Medical Literature Review Assistant
Paste the following prompt into your AI chat to install this skill:
Please install @user_f37e97ba/medical-literature-review according to https://skillhub.cn/install/skillhub.md.
About this skill
Problem to Solve
The hard part of a medical literature review is not reading individual papers, but keeping the search reproducible, the screening process complete, the quality appraisal consistent, and the conclusions aligned with evidence strength. This skill frames the task as evidence-based writing assistance rather than diagnosis or treatment advice.
Core Workflow
It follows a structured review path. First, define the question using PICO: population, intervention, comparison, and outcome. Then build the search strategy from MeSH terms, free-text terms, Boolean operators, and filters, while recording databases, search date, syntax, and limits. Screening proceeds through deduplication, title/abstract review, and full-text review, with reasons for exclusions preserved. Extraction focuses on study design, sample size, effect measures such as RR, OR, HR, MD + 95%CI, and risk of bias. Quality appraisal uses tools matched to study type, such as Cochrane RoB, NOS, QUADAS-2, or AMSTAR 2. Synthesis is labeled with GRADE, and the discussion covers publication bias, heterogeneity, and clinical applicability.
Scope and Limits
Use it for drafting reviews, structuring inclusion tables, documenting search strategies, and explaining evidence quality. It should not be used for patient diagnosis, treatment plans, medication recommendations, or single-case advice. By default it emphasizes recent literature and covers at least PubMed and Cochrane Library; extend the scope explicitly when older evidence, rare populations, or specialty databases are required.
Use Cases
- Break a clinical question into PICO components and generate a PubMed search string with MeSH terms, Boolean operators, and exact search date.
- Screen titles, abstracts, and full texts following PRISMA, producing per-stage exclusion counts and reasons.
- Extract effect sizes (RR/HR with 95% CI) and study design from included papers into a GRADE-labeled characteristics table.
- Apply Cochrane RoB for RCTs and NOS for observational studies to assess risk of bias, flagging limitations in the discussion.
Best For
- Medical graduate students writing a thesis or grant report who need to complete literature screening and GRADE grading per PRISMA.
- Clinicians preparing a systematic review or meta-analysis who need a reproducible search strategy and risk-of-bias assessment.
- Research assistants drafting clinical guidelines or reviews who need to extract effect sizes, build inclusion tables, and label evidence levels.
- Teachers of evidence-based medicine who need to demonstrate PICO breakdown, search-string construction, and GRADE grading.
Related Skills
Covers literature review, data analysis, visualization, drug discovery, paper writing, and grant writing workflows.
A retrieval assistant for Chinese laws and regulations, supporting semantic queries, validity checks, clause location, and regulation comparison with CLI-based output.
Run questionnaire-based tax risk scans that generate red/orange/yellow alerts with industry templates, policy references, remediation actions, and local trend tracking.
A contract review assistant for legal and business teams that extracts clauses, flags risks, compares versions, and generates opinion reports with a built-in legal knowledge base.