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 uses the parallel-web skill (parallel-cli search) as the primary web search tool for broad academic literature discovery, supplemented by specialized database access skills (gget, bioservices, datacommons-client). It 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
- Use the parallel-web skill (
parallel-cli search) for initial scoping to quickly gauge the landscape before formal database searches
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. Always start with parallel-web for broad academic coverage, then supplement with domain-specific databases.
Web-Based Academic Search (parallel-web skill — START HERE):
- Use
parallel-cli search with academic domain filtering for broad scholarly coverage
- Run two searches: academic-focused + general to catch all relevant sources
# Academic-focused search across scholarly sources
parallel-cli search "your research topic" -q "keyword1" -q "keyword2" \
--json --max-results 10 --excerpt-max-chars-total 27000 \
--include-domains "scholar.google.com,arxiv.org,pubmed.ncbi.nlm.nih.gov,semanticscholar.org,biorxiv.org,medrxiv.org,ncbi.nlm.nih.gov,nature.com,science.org,ieee.org,acm.org,springer.com,wiley.com,cell.com,pnas.org,nih.gov" \
-o sources/litreview_<topic>-academic.json
# General search for supplementary sources
parallel-cli search "your research topic" -q "keyword1" -q "keyword2" \
--json --max-results 10 --excerpt-max-chars-total 27000 \
-o sources/litreview_<topic>-general.json
- Use
parallel-cli extract to fetch full content from specific paper URLs or PDFs found in search results
parallel-cli extract "https://arxiv.org/abs/XXXX.XXXXX" --json
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
parallel-cli search to find papers citing a specific work:parallel-cli search "papers citing [Author et al. Year] [paper title]" \
-q "citing" -q "[key author]" \
--json --max-results 10 --excerpt-max-chars-total 27000 \
--include-domains "scholar.google.com,semanticscholar.org,arxiv.org,pubmed.ncbi.nlm.nih.gov" \
-o sources/litreview_forward_citations.json
- Use Google Scholar "Cited by"
- Use Semantic Scholar or OpenAlex APIs
- Identifies newer research building on seminal work
Backward citations (references from key papers):
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
- Start with parallel-web: Use
parallel-cli search with academic domains for initial broad coverage before querying specialized databases
- Use multiple databases (minimum 3): Ensures comprehensive coverage — parallel-web counts as one source
- Include preprint servers: Captures latest unpublished findings
- Document everything: Search strings, dates, result counts for reproducibility — save all parallel-cli output to
sources/
- 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
- Use parallel-cli extract: Fetch full content from promising URLs found during search to verify relevance before full-text screening
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. Start with parallel-web for broad academic search
parallel-cli search "CRISPR Cas9 sickle cell disease gene therapy efficacy" \
-q "CRISPR" -q "sickle cell" -q "gene therapy" \
--json --max-results 10 --excerpt-max-chars-total 27000 \
--include-domains "scholar.google.com,arxiv.org,pubmed.ncbi.nlm.nih.gov,semanticscholar.org,biorxiv.org,nature.com,science.org,cell.com,pnas.org,nih.gov" \
-o sources/litreview_crispr_scd-academic.json
parallel-cli search "CRISPR sickle cell disease clinical trials treatment" \
-q "CRISPR" -q "sickle cell" \
--json --max-results 10 --excerpt-max-chars-total 27000 \
-o sources/litreview_crispr_scd-general.json
# 3. Search specialized databases using appropriate skills
# - Use gget skill for PubMed, bioRxiv
# - Use direct API access for arXiv, Semantic Scholar
# - Export results in JSON format
# 4. Aggregate and process results (combine parallel-cli + database 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
# 5. Screen results and extract data
# - Use parallel-cli extract to fetch full content from promising URLs
# - Manually screen titles, abstracts, full texts
# - Extract key data into the review document
# - Organize by themes
# 6. Write the review following template structure
# - Introduction with clear objectives
# - Detailed methodology section
# - Results organized thematically
# - Critical discussion
# - Clear conclusions
# 7. 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
# 8. Generate professional PDF
python scripts/generate_pdf.py crispr_sickle_cell_review.md \
--citation-style nature \
--output crispr_sickle_cell_review.pdf
# 9. Review final PDF and markdown outputs
Integration with Other Skills
This skill works seamlessly with other scientific skills:
Web Search & Extraction (parallel-web skill — PRIMARY)
- parallel-cli search: Broad academic and general web search with domain filtering — use for initial scoping, finding papers, citation chaining, and supplementary searches
- parallel-cli extract: Fetch full content from paper URLs, journal websites, and preprint servers — use for reading abstracts, extracting reference lists, and verifying paper details
- parallel-cli search --include-domains: Academic-focused search across scholarly domains (arxiv.org, pubmed, nature.com, etc.)
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 CLI Tools
# parallel-cli (PRIMARY — for web search and URL extraction)
curl -fsSL https://parallel.ai/install.sh | bash
# Or: uv tool install "parallel-web-tools[cli]"
# Authenticate: parallel-cli auth
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
- Parallel-web powered search using
parallel-cli search for fast, broad academic literature discovery with scholarly domain filtering
- Multi-database integration via existing scientific skills (gget, bioservices, datacommons-client)
- 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 Bash5license: MIT license6metadata:7 source: https://skillmd.com/skills/zuoguyoupan2023/literature-review8 version: "1.0"9 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 uses the **parallel-web skill** (`parallel-cli search`) as the primary web search tool for broad academic literature discovery, supplemented by specialized database access skills (gget, bioservices, datacommons-client). It 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 databases87 - **Use the parallel-web skill (`parallel-cli search`) for initial scoping** to quickly gauge the landscape before formal database searches88894. **Set Inclusion/Exclusion Criteria**:90 - Date range (e.g., last 10 years: 2015-2024)91 - Language (typically English, or specify multilingual)92 - Publication types (peer-reviewed, preprints, reviews)93 - Study designs (RCTs, observational, in vitro, etc.)94 - Document all criteria clearly9596### Phase 2: Systematic Literature Search97981. **Multi-Database Search**:99100 Select databases appropriate for the domain. **Always start with parallel-web for broad academic coverage**, then supplement with domain-specific databases.101102 **Web-Based Academic Search (parallel-web skill — START HERE):**103 - Use `parallel-cli search` with academic domain filtering for broad scholarly coverage104 - Run two searches: academic-focused + general to catch all relevant sources105 ```bash106 # Academic-focused search across scholarly sources107 parallel-cli search "your research topic" -q "keyword1" -q "keyword2" \108 --json --max-results 10 --excerpt-max-chars-total 27000 \109 --include-domains "scholar.google.com,arxiv.org,pubmed.ncbi.nlm.nih.gov,semanticscholar.org,biorxiv.org,medrxiv.org,ncbi.nlm.nih.gov,nature.com,science.org,ieee.org,acm.org,springer.com,wiley.com,cell.com,pnas.org,nih.gov" \110 -o sources/litreview_<topic>-academic.json111112 # General search for supplementary sources113 parallel-cli search "your research topic" -q "keyword1" -q "keyword2" \114 --json --max-results 10 --excerpt-max-chars-total 27000 \115 -o sources/litreview_<topic>-general.json116 ```117 - Use `parallel-cli extract` to fetch full content from specific paper URLs or PDFs found in search results118 ```bash119 parallel-cli extract "https://arxiv.org/abs/XXXX.XXXXX" --json120 ```121122 **Biomedical & Life Sciences:**123 - Use `gget` skill: `gget search pubmed "search terms"` for PubMed/PMC124 - Use `gget` skill: `gget search biorxiv "search terms"` for preprints125 - Use `bioservices` skill for ChEMBL, KEGG, UniProt, etc.126127 **General Scientific Literature:**128 - Search arXiv via direct API (preprints in physics, math, CS, q-bio)129 - Search Semantic Scholar via API (200M+ papers, cross-disciplinary)130 - Use Google Scholar for comprehensive coverage (manual or careful scraping)131132 **Specialized Databases:**133 - Use `gget alphafold` for protein structures134 - Use `gget cosmic` for cancer genomics135 - Use `datacommons-client` for demographic/statistical data136 - Use specialized databases as appropriate for the domain1371382. **Document Search Parameters**:139 ```markdown140 ## Search Strategy141142 ### Database: PubMed143 - **Date searched**: 2024-10-25144 - **Date range**: 2015-01-01 to 2024-10-25145 - **Search string**:146 ```147 ("CRISPR"[Title] OR "Cas9"[Title])148 AND ("sickle cell"[MeSH] OR "SCD"[Title/Abstract])149 AND 2015:2024[Publication Date]150 ```151 - **Results**: 247 articles152 ```153154 Repeat for each database searched.1551563. **Export and Aggregate Results**:157 - Export results in JSON format from each database158 - Combine all results into a single file159 - Use `scripts/search_databases.py` for post-processing:160 ```bash161 python search_databases.py combined_results.json \162 --deduplicate \163 --format markdown \164 --output aggregated_results.md165 ```166167### Phase 3: Screening and Selection1681691. **Deduplication**:170 ```bash171 python search_databases.py results.json --deduplicate --output unique_results.json172 ```173 - Removes duplicates by DOI (primary) or title (fallback)174 - Document number of duplicates removed1751762. **Title Screening**:177 - Review all titles against inclusion/exclusion criteria178 - Exclude obviously irrelevant studies179 - Document number excluded at this stage1801813. **Abstract Screening**:182 - Read abstracts of remaining studies183 - Apply inclusion/exclusion criteria rigorously184 - Document reasons for exclusion1851864. **Full-Text Screening**:187 - Obtain full texts of remaining studies188 - Conduct detailed review against all criteria189 - Document specific reasons for exclusion190 - Record final number of included studies1911925. **Create PRISMA Flow Diagram**:193 ```194 Initial search: n = X195 ├─ After deduplication: n = Y196 ├─ After title screening: n = Z197 ├─ After abstract screening: n = A198 └─ Included in review: n = B199 ```200201### Phase 4: Data Extraction and Quality Assessment2022031. **Extract Key Data** from each included study:204 - Study metadata (authors, year, journal, DOI)205 - Study design and methods206 - Sample size and population characteristics207 - Key findings and results208 - Limitations noted by authors209 - Funding sources and conflicts of interest2102112. **Assess Study Quality**:212 - **For RCTs**: Use Cochrane Risk of Bias tool213 - **For observational studies**: Use Newcastle-Ottawa Scale214 - **For systematic reviews**: Use AMSTAR 2215 - Rate each study: High, Moderate, Low, or Very Low quality216 - Consider excluding very low-quality studies2172183. **Organize by Themes**:219 - Identify 3-5 major themes across studies220 - Group studies by theme (studies may appear in multiple themes)221 - Note patterns, consensus, and controversies222223### Phase 5: Synthesis and Analysis2242251. **Create Review Document** from template:226 ```bash227 cp assets/review_template.md my_literature_review.md228 ```2292302. **Write Thematic Synthesis** (NOT study-by-study summaries):231 - Organize Results section by themes or research questions232 - Synthesize findings across multiple studies within each theme233 - Compare and contrast different approaches and results234 - Identify consensus areas and points of controversy235 - Highlight the strongest evidence236237 Example structure:238 ```markdown239 #### 3.3.1 Theme: CRISPR Delivery Methods240241 Multiple delivery approaches have been investigated for therapeutic242 gene editing. Viral vectors (AAV) were used in 15 studies^1-15^ and243 showed high transduction efficiency (65-85%) but raised immunogenicity244 concerns^3,7,12^. In contrast, lipid nanoparticles demonstrated lower245 efficiency (40-60%) but improved safety profiles^16-23^.246 ```2472483. **Critical Analysis**:249 - Evaluate methodological strengths and limitations across studies250 - Assess quality and consistency of evidence251 - Identify knowledge gaps and methodological gaps252 - Note areas requiring future research2532544. **Write Discussion**:255 - Interpret findings in broader context256 - Discuss clinical, practical, or research implications257 - Acknowledge limitations of the review itself258 - Compare with previous reviews if applicable259 - Propose specific future research directions260261### Phase 6: Citation Verification262263**CRITICAL**: All citations must be verified for accuracy before final submission.2642651. **Verify All DOIs**:266 ```bash267 python scripts/verify_citations.py my_literature_review.md268 ```269270 This script:271 - Extracts all DOIs from the document272 - Verifies each DOI resolves correctly273 - Retrieves metadata from CrossRef274 - Generates verification report275 - Outputs properly formatted citations2762772. **Review Verification Report**:278 - Check for any failed DOIs279 - Verify author names, titles, and publication details match280 - Correct any errors in the original document281 - Re-run verification until all citations pass2822833. **Format Citations Consistently**:284 - Choose one