risk-of-bias-assessment

$npx mdskill add yogsoth-ai/de-anthropocentric-research-engine/risk-of-bias-assessment

Conduct structured risk-of-bias assessment for individual studies using validated tools

  • Identifies appropriate methodological bias assessment tool (RoB2, PROBAST, QUADAS-2) based on study design.
  • Deploys the selected tool to analyze study metadata and design characteristics.
  • Generates domain-level risk-of-bias judgments with rationale for each question.
  • Delivers results in a structured format suitable for meta-analysis.

SKILL.md

.github/skills/risk-of-bias-assessmentView on GitHub ↗
---
name: risk-of-bias-assessment
description: Assess methodological bias using RoB2, PROBAST, or QUADAS-2 validated tools
execution: subagent
prompt: ./prompt.md
input: study_metadata, study_design
used-by: meta-analysis
---

# Risk of Bias Assessment SOP

Conduct structured risk-of-bias assessment for individual studies using the appropriate validated tool (RoB 2.0, ROBINS-I, QUADAS-2, PROBAST, or Newcastle-Ottawa Scale).

## When to Use

- During quality assessment of each included study
- When deciding sensitivity analysis groupings
- When assessing GRADE certainty (risk of bias domain)

## Input

- `study_metadata`: Study characteristics, methods description, and results
- `study_design`: The study design (RCT, non-randomized, diagnostic, prediction model, observational)

## Output

Domain-level risk-of-bias judgments with supporting rationale for each signaling question.

More from yogsoth-ai/de-anthropocentric-research-engine

SkillDescription
abductive-hypothesis-generationStrategy: 面对异常的最佳解释推理
ablation-brainstormRemove components one by one, observe system changes to reveal hidden dependencies and generate ideas from structural gaps.
ablation-component-mappingMap system architecture to ablatable units for ablation studies
ablation-designDesign ablation studies to isolate component contributions in ML systems
ablation-executionRemove components one by one from a system, record the response/impact of each removal.
abp-vulnerability-classificationClassify assumptions on 2 axes — load-bearing (how much conclusion depends on it) × vulnerable (how likely to be false). Focuses attention on High-Load × High-Vulnerable quadrant.
abstraction-extractionExtract abstract principles from concrete domain cases. Strips domain-specific details to reveal transferable mechanisms.
abstraction-ladderPerform bisociation at multiple abstraction levels
abstraction-ladderingMove between concrete and abstract framings — 3 levels up (Why?) and 3 levels down (How?) to find the most productive research level.
abstraction-to-designAbstract biological principle to design principle. Bridge from biology to engineering.