Meta Criteria Generator

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

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 scientifically sound inclusion and exclusion criteria for Meta-Analysis based on a given title or keywords. Use when user wants to design eligibility criteria for a systematic review or meta-analysis.
• Packaged executable path(s): scripts/extract_criteria.py plus 1 additional script(s).
• 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

See ## Usage above for related details.

cd "20260316/scientific-skills/Data Analytics/meta-criteria-generator"
python -m py_compile scripts/extract_criteria.py
python scripts/extract_criteria.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/extract_criteria.py with the validated inputs.
4. Review the generated output and return the final artifact with any assumptions called out.

Implementation 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_criteria.py with additional helper scripts under scripts/.
• 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/extract_criteria.py --help

Meta-Analysis Criteria Generator

This skill generates inclusion and exclusion criteria for Meta-Analysis based on the PICO framework (Population, Intervention, Comparator, Outcomes) and Study Design.

Usage

1. Ask for Title/Keywords: If not provided, ask the user for the Meta-Analysis topic.
2. Generate Inclusion Criteria: Use LLM to generate criteria based on the input.
3. Generate Exclusion Criteria: Use LLM to generate exclusion criteria that do not contradict the inclusion criteria.
4. Format Output: Use scripts/extract_criteria.py to extract the final criteria from the LLM outputs and present them clearly.

Workflow Details

Step 1: Generate Inclusion Criteria

Prompt the LLM to act as a Meta-Analysis expert. Input: User provided title/keywords. Requirements:

• Cover P (Population), I (Intervention), C (Comparator), O (Outcomes), S (Study Design).
• Output must be in English.
• Crucial: Enclose the final criteria list in {} for extraction.
• Format: {(1) Participants: ...; (2) Interventions: ...; ...}

Step 2: Generate Exclusion Criteria

Prompt the LLM to generate exclusion criteria. Input: Inclusion Criteria from Step 1, User title. Requirements:

• Must NOT contradict Inclusion Criteria.
• Must NOT repeat Inclusion Criteria.
• Output must be in English.
• Crucial: Enclose the final criteria list in {} for extraction.

Step 3: Extract and Format

Run the extraction script to clean up the outputs.

python scripts/extract_criteria.py --inclusion "<inclusion_text>" --exclusion "<exclusion_text>"

Quality Rules

• Language: All outputs must be in English.
• Format: The final output must be clearly separated into "Inclusion Criteria" and "Exclusion Criteria".
• Consistency: Exclusion criteria must be logically consistent with inclusion criteria.

When Not to Use

• Do not use this skill when the required source data, identifiers, files, or credentials are missing.
• Do not use this skill when the user asks for fabricated results, unsupported claims, or out-of-scope conclusions.
• Do not use this skill when a simpler direct answer is more appropriate than the documented workflow.