Literature Review
Produce a structured scientific literature review draft with PRISMA-aware sections, research questions, and methodology scaffolding.
Overview
literature-review is an agent skill for the Idea phase that structures narrative or systematic literature reviews with PRISMA-oriented methodology sections.
Install
npx skills add https://github.com/k-dense-ai/scientific-agent-skills --skill literature-reviewWhat is this skill?
- Full manuscript skeleton: abstract, introduction, methodology, with PRISMA and PROSPERO fields
- Supports narrative, systematic, scoping, meta-analysis, and umbrella review types
- Primary research questions block and protocol deviation documentation
- Abstract structured for Background, Objectives, Methods, Results, Conclusions
- Keyword and registration metadata for reproducible review workflows
- structured abstract with five mandatory fields
- primary research questions numbered list
- review types include narrative systematic scoping meta-analysis umbrella
Adoption & trust: 652 installs on skills.sh; 27.6k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have papers and notes scattered but no review protocol, research questions, or publication-ready section outline.
Who is it for?
Builders and researchers documenting evidence before product, ML, or scientific feature decisions.
Skip if: Quick competitive blog posts without methodology, or teams that already finished a registered systematic review protocol elsewhere.
When should I use this skill?
When drafting or completing a formal literature review with stated review type, PRISMA compliance, and methodology sections.
What do I get? / Deliverables
You get a filled literature review manuscript skeleton with abstract, methods, and stated review type ready for screening results and synthesis.
- Literature review document with abstract and methodology
- Documented review protocol and registration fields
- Introduction with significance and scope
Recommended Skills
Journey fit
Literature synthesis belongs in Idea research before you commit product or technical bets on thin evidence. Research subphase is where systematic and narrative reviews clarify background, gaps, and primary questions.
How it compares
Template for scholarly review structure—not a substitute for database search integrations or automated paper retrieval MCPs.
Common Questions / FAQ
Who is literature-review for?
Solo builders and researchers who need PRISMA-aware review documentation during early discovery.
When should I use literature-review?
In Idea research when defining questions and methods before build; early Validate when scoping whether evidence supports the prototype direction.
Is literature-review safe to install?
It is primarily a writing template without repo shell requirements; review the Security Audits panel on this page for the package source like any catalog skill.
SKILL.md
READMESKILL.md - Literature Review
# [Literature Review Title] **Authors**: [Author Names and Affiliations] **Date**: [Date] **Review Type**: [Narrative / Systematic / Scoping / Meta-Analysis / Umbrella Review] **Review Protocol**: [PROSPERO ID if registered, or state "Not registered"] **PRISMA Compliance**: [Yes/No/Partial - specify which guidelines] --- ## Abstract **Background**: [Context and rationale] **Objectives**: [Primary and secondary objectives] **Methods**: [Databases, dates, selection criteria, quality assessment] **Results**: [n studies included; key findings by theme] **Conclusions**: [Main conclusions and implications] **Registration**: [PROSPERO ID or "Not registered"] **Keywords**: [5-8 keywords] --- ## 1. Introduction ### 1.1 Background and Context [Provide background information on the topic. Establish why this literature review is important and timely. Discuss the broader context and current state of knowledge.] ### 1.2 Scope and Objectives [Clearly define the scope of the review and state the specific objectives. What questions will this review address?] **Primary Research Questions:** 1. [Research question 1] 2. [Research question 2] 3. [Research question 3] ### 1.3 Significance [Explain the significance of this review. Why is it important to synthesize this literature now? What gaps does it fill?] --- ## 2. Methodology ### 2.1 Protocol and Registration **Protocol**: [PROSPERO ID / OSF link / Not registered] **Deviations**: [Document any protocol deviations] **PRISMA**: [Checklist in Appendix B] ### 2.2 Search Strategy **Databases:** [PubMed, Scopus, Web of Science, bioRxiv, etc.] **Supplementary:** [Citation chaining, grey literature, trial registries] **Search String Example:** ``` ("CRISPR"[Title/Abstract] OR "Cas9"[Title/Abstract]) AND ("disease"[MeSH Terms]) AND ("2015/01/01"[Date] : "2024/12/31"[Date]) ``` **Dates:** [YYYY-MM-DD to YYYY-MM-DD] | **Executed:** [Date] **Validation:** [Key papers used to test search strategy] ### 2.3 Tools and Software **Screening:** [Rayyan, Covidence, ASReview] **Analysis:** [VOSviewer, R, Python] **Citation Management:** [Zotero, Mendeley, EndNote] **AI Tools:** [Any AI-assisted tools used; document validation approach] ### 2.4 Inclusion and Exclusion Criteria **Inclusion Criteria:** - [Criterion 1: e.g., Published between 2015-2024] - [Criterion 2: e.g., Peer-reviewed articles and preprints] - [Criterion 3: e.g., English language] - [Criterion 4: e.g., Human or animal studies] - [Criterion 5: e.g., Original research or systematic reviews] **Exclusion Criteria:** - [Criterion 1: e.g., Case reports with n<5] - [Criterion 2: e.g., Conference abstracts without full text] - [Criterion 3: e.g., Editorials and commentaries] - [Criterion 4: e.g., Duplicate publications] - [Criterion 5: e.g., Retracted articles] - [Criterion 6: e.g., Studies with unavailable full text after author contact] ### 2.5 Study Selection **Reviewers:** [n independent reviewers] | **Conflict resolution:** [Method] **Inter-rater reliability:** [Cohen's kappa = X] **PRISMA Flow:** ``` Records identified: n=[X] → Deduplicated: n=[Y] → Title/abstract screened: n=[Y] → Full-text assessed: n=[Z] → Included: n=[N] ``` **Exclusion reasons:** [List with counts] ### 2.6 Data Extraction **Method:** [Standardized form (Appendix E); pilot-tested on n studies] **Extractors:** [n independent] | **Verification:** [Double-checked] **Items:** Study ID, design, population, interventions/exposures, outcomes, statistics, funding, COI, bias domains **Missing data:** [Author contact protocol] ### 2.7 Quality Assessment **Tool:** [Cochrane RoB 2.0 / ROBINS-I / Newcastle-Ottawa / AMSTAR 2 / JBI] **Method:** [2 independent reviewers; third for conflicts] **Rating:** [Low/Moderate/High risk of bias] **Publication bias:** [Funnel plots, Egger's test - if meta-analysis] ### 2.8 Synthesis and Analysis **Approach:** [Narrative / Meta-analysis / Both] **Statistics** (if meta-analysis): E