citation style and use throughout (see `references/citation_styles.md`)285 - Common styles: APA, Nature, Vancouver, Chicago, IEEE286 - Use verification script output to format citations correctly287 - Ensure in-text citations match reference list format288289### Phase 7: Document Generation2902911. **Generate PDF**:292 ```bash293 python scripts/generate_pdf.py my_literature_review.md \294 --citation-style apa \295 --output my_review.pdf296 ```297298 Options:299 - `--citation-style`: apa, nature, chicago, vancouver, ieee300 - `--no-toc`: Disable table of contents301 - `--no-numbers`: Disable section numbering302 - `--check-deps`: Check if pandoc/xelatex are installed3033042. **Review Final Output**:305 - Check PDF formatting and layout306 - Verify all sections are present307 - Ensure citations render correctly308 - Check that figures/tables appear properly309 - Verify table of contents is accurate3103113. **Quality Checklist**:312 - [ ] All DOIs verified with verify_citations.py313 - [ ] Citations formatted consistently314 - [ ] PRISMA flow diagram included (for systematic reviews)315 - [ ] Search methodology fully documented316 - [ ] Inclusion/exclusion criteria clearly stated317 - [ ] Results organized thematically (not study-by-study)318 - [ ] Quality assessment completed319 - [ ] Limitations acknowledged320 - [ ] References complete and accurate321 - [ ] PDF generates without errors322323## Database-Specific Search Guidance324325### PubMed / PubMed Central326327Access via `gget` skill:328```bash329# Search PubMed330gget search pubmed "CRISPR gene editing" -l 100331332# Search with filters333# Use PubMed Advanced Search Builder to construct complex queries334# Then execute via gget or direct Entrez API335```336337**Search tips**:338- Use MeSH terms: `"sickle cell disease"[MeSH]`339- Field tags: `[Title]`, `[Title/Abstract]`, `[Author]`340- Date filters: `2020:2024[Publication Date]`341- Boolean operators: AND, OR, NOT342- See MeSH browser: https://meshb.nlm.nih.gov/search343344### bioRxiv / medRxiv345346Access via `gget` skill:347```bash348gget search biorxiv "CRISPR sickle cell" -l 50349```350351**Important considerations**:352- Preprints are not peer-reviewed353- Verify findings with caution354- Check if preprint has been published (CrossRef)355- Note preprint version and date356357### arXiv358359Access via direct API or WebFetch:360```python361# Example search categories:362# q-bio.QM (Quantitative Methods)363# q-bio.GN (Genomics)364# q-bio.MN (Molecular Networks)365# cs.LG (Machine Learning)366# stat.ML (Machine Learning Statistics)367368# Search format: category AND terms369search_query = "cat:q-bio.QM AND ti:\"single cell sequencing\""370```371372### Semantic Scholar373374Access via direct API (requires API key, or use free tier):375- 200M+ papers across all fields376- Excellent for cross-disciplinary searches377- Provides citation graphs and paper recommendations378- Use for finding highly influential papers379380### Specialized Biomedical Databases381382Use appropriate skills:383- **ChEMBL**: `bioservices` skill for chemical bioactivity384- **UniProt**: `gget` or `bioservices` skill for protein information385- **KEGG**: `bioservices` skill for pathways and genes386- **COSMIC**: `gget` skill for cancer mutations387- **AlphaFold**: `gget alphafold` for protein structures388- **PDB**: `gget` or direct API for experimental structures389390### Citation Chaining391392Expand search via citation networks:3933941. **Forward citations** (papers citing key papers):395 - Use `parallel-cli search` to find papers citing a specific work:396 ```bash397 parallel-cli search "papers citing [Author et al. Year] [paper title]" \398 -q "citing" -q "[key author]" \399 --json --max-results 10 --excerpt-max-chars-total 27000 \400 --include-domains "scholar.google.com,semanticscholar.org,arxiv.org,pubmed.ncbi.nlm.nih.gov" \401 -o sources/litreview_forward_citations.json402 ```403 - Use Google Scholar "Cited by"404 - Use Semantic Scholar or OpenAlex APIs405 - Identifies newer research building on seminal work4064072. **Backward citations** (references from key papers):408 - Use `parallel-cli extract` to fetch full text of key papers and extract their reference lists:409 ```bash410 parallel-cli extract "https://doi.org/10.xxxx/yyyy" --json411 ```412 - Extract references from included papers413 - Identify highly cited foundational work414 - Find papers cited by multiple included studies415416## Citation Style Guide417418Detailed formatting guidelines are in `references/citation_styles.md`. Quick reference:419420### APA (7th Edition)421- In-text: (Smith et al., 2023)422- Reference: Smith, J. D., Johnson, M. L., & Williams, K. R. (2023). Title. *Journal*, *22*(4), 301-318. https://doi.org/10.xxx/yyy423424### Nature425- In-text: Superscript numbers^1,2^426- Reference: Smith, J. D., Johnson, M. L. & Williams, K. R. Title. *Nat. Rev. Drug Discov.