$npx -y skills add K-Dense-AI/scientific-agent-skills --skill literature-reviewConduct 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 searche
| 1 | # Literature Review |
| 2 | |
| 3 | ## Overview |
| 4 | |
| 5 | 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. |
| 6 | |
| 7 | 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. |
| 8 | |
| 9 | ## When to Use This Skill |
| 10 | |
| 11 | Use this skill when: |
| 12 | - Conducting a systematic literature review for research or publication |
| 13 | - Synthesizing current knowledge on a specific topic across multiple sources |
| 14 | - Performing meta-analysis or scoping reviews |
| 15 | - Writing the literature review section of a research paper or thesis |
| 16 | - Investigating the state of the art in a research domain |
| 17 | - Identifying research gaps and future directions |
| 18 | - Requiring verified citations and professional formatting |
| 19 | |
| 20 | ## Visual Enhancement with Scientific Schematics |
| 21 | |
| 22 | **⚠️ MANDATORY: Every literature review MUST include at least 1-2 AI-generated figures using the scientific-schematics skill.** |
| 23 | |
| 24 | This is not optional. Literature reviews without visual elements are incomplete. Before finalizing any document: |
| 25 | 1. Generate at minimum ONE schematic or diagram (e.g., PRISMA flow diagram for systematic reviews) |
| 26 | 2. Prefer 2-3 figures for comprehensive reviews (search strategy flowchart, thematic synthesis diagram, conceptual framework) |
| 27 | |
| 28 | **How to generate figures:** |
| 29 | - Use the **scientific-schematics** skill to generate AI-powered publication-quality diagrams |
| 30 | - Simply describe your desired diagram in natural language |
| 31 | - Nano Banana Pro will automatically generate, review, and refine the schematic |
| 32 | |
| 33 | **How to generate schematics:** |
| 34 | ```bash |
| 35 | python scripts/generate_schematic.py "your diagram description" -o figures/output.png |
| 36 | ``` |
| 37 | |
| 38 | The AI will automatically: |
| 39 | - Create publication-quality images with proper formatting |
| 40 | - Review and refine through multiple iterations |
| 41 | - Ensure accessibility (colorblind-friendly, high contrast) |
| 42 | - Save outputs in the figures/ directory |
| 43 | |
| 44 | **When to add schematics:** |
| 45 | - PRISMA flow diagrams for systematic reviews |
| 46 | - Literature search strategy flowcharts |
| 47 | - Thematic synthesis diagrams |
| 48 | - Research gap visualization maps |
| 49 | - Citation network diagrams |
| 50 | - Conceptual framework illustrations |
| 51 | - Any complex concept that benefits from visualization |
| 52 | |
| 53 | For detailed guidance on creating schematics, refer to the scientific-schematics skill documentation. |
| 54 | |
| 55 | --- |
| 56 | |
| 57 | ## Core Workflow |
| 58 | |
| 59 | Literature reviews follow a structured, multi-phase workflow: |
| 60 | |
| 61 | ### Phase 1: Planning and Scoping |
| 62 | |
| 63 | 1. **Define Research Question**: Use PICO framework (Population, Intervention, Comparison, Outcome) for clinical/biomedical reviews |
| 64 | - Example: "What is the efficacy of CRISPR-Cas9 (I) for treating sickle cell disease (P) compared to standard care (C)?" |
| 65 | |
| 66 | 2. **Establish Scope and Objectives**: |
| 67 | - Define clear, specific research questions |
| 68 | - Determine review type (narrative, systematic, scoping, meta-analysis) |
| 69 | - Set boundaries (time period, geographic scope, study types) |
| 70 | |
| 71 | 3. **Develop Search Strategy**: |
| 72 | - Identify 2-4 main concepts from research question |
| 73 | - List synonyms, abbreviations, and related terms for each concept |
| 74 | - Plan Boolean operators (AND, OR, NOT) to combine terms |
| 75 | - Select minimum 3 complementary databases |
| 76 | - **Use the parallel-web skill (`parallel-cli search`) for initial scoping** to quickly gauge the landscape before formal database searches |
| 77 | |
| 78 | 4. **Set Inclusion/Exclusion Criteria**: |
| 79 | - Date range (e.g., last 10 years: 2015-2024) |
| 80 | - Language (typically English, or specify multilingual) |
| 81 | - Publication types (peer-reviewed, preprints, reviews) |
| 82 | - Study designs (RCTs, observational, in vitro, etc.) |
| 83 | - Document all criteria clearly |
| 84 | |
| 85 | ### Phase 2: S |