scholar-evaluation_skill

This skill systematically evaluates scholarly work using the ScholarEval framework, delivering structured quality assessments, actionable feedback, and

Python

7.4k

GitHub Stars

1

Bundled Files

3 weeks ago

Catalog Refreshed

2 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstart where the catalogue uses aiagentskills.

npx veilstart add skill k-dense-ai/claude-scientific-skills --skill scholar-evaluation

SKILL.md12.8 KB

Overview

This skill systematically evaluates scholarly work using the ScholarEval framework, producing structured assessments across core research quality dimensions. It returns dimension-level scores, concise qualitative summaries, and prioritized, actionable feedback to guide revision and publication decisions. The output is suitable for authors, reviewers, and research managers seeking objective, evidence-based critiques.

How this skill works

The skill inspects a submitted document or description and applies a rubric covering problem formulation, literature, methodology, data, analysis, results, writing, and citations. For each dimension it identifies strengths, weaknesses, and critical issues, assigns a 1–5 score, and generates prioritized, actionable recommendations. It can produce full structured reports, annotated comments tied to sections, or concise executive summaries depending on scope.

When to use it

Preparing a manuscript for journal or conference submission
Conducting a review of a research proposal or grant application
Benchmarking research quality across competing projects
Generating constructive feedback for student theses or drafts
Complementing peer review with quantitative scoring and evidence-backed suggestions

Best practices

Define the evaluation scope up front (comprehensive, targeted, or comparative)
Ground assessments in explicit rubric criteria and cite document locations for examples
Prioritize high-impact fixes first to maximize revision efficiency
Adjust expectations to the work stage (early draft vs final submission)
Provide balanced feedback: acknowledge strengths while listing concrete fixes

Example use cases

Full paper evaluation: dimension scores, summary of major strengths, and prioritized revision list
Methodology audit: focused review of experimental design, reproducibility, and ethical considerations
Literature review check: assess coverage, synthesis quality, and gap identification
Publication readiness check: assess fit for target venue and list required improvements
Iterative review: re-evaluate updated drafts to track score changes and persistent issues

FAQ

Yes. The evaluation adapts: dimensions like data collection may be marked not applicable and emphasis shifts to argumentation, theory, and contribution.

How are scores calculated and interpreted?

Scores use a 1–5 scale (1 poor to 5 excellent). Dimension-level scores can be aggregated using weighted averages; scripts are available to compute aggregates and visualizations.