* **22**, 301-318 (2023).427428### Vancouver429- In-text: Superscript numbers^1,2^430- Reference: Smith JD, Johnson ML, Williams KR. Title. Nat Rev Drug Discov. 2023;22(4):301-18.431432**Always verify citations** with verify_citations.py before finalizing.433434### Prioritizing High-Impact Papers (CRITICAL)435436**Always prioritize influential, highly-cited papers from reputable authors and top venues.** Quality matters more than quantity in literature reviews.437438#### Citation Count Thresholds439440Use citation counts to identify the most impactful papers:441442| Paper Age | Citation Threshold | Classification |443|-----------|-------------------|----------------|444| 0-3 years | 20+ citations | Noteworthy |445| 0-3 years | 100+ citations | Highly Influential |446| 3-7 years | 100+ citations | Significant |447| 3-7 years | 500+ citations | Landmark Paper |448| 7+ years | 500+ citations | Seminal Work |449| 7+ years | 1000+ citations | Foundational |450451#### Journal and Venue Tiers452453Prioritize papers from higher-tier venues:454455- **Tier 1 (Always Prefer):** Nature, Science, Cell, NEJM, Lancet, JAMA, PNAS, Nature Medicine, Nature Biotechnology456- **Tier 2 (Strong Preference):** High-impact specialized journals (IF>10), top conferences (NeurIPS, ICML for ML/AI)457- **Tier 3 (Include When Relevant):** Respected specialized journals (IF 5-10)458- **Tier 4 (Use Sparingly):** Lower-impact peer-reviewed venues459460#### Author Reputation Assessment461462Prefer papers from:463- **Senior researchers** with high h-index (>40 in established fields)464- **Leading research groups** at recognized institutions (Harvard, Stanford, MIT, Oxford, etc.)465- **Authors with multiple Tier-1 publications** in the relevant field466- **Researchers with recognized expertise** (awards, editorial positions, society fellows)467468#### Identifying Seminal Papers469470For any topic, identify foundational work by:4711. **High citation count** (typically 500+ for papers 5+ years old)4722. **Frequently cited by other included studies** (appears in many reference lists)4733. **Published in Tier-1 venues** (Nature, Science, Cell family)4744. **Written by field pioneers** (often cited as establishing concepts)475476## Best Practices477478### Search Strategy4791. **Start with parallel-web**: Use `parallel-cli search` with academic domains for initial broad coverage before querying specialized databases4802. **Use multiple databases** (minimum 3): Ensures comprehensive coverage — parallel-web counts as one source4813. **Include preprint servers**: Captures latest unpublished findings4824. **Document everything**: Search strings, dates, result counts for reproducibility — save all parallel-cli output to `sources/`4835. **Test and refine**: Run pilot searches, review results, adjust search terms4846. **Sort by citations**: When available, sort search results by citation count to surface influential work first4857. **Use parallel-cli extract**: Fetch full content from promising URLs found during search to verify relevance before full-text screening486487### Screening and Selection4881. **Use multiple databases** (minimum 3): Ensures comprehensive coverage4892. **Include preprint servers**: Captures latest unpublished findings4903. **Document everything**: Search strings, dates, result counts for reproducibility4914. **Test and refine**: Run pilot searches, review results, adjust search terms492493### Screening and Selection4941. **Use clear criteria**: Document inclusion/exclusion criteria before screening4952. **Screen systematically**: Title → Abstract → Full text4963. **Document exclusions**: Record reasons