K-Dense-AI/scientific-agent-skills / skills/literature-review
literature-review
VerifiedConducts systematic, scoping, and narrative literature reviews using PubMed, arXiv, bioRxiv, Semantic Scholar, and other appropriate sources. Use for research synthesis, reproducible literature searches, screening, citation checking, or preparing Markdown and PDF reviews. Tracks search coverage, records versus studies, and evidence limitations; supports meta-analysis planning but does not supply a meta-analysis engine.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 12.6 KB |
| assets/review_template.md | markdown | 13.4 KB |
| references/citation_styles.md | markdown | 7.4 KB |
| references/core_workflow.md | markdown | 11.6 KB |
| references/database_strategies.md | markdown | 10.2 KB |
| references/example_workflow.md | markdown | 3.0 KB |
| references/search_and_citation.md | markdown | 4.6 KB |
| scripts/generate_pdf.py | script | 4.9 KB |
| scripts/generate_schematic.py | script | 7.6 KB |
| scripts/generate_schematic_ai.py | script | 34.8 KB |
| scripts/search_databases.py | script | 8.6 KB |
| scripts/verify_citations.py | script | 9.7 KB |
references/example_workflow.md
View on GitHub# Example Workflow
Illustrative end-to-end recipe, not an executed review. Run from the skill directory; populate the protocol, normalized search records, bibliography, and CSL file before the dependent commands. Dates below are a deliberately historical 2015-2024 interval.
## Example Workflow
Complete workflow for a biomedical literature review:
```bash
# 1. Create review document from template
mkdir -p sources styles
cp assets/review_template.md crispr_sickle_cell_review.md
# 2. Optional supplementary discovery (authenticated Parallel account)
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 PubMed E-utilities and bioRxiv/medRxiv search or date-metadata APIs
# - Use direct API access for arXiv, Semantic Scholar
# - Save all pages and counts; document any API caps or failed requests
# - Normalize into a JSON array; keep raw exports and provenance
# 4. Process your normalized combined_results.json; raw API envelopes will fail
python scripts/search_databases.py combined_results.json \
--deduplicate \
--year-start 2015 \
--year-end 2024 \
--format markdown \
--output search_results.md \
--summary
# 5. Screen results and extract data
# - Request extracts with --full-content; obtain original reports and record failures
# - Use independent final full-text decisions and retain exclusion reasons
# - Track records, reports, studies, and overlapping participants separately
# - 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. Check DOI registration/metadata, then manually verify identity and claim support
python scripts/verify_citations.py crispr_sickle_cell_review.md
# Review the citation report
cat crispr_sickle_cell_review_citation_report.json
# Investigate missing/inconclusive results; transient failures do not invalidate citations
python scripts/verify_citations.py crispr_sickle_cell_review.md
# 8. Render after supplying bibliography, local CSL, and [@key] citations
# For manually typed references, omit those options; text will not be restyled
python scripts/generate_pdf.py crispr_sickle_cell_review.md \
--bibliography crispr_sickle_cell_review.bib --csl styles/nature.csl \
--output crispr_sickle_cell_review.pdf
# 9. Review final PDF and markdown outputs
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |