aipoch/probast-quality-assessment for prediction model studies
scientific-skills/Data Analysis/probast-quality-assessment-for-prediction-model-studies/SKILL.md
Assess bias in medical prediction model studies using PROBAST tool. Use when user wants to evaluate the quality or risk of bias of a medical paper (text or PDF).
$ install --global
skillsauthnpx skillsauth add aipoch/medical-research-skills probast-quality-assessment for prediction model studiesInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
4 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
4
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 5, 2026, 12:46 AM43.0s1 file scanned
SKILL.md
- name:
- probast-quality-assessment for prediction model studies
- description:
- Assess bias in medical prediction model studies using PROBAST tool. Use when user wants to evaluate the quality or risk of bias of a medical paper (text or PDF).
- license:
- MIT
- skill-author:
- AIPOCH
PROBAST Quality Assessment
This skill evaluates the risk of bias in medical prediction model studies using the PROBAST (Prediction model Risk Of Bias ASsessment Tool) framework. It analyzes the full text of a paper across four domains: Participants, Predictors, Outcome, and Analysis.
When to Use
- Use this skill when you need assess bias in medical prediction model studies using probast tool. use when user wants to evaluate the quality or risk of bias of a medical paper (text or pdf) in a reproducible workflow.
- Use this skill when a data analytics task needs a packaged method instead of ad-hoc freeform output.
- Use this skill when the user expects a concrete deliverable, validation step, or file-based result.
- Use this skill when
scripts/extract_pdf.pyis the most direct path to complete the request. - Use this skill when you need the
probast-quality-assessment for prediction model studiespackage behavior rather than a generic answer.
Key Features
- Scope-focused workflow aligned to: Assess bias in medical prediction model studies using PROBAST tool. Use when user wants to evaluate the quality or risk of bias of a medical paper (text or PDF).
- Packaged executable path(s):
scripts/extract_pdf.py. - Reference material available in
references/for task-specific guidance. - Structured execution path designed to keep outputs consistent and reviewable.
Dependencies
Python:3.10+. Repository baseline for current packaged skills.Third-party packages:not explicitly version-pinned in this skill package. Add pinned versions if this skill needs stricter environment control.
Example Usage
cd "20260316/scientific-skills/Data Analytics/probast-quality-assessment-for-prediction-model-studies"
python -m py_compile scripts/extract_pdf.py
python scripts/extract_pdf.py --help
Example run plan:
- Confirm the user input, output path, and any required config values.
- Edit the in-file
CONFIGblock or documented parameters if the script uses fixed settings. - Run
python scripts/extract_pdf.pywith the validated inputs. - Review the generated output and return the final artifact with any assumptions called out.
Implementation Details
See ## Workflow above for related details.
- Execution model: validate the request, choose the packaged workflow, and produce a bounded deliverable.
- Input controls: confirm the source files, scope limits, output format, and acceptance criteria before running any script.
- Primary implementation surface:
scripts/extract_pdf.py. - Reference guidance:
references/contains supporting rules, prompts, or checklists. - Parameters to clarify first: input path, output path, scope filters, thresholds, and any domain-specific constraints.
- Output discipline: keep results reproducible, identify assumptions explicitly, and avoid undocumented side effects.
Workflow
To perform the assessment, follow this sequence of operations using the prompts defined in references/probast_prompts.md.
Step 1: Extract Metadata
Extract the first author and year from the paper.
- Prompt: Use "1. Metadata Extraction" from
references/probast_prompts.md.
Step 2: Assess Risk Domains (Parallel)
Assess the risk of bias for each of the four domains. For each domain, use the corresponding prompt to generate a risk rating (Low/High/Unclear) and detailed reasoning.
- Domain 1 (Participants): Use "2. Domain 1: Participants" from
references/probast_prompts.md. - Domain 2 (Predictors): Use "3. Domain 2: Predictors" from
references/probast_prompts.md. - Domain 3 (Outcome): Use "4. Domain 3: Outcome" from
references/probast_prompts.md. - Domain 4 (Analysis): Use "5. Domain 4: Analysis" from
references/probast_prompts.md.