for excluding studies4974. **Consider dual screening**: For systematic reviews, have two reviewers screen independently498499### Synthesis5001. **Organize thematically**: Group by themes, NOT by individual studies5012. **Synthesize across studies**: Compare, contrast, identify patterns5023. **Be critical**: Evaluate quality and consistency of evidence5034. **Identify gaps**: Note what's missing or understudied504505### Quality and Reproducibility5061. **Assess study quality**: Use appropriate quality assessment tools5072. **Verify all citations**: Run verify_citations.py script5083. **Document methodology**: Provide enough detail for others to reproduce5094. **Follow guidelines**: Use PRISMA for systematic reviews510511### Writing5121. **Be objective**: Present evidence fairly, acknowledge limitations5132. **Be systematic**: Follow structured template5143. **Be specific**: Include numbers, statistics, effect sizes where available5154. **Be clear**: Use clear headings, logical flow, thematic organization516517## Common Pitfalls to Avoid5185191. **Single database search**: Misses relevant papers; always search multiple databases5202. **No search documentation**: Makes review irreproducible; document all searches5213. **Study-by-study summary**: Lacks synthesis; organize thematically instead5224. **Unverified citations**: Leads to errors; always run verify_citations.py5235. **Too broad search**: Yields thousands of irrelevant results; refine with specific terms5246. **Too narrow search**: Misses relevant papers; include synonyms and related terms5257. **Ignoring preprints**: Misses latest findings; include bioRxiv, medRxiv, arXiv5268. **No quality assessment**: Treats all evidence equally; assess and report quality5279. **Publication bias**: Only positive results published; note potential bias52810. **Outdated search**: Field evolves rapidly; clearly state search date529530## Example Workflow531532Complete workflow for a biomedical literature review:533534```bash535# 1. Create review document from template536cp assets/review_template.md crispr_sickle_cell_review.md537538# 2. Start with parallel-web for broad academic search539parallel-cli search "CRISPR Cas9 sickle cell disease gene therapy efficacy" \540 -q "CRISPR" -q "sickle cell" -q "gene therapy" \541 --json --max-results 10 --excerpt-max-chars-total 27000 \542 --include-domains "scholar.google.com,arxiv.org,pubmed.ncbi.nlm.nih.gov,semanticscholar.org,biorxiv.org,nature.com,science.org,cell.com,pnas.org,nih.gov" \543 -o sources/litreview_crispr_scd-academic.json544545parallel-cli search "CRISPR sickle cell disease clinical trials treatment" \546 -q "CRISPR" -q "sickle cell" \547 --json --max-results 10 --excerpt-max-chars-total 27000 \548 -o sources/litreview_crispr_scd-general.json549550# 3. Search specialized databases using appropriate skills551# - Use gget skill for PubMed, bioRxiv552# - Use direct API access for arXiv, Semantic Scholar553# - Export results in JSON format554555# 4. Aggregate and process results (combine parallel-cli + database results)556python scripts/search_databases.py combined_results.json \557 --deduplicate \558 --rank citations \559 --year-start 2015 \560 --year-end 2024 \561 --format markdown \562 --output search_results.md \563 --summary564565# 5. Screen results and extract data566# - Use parallel-cli extract to fetch full content from promising URLs567# - Manually screen titles, abstracts, full texts568# - Extract key data into the review document569# - Organize by themes570571# 6. Write the review following template structure572# - Introduction with clear objectives573# - Detailed methodology section574# - Results organized thematically575# - Critical discussion576# - Clear conclusions577578# 7. Verify all citations579python scripts/verify_citations.py crispr_sickle_cell_review.md580581# Review the citation report582cat crispr_sickle_cell_review_citation_report.json583584# Fix any failed citations and re-verify585python scripts/verify_citations.py crispr_sickle_cell_review.md586587# 8. Generate professional PDF588python scripts/generate_pdf.py crispr_sickle_cell_review.md \589 --citation-style nature \590 --output crispr_sickle_cell_review.pdf591592# 9. Review final PDF and markdown outputs593```594595## Integration