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.
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)
Best Practices
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 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
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
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
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
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
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---2author: luo-kai3name: literature-review-24description: 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.).5allowed-tools: Read Write Edit Bash6license: MIT license7metadata:8 source: https://skillmd.com/skills/luokai0/literature-review-29 skill-author: K-Dense Inc.10---1112# Literature Review1314## Overview1516Conduct 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.1718This 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.1920## When to Use This Skill2122Use this skill when:23- Conducting a systematic literature review for research or publication24- Synthesizing current knowledge on a specific topic across multiple sources25- Performing meta-analysis or scoping reviews26- Writing the literature review section of a research paper or thesis27- Investigating the state of the art in a research domain28- Identifying research gaps and future directions29- Requiring verified citations and professional formatting3031## Visual Enhancement with Scientific Schematics3233**⚠️ MANDATORY: Every literature review MUST include at least 1-2 AI-generated figures using the scientific-schematics skill.**3435This is not optional. Literature reviews without visual elements are incomplete. Before finalizing any document:361. Generate at minimum ONE schematic or diagram (e.g., PRISMA flow diagram for systematic reviews)372. Prefer 2-3 figures for comprehensive reviews (search strategy flowchart, thematic synthesis diagram, conceptual framework)3839**How to generate figures:**40- Use the **scientific-schematics** skill to generate AI-powered publication-quality diagrams41- Simply describe your desired diagram in natural language42- Nano Banana Pro will automatically generate, review, and refine the schematic4344**How to generate schematics:**45```bash46python scripts/generate_schematic.py "your diagram description" -o figures/output.png47```4849The AI will automatically:50- Create publication-quality images with proper formatting51- Review and refine through multiple iterations52- Ensure accessibility (colorblind-friendly, high contrast)53- Save outputs in the figures/ directory5455**When to add schematics:**56- PRISMA flow diagrams for systematic reviews57- Literature search strategy flowcharts58- Thematic synthesis diagrams59- Research gap visualization maps60- Citation network diagrams61- Conceptual framework illustrations62- Any complex concept that benefits from visualization6364For detailed guidance on creating schematics, refer to the scientific-schematics skill documentation.6566---6768## Core Workflow6970Literature reviews follow a structured, multi-phase workflow:7172### Phase 1: Planning and Scoping73741. **Define Research Question**: Use PICO framework (Population, Intervention, Comparison, Outcome) for clinical/biomedical reviews75 - Example: "What is the efficacy of CRISPR-Cas9 (I) for treating sickle cell disease (P) compared to standard care (C)?"76772. **Establish Scope and Objectives**:78 - Define clear, specific research questions79 - Determine review type (narrative, systematic, scoping, meta-analysis)80 - Set boundaries (time period, geographic scope, study types)81823. **Develop Search Strategy**:83 - Identify 2-4 main concepts from research question84 - List synonyms, abbreviations, and related terms for each concept85 - Plan Boolean operators (AND, OR, NOT) to combine terms86 - Select minimum 3 complementary databases87884. **Set Inclusion/Exclusion Criteria**:89 - Date range (e.g., last 10 years: 2015-2024)90 - Language (typically English, or specify multilingual)91 - Publication types (peer-reviewed, preprints, reviews)92 - Study designs (RCTs, observational, in vitro, etc.)93 - Document all criteria clearly9495### Phase 2: Systematic Literature Search96971. **Multi-Database Search**:9899 Select databases appropriate for the domain:100101 **Biomedical & Life Sciences:**102 - Use `gget` skill: `gget search pubmed "search terms"` for PubMed/PMC103 - Use `gget` skill: `gget search biorxiv "search