scholar-evaluation

Evaluate scholarly work across eight quality dimensions using the ScholarEval framework with structured scoring.

Updated Sep 2, 2026
One-click install
npx skills add https://github.com/ricfulop/cba-agentic-engineering-bootstrap --skill scholar-evaluation-ricfulop
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: scholar-evaluation
Source: https://github.com/ricfulop/cba-agentic-engineering-bootstrap/tree/main/skills/scholar-evaluation
Command: npx skills add https://github.com/ricfulop/cba-agentic-engineering-bootstrap --skill scholar-evaluation-ricfulop

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, and includes scripts (resource) and references (resource) components.

What problem does it solve? Assessing research papers, proposals, and literature reviews consistently is difficult without a structured rubric, leading to subjective or incomplete feedback. This Skill applies the ScholarEval framework to produce systematic, dimension-by-dimension evaluations with quantitative scores and actionable recommendations. ## Core Features & Use Cases - Eight-Dimension Assessment: Evaluates problem formulation, literature review, methodology, data collection, analysis, results, writing, and citations using detailed rubrics in references/evaluation_framework.md. - Quantitative Scoring: Aggregates dimension ratings on a 5-point scale with weighted averaging, quality-level classification, and ASCII bar charts via scripts/calculate_scores.py. - Structured Feedback Reports: Produces prioritized strengths, weaknesses, and publication-readiness assessments tailored to work stage, venue, and discipline. - Use Case: Given a draft machine learning paper, systematically score each dimension, generate a SCHOLAR_EVALUATION.md report, and identify the highest-impact revisions before journal submission. ## Quick Start Evaluate this research paper using the scholar-evaluation skill and produce a scored report with prioritized feedback.

Frequently Asked Questions about scholar-evaluation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I evaluate a research paper with the ScholarEval framework?

Identify the work type and scope, then assess each of the eight dimensions using the rubrics in references/evaluation_framework.md. Score each dimension from 1 to 5 and synthesize an overall assessment with prioritized recommendations.

How do I calculate weighted evaluation scores from dimension ratings?

Run scripts/calculate_scores.py with a JSON file of dimension scores to compute a weighted average, quality level, and ASCII bar chart report. Use --interactive to enter scores manually or --weights to supply custom dimension weights.

What dimensions does ScholarEval use to assess research quality?

The framework covers problem formulation, literature review, methodology, data collection, analysis, results, scholarly writing, and citations. Default weights emphasize methodology at 20 percent and citations at 5 percent.

Can the evaluation adjust for different venues or work stages?

Yes, the framework supports contextual adjustments for early drafts versus final submissions, student work versus top-tier journals, and discipline-specific norms such as reproducibility emphasis in STEM fields.

What are the limitations of automated scholarly evaluation?

The framework complements rather than replaces domain expertise and peer review. Some dimensions may not apply to all work types, such as data collection for purely theoretical papers, and cultural or disciplinary norms require human judgment.