with Other Skills596597This skill works seamlessly with other scientific skills:598599### Web Search & Extraction (parallel-web skill — PRIMARY)600- **parallel-cli search**: Broad academic and general web search with domain filtering — use for initial scoping, finding papers, citation chaining, and supplementary searches601- **parallel-cli extract**: Fetch full content from paper URLs, journal websites, and preprint servers — use for reading abstracts, extracting reference lists, and verifying paper details602- **parallel-cli search --include-domains**: Academic-focused search across scholarly domains (arxiv.org, pubmed, nature.com, etc.)603604### Database Access Skills605- **gget**: PubMed, bioRxiv, COSMIC, AlphaFold, Ensembl, UniProt606- **bioservices**: ChEMBL, KEGG, Reactome, UniProt, PubChem607- **datacommons-client**: Demographics, economics, health statistics608609### Analysis Skills610- **pydeseq2**: RNA-seq differential expression (for methods sections)611- **scanpy**: Single-cell analysis (for methods sections)612- **anndata**: Single-cell data (for methods sections)613- **biopython**: Sequence analysis (for background sections)614615### Visualization Skills616- **matplotlib**: Generate figures and plots for review617- **seaborn**: Statistical visualizations618619### Writing Skills620- **brand-guidelines**: Apply institutional branding to PDF621- **internal-comms**: Adapt review for different audiences622623## Resources624625### Bundled Resources626627**Scripts:**628- `scripts/verify_citations.py`: Verify DOIs and generate formatted citations629- `scripts/generate_pdf.py`: Convert markdown to professional PDF630- `scripts/search_databases.py`: Process, deduplicate, and format search results631632**References:**633- `references/citation_styles.md`: Detailed citation formatting guide (APA, Nature, Vancouver, Chicago, IEEE)634- `references/database_strategies.md`: Comprehensive database search strategies635636**Assets:**637- `assets/review_template.md`: Complete literature review template with all sections638639### External Resources640641**Guidelines:**642- PRISMA (Systematic Reviews): http://www.prisma-statement.org/643- Cochrane Handbook: https://training.cochrane.org/handbook644- AMSTAR 2 (Review Quality): https://amstar.ca/645646**Tools:**647- MeSH Browser: https://meshb.nlm.nih.gov/search648- PubMed Advanced Search: https://pubmed.ncbi.nlm.nih.gov/advanced/649- Boolean Search Guide: https://www.ncbi.nlm.nih.gov/books/NBK3827/650651**Citation Styles:**652- APA Style: https://apastyle.apa.org/653- Nature Portfolio: https://www.nature.com/nature-portfolio/editorial-policies/reporting-standards654- NLM/Vancouver: https://www.nlm.nih.gov/bsd/uniform_requirements.html655656## Dependencies657658### Required CLI Tools659```bash660# parallel-cli (PRIMARY — for web search and URL extraction)661curl -fsSL https://parallel.ai/install.sh | bash662# Or: uv tool install "parallel-web-tools[cli]"663# Authenticate: parallel-cli auth664```665666### Required Python Packages667```bash668pip install requests # For citation verification669```670671### Required System Tools672```bash673# For PDF generation674brew install pandoc # macOS675apt-get install pandoc # Linux676677# For LaTeX (PDF generation)678brew install --cask mactex # macOS679apt-get install texlive-xetex # Linux680```681682Check dependencies:683```bash684python scripts/generate_pdf.py --check-deps685```686687## Summary688689This literature-review skill provides:6906911. **Systematic methodology** following academic best practices6922. **Parallel-web powered search** using `parallel-cli search` for fast, broad academic literature discovery with scholarly domain filtering6933. **Multi-database integration** via existing scientific skills (gget, bioservices, datacommons-client)6944. **Citation verification** ensuring accuracy and credibility6955. **Professional output** in markdown and PDF formats6966. **Comprehensive guidance** covering the entire review process6977. **Quality assurance** with verification and validation tools6988. **Reproducibility** through detailed documentation requirements699700Conduct thorough, rigorous literature reviews that meet academic standards and provide comprehensive synthesis of current knowledge in any domain.701