terms"` for preprints104 - Use `bioservices` skill for ChEMBL, KEGG, UniProt, etc.105106 **General Scientific Literature:**107 - Search arXiv via direct API (preprints in physics, math, CS, q-bio)108 - Search Semantic Scholar via API (200M+ papers, cross-disciplinary)109 - Use Google Scholar for comprehensive coverage (manual or careful scraping)110111 **Specialized Databases:**112 - Use `gget alphafold` for protein structures113 - Use `gget cosmic` for cancer genomics114 - Use `datacommons-client` for demographic/statistical data115 - Use specialized databases as appropriate for the domain1161172. **Document Search Parameters**:118 ```markdown119 ## Search Strategy120121 ### Database: PubMed122 - **Date searched**: 2024-10-25123 - **Date range**: 2015-01-01 to 2024-10-25124 - **Search string**:125 ```126 ("CRISPR"[Title] OR "Cas9"[Title])127 AND ("sickle cell"[MeSH] OR "SCD"[Title/Abstract])128 AND 2015:2024[Publication Date]129 ```130 - **Results**: 247 articles131 ```132133 Repeat for each database searched.1341353. **Export and Aggregate Results**:136 - Export results in JSON format from each database137 - Combine all results into a single file138 - Use `scripts/search_databases.py` for post-processing:139 ```bash140 python search_databases.py combined_results.json \141 --deduplicate \142 --format markdown \143 --output aggregated_results.md144 ```145146### Phase 3: Screening and Selection1471481. **Deduplication**:149 ```bash150 python search_databases.py results.json --deduplicate --output unique_results.json151 ```152 - Removes duplicates by DOI (primary) or title (fallback)153 - Document number of duplicates removed1541552. **Title Screening**:156 - Review all titles against inclusion/exclusion criteria157 - Exclude obviously irrelevant studies158 - Document number excluded at this stage1591603. **Abstract Screening**:161 - Read abstracts of remaining studies162 - Apply inclusion/exclusion criteria rigorously163 - Document reasons for exclusion1641654. **Full-Text Screening**:166 - Obtain full texts of remaining studies167 - Conduct detailed review against all criteria168 - Document specific reasons for exclusion169 - Record final number of included studies1701715. **Create PRISMA Flow Diagram**:172 ```173 Initial search: n = X174 ├─ After deduplication: n = Y175 ├─ After title screening: n = Z176 ├─ After abstract screening: n = A177 └─ Included in review: n = B178 ```179180### Phase 4: Data Extraction and Quality Assessment1811821. **Extract Key Data** from each included study:183 - Study metadata (authors, year, journal, DOI)184 - Study design and methods185 - Sample size and population characteristics186 - Key findings and results187 - Limitations noted by authors188 - Funding sources and conflicts of interest1891902. **Assess Study Quality**:191 - **For RCTs**: Use Cochrane Risk of Bias tool192 - **For observational studies**: Use Newcastle-Ottawa Scale193 - **For systematic reviews**: Use AMSTAR 2194 - Rate each study: High, Moderate, Low, or Very Low quality195 - Consider excluding very low-quality studies1961973. **Organize by Themes**:198 - Identify 3-5 major themes across studies199 - Group studies by theme (studies may appear in multiple themes)200 - Note patterns, consensus, and controversies201202### Phase 5: Synthesis and Analysis2032041. **Create Review Document** from template:205 ```bash206 cp assets/review_template.md my_literature_review.md207 ```2082092. **Write Thematic Synthesis** (NOT study-by-study summaries):210 - Organize Results section by themes or research questions211 - Synthesize findings across multiple studies within each theme212 - Compare and contrast different approaches and results213 - Identify consensus areas and points of controversy214 - Highlight the strongest evidence215216 Example structure:217 ```markdown218 #### 3.3.1 Theme: CRISPR Delivery Methods219220 Multiple delivery approaches have been investigated for therapeutic221 gene editing. Viral vectors (AAV) were used in 15 studies^1-15^ and222 showed high transduction efficiency (65-85%) but raised immunogenicity223 concerns^3,7,12^. In contrast, lipid nanoparticles demonstrated lower224 efficiency (40-60%) but improved safety profiles^16-23^.225 ```2262273. **Critical Analysis**:228 - Evaluate methodological strengths and limitations across studies229 - Assess quality and consistency of evidence230 - Identify knowledge gaps and methodological gaps231 - Note areas requiring future research2322334. **Write