAR 2 (Review Quality): https://amstar.ca/598599**Tools:**600- MeSH Browser: https://meshb.nlm.nih.gov/search601- PubMed Advanced Search: https://pubmed.ncbi.nlm.nih.gov/advanced/602- Boolean Search Guide: https://www.ncbi.nlm.nih.gov/books/NBK3827/603604**Citation Styles:**605- APA Style: https://apastyle.apa.org/606- Nature Portfolio: https://www.nature.com/nature-portfolio/editorial-policies/reporting-standards607- NLM/Vancouver: https://www.nlm.nih.gov/bsd/uniform_requirements.html608609## Dependencies610611### Required Python Packages612```bash613pip install requests # For citation verification614```615616### Required System Tools617```bash618# For PDF generation619brew install pandoc # macOS620apt-get install pandoc # Linux621622# For LaTeX (PDF generation)623brew install --cask mactex # macOS624apt-get install texlive-xetex # Linux625```626627Check dependencies:628```bash629python scripts/generate_pdf.py --check-deps630```631632## Summary633634This literature-review skill provides:6356361. **Systematic methodology** following academic best practices6372. **Multi-database integration** via existing scientific skills6383. **Citation verification** ensuring accuracy and credibility6394. **Professional output** in markdown and PDF formats6405. **Comprehensive guidance** covering the entire review process6416. **Quality assurance** with verification and validation tools6427. **Reproducibility** through detailed documentation requirements643644Conduct thorough, rigorous literature reviews that meet academic standards and provide comprehensive synthesis of current knowledge in any domain.