Step 3: Determine Overall Risk
Combine the risk ratings from the four domains to determine the overall risk of bias.
- Input: The risk ratings (Low/High/Unclear) from Domains 1-4.
- Prompt: Use "6. Overall Risk Assessment" from
references/probast_prompts.md.
Step 4: Format Output
Generate a final JSON report containing the risk ratings for all domains and the overall assessment.
- Input: The results from Steps 1-3.
- Prompt: Use "7. JSON Extraction" from
references/probast_prompts.md. - Output Format: A JSON object matching the
study_risk_of_bias_schema.
Helper Scripts
PDF Text Extraction
When the user provides a PDF file path, use extract_pdf.py to extract the text content before assessment:
Related Skills
aipoch/conventional-oncology-hub-gene
tools
VerifiedTrustedCommunity
Generates complete conventional oncology bulk-transcriptome biomarker and hub-gene research designs from a user-provided cancer type and study direction. Always use this skill whenever a user wants to design, plan, or build a tumor bioinformatics study centered on differential expression, prognostic filtering or risk modeling, PPI-based hub-gene prioritization, diagnostic/prognostic evaluation, clinical association, immune infiltration context, methylation context, and optional tissue or cell validation. Covers five study patterns (signature-first prognostic workflow, hub-gene-first biomarker workflow, hybrid signature-to-hub workflow, immune-context biomarker workflow, translational validation workflow) and always outputs four workload configs (Lite / Standard / Advanced / Publication+) with recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version, publication upgrade path...
348SKILL.mdUpdated Apr 28, 2026
aipoch/conventional-non-oncology-hub-gene
development
VerifiedTrustedCommunity
Generates complete conventional non-oncology bioinformatics research designs from a user-provided disease context, process-related gene family or biological theme, and validation direction. Use when a study centers on multi-dataset bulk transcriptome integration, DEG analysis, process-gene intersection, enrichment analysis, GSEA, PPI hub-gene prioritization, TF/miRNA regulatory networks, ROC-based biomarker evaluation, and immune infiltration analysis. Covers five study patterns (process-DEG discovery, enrichment/GSEA interpretation, hub-gene prioritization, regulatory-network and immune interpretation, multi-layer public validation) and always outputs Lite / Standard / Advanced / Publication+ with a recommended primary plan, stepwise workflow, figure plan, validation hierarchy, minimal executable version, publication upgrade path, and strictly verified literature retrieval.
348SKILL.mdUpdated Apr 28, 2026
aipoch/confounder-and-bias-control-planner
tools
VerifiedTrustedCommunity
Plans confounder control, variable adjustment logic, and bias mitigation strategies at the protocol stage for clinical, epidemiologic, translational, observational, and biomarker studies. Always use this skill when a user needs to identify major confounders, decide which variables should or should not be adjusted for, compare matching/stratification/weighting approaches, anticipate selection or measurement bias, or pressure-test a study design before execution. Focus on bias sensing, causal structure awareness, variable-role classification, and critical design review rather than generic statistical advice.
348SKILL.mdUpdated Apr 28, 2026
aipoch/comparative-network-toxicology-shared-mechanism-reference-grounded
testing
VerifiedTrustedCommunity
Generates complete comparative network-toxicology research designs from a user-provided exposure pair, shared toxic phenotype, and validation direction. Use when a study centers on two related exposures under one outcome and needs target collection, shared-vs-specific target decomposition, enrichment, PPI hub prioritization, docking, optional transcriptomic cross-checks, and conservative mechanistic synthesis. Covers five study patterns and always outputs Lite / Standard / Advanced / Publication+ with a recommended primary plan, stepwise workflow, figure plan, validation hierarchy, minimal executable version, publication upgrade path, and strictly verified literature retrieval.
348SKILL.mdUpdated Apr 28, 2026