Discussion**:234 - Interpret findings in broader context235 - Discuss clinical, practical, or research implications236 - Acknowledge limitations of the review itself237 - Compare with previous reviews if applicable238 - Propose specific future research directions239240### Phase 6: Citation Verification241242**CRITICAL**: All citations must be verified for accuracy before final submission.2432441. **Verify All DOIs**:245 ```bash246 python scripts/verify_citations.py my_literature_review.md247 ```248249 This script:250 - Extracts all DOIs from the document251 - Verifies each DOI resolves correctly252 - Retrieves metadata from CrossRef253 - Generates verification report254 - Outputs properly formatted citations2552562. **Review Verification Report**:257 - Check for any failed DOIs258 - Verify author names, titles, and publication details match259 - Correct any errors in the original document260 - Re-run verification until all citations pass2612623. **Format Citations Consistently**:263 - Choose one citation style and use throughout (see `references/citation_styles.md`)264 - Common styles: APA, Nature, Vancouver, Chicago, IEEE265 - Use verification script output to format citations correctly266 - Ensure in-text citations match reference list format267268### Phase 7: Document Generation2692701. **Generate PDF**:271 ```bash272 python scripts/generate_pdf.py my_literature_review.md \273 --citation-style apa \274 --output my_review.pdf275 ```276277 Options:278 - `--citation-style`: apa, nature, chicago, vancouver, ieee279 - `--no-toc`: Disable table of contents280 - `--no-numbers`: Disable section numbering281 - `--check-deps`: Check if pandoc/xelatex are installed2822832. **Review Final Output**:284 - Check PDF formatting and layout285 - Verify all sections are present286 - Ensure citations render correctly287 - Check that figures/tables appear properly288 - Verify table of contents is accurate2892903. **Quality Checklist**:291 - [ ] All DOIs verified with verify_citations.py292 - [ ] Citations formatted consistently293 - [ ] PRISMA flow diagram included (for systematic reviews)294 - [ ] Search methodology fully documented295 - [ ] Inclusion/exclusion criteria clearly stated296 - [ ] Results organized thematically (not study-by-study)297 - [ ] Quality assessment completed298 - [ ] Limitations acknowledged299 - [ ] References complete and accurate300 - [ ] PDF generates without errors301302## Database-Specific Search Guidance303304### PubMed / PubMed Central305306Access via `gget` skill:307```bash308# Search PubMed309gget search pubmed "CRISPR gene editing" -l 100310311# Search with filters312# Use PubMed Advanced Search Builder to construct complex queries313# Then execute via gget or direct Entrez API314```315316**Search tips**:317- Use MeSH terms: `"sickle cell disease"[MeSH]`318- Field tags: `[Title]`, `[Title/Abstract]`, `[Author]`319- Date filters: `2020:2024[Publication Date]`320- Boolean operators: AND, OR, NOT321- See MeSH browser: https://meshb.nlm.nih.gov/search322323### bioRxiv / medRxiv324325Access via `gget` skill:326```bash327gget search biorxiv "CRISPR sickle cell" -l 50328```329330**Important considerations**:331- Preprints are not peer-reviewed332- Verify findings with caution333- Check if preprint has been published (CrossRef)334- Note preprint version and date335336### arXiv337338Access via direct API or WebFetch:339```python340# Example search categories:341# q-bio.QM (Quantitative Methods)342# q-bio.GN (Genomics)343# q-bio.MN (Molecular Networks)344# cs.LG (Machine Learning)345# stat.ML (Machine Learning Statistics)346347# Search format: category AND terms348search_query = "cat:q-bio.QM AND ti:\"single cell sequencing\""349```350351### Semantic Scholar352353Access via direct API (requires API key, or use free tier):354- 200M+ papers across all fields355- Excellent for cross-disciplinary searches356- Provides citation graphs and paper recommendations357- Use for finding highly influential papers358359### Specialized Biomedical Databases360361Use appropriate skills:362- **ChEMBL**: `bioservices` skill for chemical bioactivity363- **UniProt**: `gget` or `bioservices` skill for protein information364- **KEGG**: `bioservices` skill for pathways and genes365- **COSMIC**: `gget` skill for cancer mutations366- **AlphaFold**: `gget alphafold` for protein structures367- **PDB**: `gget` or direct API for experimental structures368369### Citation Chaining370371Expand search via citation networks:3723731. **Forward