Systematic Review

Conduct systematic reviews with transparent search, screening, and synthesis protocols that minimize bias in evidence summaries. Use when high-stakes decisions require rigorous aggregation of existing studies (academic, clinical, policy, or technical).

itsual Updated

File contents

Systematic Review

Overview

A systematic review answers a defined question by finding, appraising, and synthesizing all relevant evidence using a predetermined protocol — reducing cherry-picking.

When to Use

  • High-stakes evidence summaries
  • Academic and clinical evidence bases
  • Policy and standards decisions
  • Technical state-of-the-art with auditability needs

Core Practices

  • Register or document the protocol (question, criteria, search plan)
  • Search multiple sources with recorded strategies
  • Screen studies with dual review when possible
  • Appraise quality/risk of bias
  • Synthesize narratively or quantitatively (meta-analysis) as appropriate
  • Report PRISMA-style flow and limitations

Principles

  • Protocol precedes results to limit bias
  • Absence of evidence ≠ evidence of absence
  • Quality of included studies bounds quality of conclusions
  • Updates may be needed as literature moves

Verification

  • Protocol and criteria are explicit
  • Search and screening are reproducible
  • Conclusions respect study quality and heterogeneity

itsual/agent-skills-collection/tree/main/skills/research/systematic-review commit 207b5b22ed

Frequently asked questions

npx skillmds@latest add itsual/systematic-review