Meta Analysis Methods Generator

Source: https://github.com/aipoch/medical-research-skills

Meta Analysis Methods Generator

When to Use

• Use this skill when the request matches its documented task boundary.
• Use it when the user can provide the required inputs and expects a structured deliverable.
• Prefer this skill for repeatable, checklist-driven execution rather than open-ended brainstorming.

Key Features

• Scope-focused workflow aligned to: Generates the Methods section for a meta-analysis paper, including search strategy, screening, quality assessment, data extraction, and statistical analysis.
• Packaged executable path(s): scripts/validate_skill.py.
• 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/Academic Writing/meta-analysis-methods-generator"
python -m py_compile scripts/validate_skill.py
python scripts/validate_skill.py --help

Example run plan:

1. Confirm the user input, output path, and any required config values.
2. Edit the in-file CONFIG block or documented parameters if the script uses fixed settings.
3. Run python scripts/validate_skill.py with the validated inputs.
4. 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/validate_skill.py.
• 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.

Validation Shortcut

Run this minimal command first to verify the supported execution path:

python scripts/validate_skill.py --help

User Intent Examples

• "Generate a methods section for a meta-analysis on..."
• "Write the methods part for my paper using these criteria..."

IO Contract

Inputs:

• criteria (string, required): Inclusion and exclusion criteria.
• PICOS (string, required): Population, Intervention, Comparison, Outcome, Study design.
• title (string, required): The risk of bias assessment tool to use (e.g., ROB2, NOS, ROBINS-I, ROBINS-E, QUADAS, QUIPS, PROBAST).
• language (string, required): Output language (Chinese or English).

Outputs:

• methods_section (markdown): The complete Methods section.

Workflow

1. Input Validation: Verify criteria, PICOS, title, and language are provided.
2. Context Retrieval: Obtain current_time.
3. Execution Steps:
   • Step 1: Search Strategy
     • Action: Generate content using Search Strategy prompt.
     • Inputs: PICOS, current_time, language.
   • Step 2: Inclusion and Exclusion Criteria
     • Action: Generate content using Inclusion and Exclusion Criteria prompt.
     • Inputs: criteria, language.
   • Step 3: Literature Screening
     • Action: Generate content using Literature Screening prompt.
     • Inputs: language.
   • Step 4: Quality Assessment
     • Action: Generate content using Quality Assessment prompt.
     • Inputs: title, PICOS, language.
   • Step 5: Data Extraction
     • Action: Generate content using Data Extraction prompt.
     • Inputs: language.
   • Step 6: Statistical Analysis
     • Action: Generate content using Statistical Analysis prompt.
     • Inputs: language.
4. Compilation: Combine all generated sections into a single Markdown document.

Quality Rules

• QR-LANG-001: Output must be in the specified language.
• QR-FORMAT-001: Follow the specific outline for each subsection.
• QR-CONTENT-001: Include all 6 required subsections.

Prompts and Templates

Inclusion and Exclusion Criteria

Role: System Content:

The user will input a section of inclusion and exclusion criteria. Please:

Specific Requirements:

1. Remove JSON formatting.
2. Output the inclusion and exclusion criteria completely; do not modify.
3. Please output all content in {{ language }}.

Literature Screening

Role: System Content: Literature screening

Write a paragraph about literature screening for the methods section of a meta-analysis, following the outline below. Note that the outline is not an example; please expand or modify appropriately based on the outline. Write general information, avoiding specific details.

Please always remember that I want the text paragraph to be random, not static.

Outline:

1. Initial screening: Two experts.
2. Initial screening results are: "Yes", "No", and "Maybe".
3. Secondary screening: Three experts.
4. Please output all content in {{ language }}, more than 200 words.

Quality Assessment

Role: System Content: Quality assessment

Please select the appropriate scale type according to the following rules.

• Etiological studies use ROBINS-E or NOS.
• RCT: use ROB2.
• Non-RCT (Clinical Trials): use ROBINS-I.
• Observational studies: use NOS.
• Prognostic studies use QUIPS or PROBAST.

Based on the title and PICOS entered by the user, infer the quality assessment scale that might be used, write a section on quality assessment for the meta-analysis methods part, and follow the outline below:

1. ROB2: Covers random sequence generation, allocation concealment, the use of blinding, data completeness, selective reporting, and other potential sources of bias. NOS: This scale assesses the quality of selection, comparability, and outcome. ROBINS-I: ROBINS-I involves seven domains: confounding, selection of participants, classification of interventions, deviations from intended interventions, missing data, measurement of outcomes, and selection of the reported results. Each domain has ratings of low, moderate, serious, or unclear risk of bias. ROBINS-E: The ROBINS-E tool includes seven domains: confounding, measurement of the exposure, participant selection, post-exposure interventions, missing data, measurement of the outcome, and selection of the reported result. QUIPS: Overall risk of bias is 'low', 'moderate', or 'high'. Assess the 6 items of QUIPS: [1] study participation, [2] study attrition, [3] prognostic factor measurement, [4] outcome measurement, [5] study confounding, and [6] statistical analysis and reporting. PROBAST: The answer for each domain is classified as low, high, or unclear. If at least one domain is assessed as high risk, then the overall assessment is high risk. If at least one domain is rated as unclear and there is no high risk, then the overall assessment is unclear.
2. Please output all content in {{ language }}!!!

Data Extraction

Role: System Content:

Write a paragraph about data extraction for the meta-analysis methods section, following the outline below:

1. Extract author name, year of publication, and basic characteristics of participants (number, age, gender).
2. Please output all content in {{ language }}, more than 200 words.

Statistical Analysis

Role: System Content: Statistical analysis