citations** (papers citing key papers):374 - Use Google Scholar "Cited by"375 - Use Semantic Scholar or OpenAlex APIs376 - Identifies newer research building on seminal work3773782. **Backward citations** (references from key papers):379 - Extract references from included papers380 - Identify highly cited foundational work381 - Find papers cited by multiple included studies382383## Citation Style Guide384385Detailed formatting guidelines are in `references/citation_styles.md`. Quick reference:386387### APA (7th Edition)388- In-text: (Smith et al., 2023)389- Reference: Smith, J. D., Johnson, M. L., & Williams, K. R. (2023). Title. *Journal*, *22*(4), 301-318. https://doi.org/10.xxx/yyy390391### Nature392- In-text: Superscript numbers^1,2^393- Reference: Smith, J. D., Johnson, M. L. & Williams, K. R. Title. *Nat. Rev. Drug Discov.* **22**, 301-318 (2023).394395### Vancouver396- In-text: Superscript numbers^1,2^397- Reference: Smith JD, Johnson ML, Williams KR. Title. Nat Rev Drug Discov. 2023;22(4):301-18.398399**Always verify citations** with verify_citations.py before finalizing.400401### 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## Best Practices444445### Search Strategy4461. **Use multiple databases** (minimum 3): Ensures comprehensive coverage4472. **Include preprint servers**: Captures latest unpublished findings4483. **Document everything**: Search strings, dates, result counts for reproducibility4494. **Test and refine**: Run pilot searches, review results, adjust search terms4505. **Sort by citations**: When available, sort search results by citation count to surface influential work first451452### Screening and Selection4531. **Use multiple databases** (minimum 3): Ensures comprehensive coverage4542. **Include preprint servers**: Captures latest unpublished findings4553. **Document everything**: Search strings, dates, result counts for reproducibility4564. **Test and refine**: Run pilot searches, review results, adjust search terms457458### Screening and Selection4591. **Use clear criteria**: Document inclusion/exclusion criteria before screening4602. **Screen systematically**: Title → Abstract → Full text4613. **Document exclusions**: Record reasons for excluding studies4624. **Consider dual screening**: For systematic reviews, have two reviewers screen independently463464### Synthesis4651. **Organize thematically**: Group by themes, NOT by individual studies4662. **Synthesize across studies**: Compare, contrast, identify patterns4673. **Be critical**: Evaluate quality and consistency of evidence4684. **Identify gaps**: Note what's missing or understudied469470### Quality and Reproducibility4711. **Assess study quality**: Use appropriate quality assessment tools4722. **Verify all citations**: Run verify_citations.py script4733. **Document methodology**: Provide enough detail for others to reproduce4744. **Follow guidelines**: Use PRISMA for systematic reviews475476### Writing4771. **Be objective**: Present evidence fairly, acknowledge limitations4782. **Be systematic**: Follow structured template4793. **Be specific**: Include numbers, statistics, effect sizes where available4804. **Be clear**: Use clear headings, logical flow, thematic organization481482## Common Pitfalls to Avoid4834841. **Single database search**: Misses relevant papers; always search multiple databases4852. **No search documentation**: Makes review irreproducible; document all searches4863. **Study-by-study summary**: Lacks synthesis; organize thematically instead4874. **Unverified citations**: Leads to errors; always run verify_citations.py4885. **Too broad search**: Yields thousands of irrelevant results; refine with specific terms4896. **Too narrow search**: Misses relevant papers; include synonyms and related terms4907. **Ignoring preprints**: Misses latest findings; include bioRxiv, medRxiv, arXiv4918. **No quality assessment**: Treats all evidence equally; assess and report quality4929. **Publication bias**: Only positive results published; note potential bias49310. **Outdated search**: Field evolves rapidly; clearly state search date494495## Example Workflow496497Complete workflow for a biomedical literature review:498499```bash500# 1. Create review document from template501cp assets/review_template.md crispr_sickle_cell_review.md502503# 2. Search multiple databases using appropriate skills504# - Use gget skill for PubMed, bioRxiv505# - Use direct API access for arXiv, Semantic Scholar506# - Export