---
name: critical-appraisal
description: "Critically appraise a clinical study for validity: bias, confounding, the comparator, outcome choice, statistics and spin. Use when a clinician asks whether a study is trustworthy, how strong it is, or what is wrong with it."
---

# Critical Appraisal

Judge whether a study's conclusions follow from its methods and data.

## Checklist (work through each, briefly)

1. **Question and comparator.** Is the comparison group the right one? Is a relevant comparator missing? A treatment compared with nothing, or with an outdated alternative, can look better than it is.
2. **Design fit.** Is the design capable of answering the question asked? Observational data cannot by itself prove cause.
3. **Selection.** Who was included, who was excluded, and who was lost to follow-up? Compare the study population with the population the authors generalize to.
4. **Confounding.** List the main confounders a clinician would expect, and say whether each was measured and adjusted for.
5. **Outcomes.** Is the primary outcome clinically meaningful, or a surrogate? Was it prespecified? Is there outcome switching between registration and publication when a registry entry is available?
6. **Statistics.** Check the effect size, confidence interval, sample size, multiplicity and whether absolute risks are reported. A small p-value does not mean a large effect.
7. **Spin.** Compare the conclusion in the abstract with the actual primary result. Flag language stronger than the data.
8. **Conflicts and funding.**

## Output format

A table with three columns: Domain, Finding, Impact on conclusion (Low / Moderate / High). Follow with an overall judgment in two or three sentences and the single most important question the authors should answer.

Be fair. Name the study's strengths as well as its weaknesses.

## Safety rules (apply every time)

- This skill supports clinician judgment. It does not replace it, and its output is not a diagnosis or a treatment order.
- Never work with identifiable patient information. If the user pastes names, record numbers, dates of birth, addresses, photos of faces or other identifiers, stop and ask them to remove the identifiers first.
- Never invent facts, numbers, citations, quotations or guideline wording. If a source is not available, say so plainly. Label anything you could not verify as "unverified".
- Prefer primary sources and current professional guidelines. Give the issuing body and year of any guideline you cite, and note that guidance may have changed since.
- When the output contains clinical content, end with one line reminding the user to verify it before use.

## Language standards

- Use precise, respectful clinical language. Write "pregnant patient" or "pregnant woman", "clinician" or the specific profession rather than "provider", and "non-indicated" or "scheduled" rather than "elective" for inductions and cesareans.
- Prefer "compassion" to "empathy" when describing the clinician's stance.
- Do not call a pregnant patient a "mother" before the birth.
- Write plainly. No hype words such as "groundbreaking", "game-changer" or "revolutionary".

---
Part of the Clinician Essentials skill set, version 1.0.0 (2026-10-25), by Amos Grünebaum, MD. Free to use and share with attribution.