Runs a PRISMA-compliant systematic review from PICO question and pre-registered protocol through search strings, two-stage screening, risk-of-bias appraisal, and GRADE-rated synthesis. Use when someone asks "run a systematic review", "build my search strategy and inclusion criteria", "screen these studies against a protocol", or "meta-analyze the evidence on X". Do NOT use for a thematic narrative review of a field without a registered protocol and exhaustive search - use literature-review instead. Do NOT use for synthesizing mixed non-study sources into decision themes - use research-synthesis instead.
Click to play with sound.
---
name: Systematic Review
description: Runs a PRISMA-compliant systematic review from PICO question and pre-registered protocol through search strings, two-stage screening, risk-of-bias appraisal, and GRADE-rated synthesis. Use when someone asks "run a systematic review", "build my search strategy and inclusion criteria", "screen these studies against a protocol", or "meta-analyze the evidence on X". Do NOT use for a thematic narrative review of a field without a registered protocol and exhaustive search - use literature-review instead. Do NOT use for synthesizing mixed non-study sources into decision themes - use research-synthesis instead.
---
# Systematic Review
A systematic review answers one focused question by finding, appraising, and synthesizing all relevant studies with a transparent, reproducible method. The costly failure it prevents is post-hoc bias: deciding what counts as evidence after seeing the results. Every eligibility decision is therefore locked in a protocol before the first search runs, and every excluded study leaves a logged reason. Follow PRISMA 2020 throughout.
## Operating procedure
Order is mandatory: the protocol must exist before the search, and the search before screening, or the review is not systematic - it is a literature review wearing a lab coat (route that job to literature-review).
### Step 1: Gather inputs and frame the PICO question
Collect from the user before starting:
- The research question, decomposed into **P**opulation, **I**ntervention/Exposure, **C**omparison, **O**utcome. If it has no clear PICO, refuse and help them write one - a question like "is telehealth good?" cannot be reviewed.
- Intended study designs (RCTs only? observational too?).
- Databases available to them (default: PubMed/MEDLINE, Embase, plus one field-specific database - a minimum of 3).
- Team size: two independent screeners are required; if the user is solo, flag this as a methodological limitation up front, not in the discussion section.
- Timeline and whether meta-analysis is intended.
Label any assumed input as a guess and confirm before Step 3.
… install to load the full skill