results in JSON format507508# 3. Aggregate and process results509python scripts/search_databases.py combined_results.json \510 --deduplicate \511 --rank citations \512 --year-start 2015 \513 --year-end 2024 \514 --format markdown \515 --output search_results.md \516 --summary517518# 4. Screen results and extract data519# - Manually screen titles, abstracts, full texts520# - Extract key data into the review document521# - Organize by themes522523# 5. Write the review following template structure524# - Introduction with clear objectives525# - Detailed methodology section526# - Results organized thematically527# - Critical discussion528# - Clear conclusions529530# 6. Verify all citations531python scripts/verify_citations.py crispr_sickle_cell_review.md532533# Review the citation report534cat crispr_sickle_cell_review_citation_report.json535536# Fix any failed citations and re-verify537python scripts/verify_citations.py crispr_sickle_cell_review.md538539# 7. Generate professional PDF540python scripts/generate_pdf.py crispr_sickle_cell_review.md \541 --citation-style nature \542 --output crispr_sickle_cell_review.pdf543544# 8. Review final PDF and markdown outputs545```546547## Integration with Other Skills548549This skill works seamlessly with other scientific skills:550551### Database Access Skills552- **gget**: PubMed, bioRxiv, COSMIC, AlphaFold, Ensembl, UniProt553- **bioservices**: ChEMBL, KEGG, Reactome, UniProt, PubChem554- **datacommons-client**: Demographics, economics, health statistics555556### Analysis Skills557- **pydeseq2**: RNA-seq differential expression (for methods sections)558- **scanpy**: Single-cell analysis (for methods sections)559- **anndata**: Single-cell data (for methods sections)560- **biopython**: Sequence analysis (for background sections)561562### Visualization Skills563- **matplotlib**: Generate figures and plots for review564- **seaborn**: Statistical visualizations565566### Writing Skills567- **brand-guidelines**: Apply institutional branding to PDF568- **internal-comms**: Adapt review for different audiences569570## Resources571572### Bundled Resources573574**Scripts:**575- `scripts/verify_citations.py`: Verify DOIs and generate formatted citations576- `scripts/generate_pdf.py`: Convert markdown to professional PDF577- `scripts/search_databases.py`: Process, deduplicate, and format search results578579**References:**580- `references/citation_styles.md`: Detailed citation formatting guide (APA, Nature, Vancouver, Chicago, IEEE)581- `references/database_strategies.md`: Comprehensive database search strategies582583**Assets:**584- `assets/review_template.md`: Complete literature review template with all sections585586### External Resources587588**Guidelines:**589- PRISMA (Systematic Reviews): http://www.prisma-statement.org/590- Cochrane Handbook: https://training.cochrane.org/handbook591- AMSTAR 2 (Review Quality): https://amstar.ca/592593**Tools:**594- MeSH Browser: https://meshb.nlm.nih.gov/search595- PubMed Advanced Search: https://pubmed.ncbi.nlm.nih.gov/advanced/596- Boolean Search Guide: https://www.ncbi.nlm.nih.gov/books/NBK3827/597598**Citation Styles:**599- APA Style: https://apastyle.apa.org/600- Nature Portfolio: https://www.nature.com/nature-portfolio/editorial-policies/reporting-standards601- NLM/Vancouver: https://www.nlm.nih.gov/bsd/uniform_requirements.html602603## Dependencies604605### Required Python Packages606```bash607pip install requests # For citation verification608```609610### Required System Tools611```bash612# For PDF generation613brew install pandoc # macOS614apt-get install pandoc # Linux615616# For LaTeX (PDF generation)617brew install --cask mactex # macOS618apt-get install texlive-xetex # Linux619```620621Check dependencies:622```bash623python scripts/generate_pdf.py --check-deps624```625626## Summary627628This literature-review skill provides:6296301. **Systematic methodology** following academic best practices6312. **Multi-database integration** via existing scientific skills6323. **Citation verification** ensuring accuracy and credibility6334. **Professional output** in markdown and PDF formats6345. **Comprehensive guidance** covering the entire review process6356. **Quality assurance** with verification and validation tools6367. **Reproducibility** through detailed documentation requirements637638Conduct thorough, rigorous literature reviews that meet academic standards and provide comprehensive synthesis of current knowledge in any domain.639