scholar-evaluation
affaan-m/everything-claude-code
Structured rubric-based evaluation of academic papers, proposals, and research writing.
What is scholar-evaluation?
This skill provides a repeatable 9-dimension rubric for evaluating scholarly work including research papers, proposals, literature reviews, and theses. Use it to assess problem clarity, literature coverage, methodology, data quality, analysis rigor, results interpretation, limitations, writing, and citation support—then produce actionable revision feedback.
- Score research artifacts across 9 dimensions (problem, literature, methodology, data, analysis, results, limitations, writing, citations) on a 1–5 scale
- Identify critical blockers versus revision suggestions with evidence for each score
- Verify that cited sources actually support attached claims
- Compare multiple papers against the same rubric for ranking or selection
- Generate structured feedback tables and concrete next-edit recommendations
How to install scholar-evaluation
npx skills add https://github.com/affaan-m/everything-claude-code --skill scholar-evaluationHow to use scholar-evaluation
- 1.Identify the artifact type (empirical paper, proposal, review, thesis chapter, etc.)
- 2.Choose evaluation scope: comprehensive (all dimensions), targeted (1–2 dimensions), or comparative (rank multiple works)
- 3.Read the abstract, introduction, figures, and conclusion to understand the claimed contribution
- 4.Read methods and results sections for evidence quality and reproducibility
- 5.Check the strongest claims against their cited sources for accuracy and support
- 6.Score each applicable dimension 1–5 using the rubric; mark N/A if not applicable
- 7.Separate critical blockers from revision suggestions with specific evidence
- 8.Output results in the provided markdown template with dimension scores, critical issues, and concrete next edits
Use cases
- Review a submitted research paper or thesis chapter before publication or defense
- Evaluate a grant proposal or conference abstract for methodological rigor and clarity
- Check whether a literature review synthesizes sources or merely lists them
- Assess data quality and bias risks in an empirical study
- Compare two competing papers on the same topic for relevance and evidence strength
- Academic researchers and PhD students
- Journal editors and peer reviewers
- Grant program officers and proposal evaluators
- Thesis advisors and committee members
- Research teams conducting internal quality checks
scholar-evaluation FAQ
No. Use N/A for dimensions outside the artifact's scope. A theoretical paper may not need a data section; a methods review may not need original results.
Check whether cited papers actually support the attached claims by reading abstracts or relevant sections. Flag unsupported claims and missing foundational references in the Citations dimension.
Honest reporting of negative results is a strength, not a weakness. Score based on whether the null result is clearly presented, properly analyzed, and interpreted without overreach.
Yes. Use comparative scope: apply the same rubric to multiple papers, then rank them by overall score and dimension strengths to identify the most rigorous and relevant sources.
A critical blocker prevents publication or defense (e.g., unsupported claims, invalid methodology, missing ethics approval). A revision suggestion improves clarity or rigor but does not invalidate the work.
Full instructions (SKILL.md)
Source of truth, from affaan-m/everything-claude-code.
name: scholar-evaluation description: Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback. metadata: origin: community
Scholar Evaluation
Use this skill to evaluate academic or scientific work with a repeatable rubric.
When to Use
- Reviewing a research paper, proposal, thesis chapter, or literature review.
- Checking whether claims are supported by cited evidence.
- Evaluating methodology, study design, analysis, or limitations.
- Comparing two or more papers for quality or relevance.
- Producing structured feedback for revision.
Evaluation Scope
Start by identifying the artifact:
- empirical research paper
- theoretical paper
- technical report
- systematic or narrative literature review
- research proposal
- thesis or dissertation chapter
- conference abstract or short paper
Then choose scope:
- comprehensive: all rubric dimensions
- targeted: one or two dimensions, such as method or citations
- comparative: rank multiple works against the same rubric
Rubric
Score each applicable dimension from 1 to 5:
- 5: excellent; clear, rigorous, and publication-ready
- 4: good; minor improvements needed
- 3: adequate; meaningful gaps but usable
- 2: weak; substantial revision needed
- 1: poor; major validity or clarity problems
Use N/A for dimensions that do not apply.
1. Problem and Research Question
- Is the problem clear and specific?
- Is the contribution meaningful?
- Are scope and assumptions explicit?
- Does the question match the claimed contribution?
2. Literature and Context
- Is relevant prior work covered?
- Does the work synthesize rather than merely list sources?
- Are gaps accurately identified?
- Are recent and foundational sources balanced?
3. Methodology
- Does the method answer the research question?
- Are design choices justified?
- Are variables, datasets, participants, or materials described clearly?
- Could another researcher reproduce the work?
- Are ethical and practical constraints acknowledged?
4. Data and Evidence
- Are data sources credible and appropriate?
- Is sample size or corpus coverage adequate?
- Are inclusion, exclusion, and preprocessing decisions documented?
- Are missing data and bias risks discussed?
5. Analysis
- Are statistical, qualitative, or computational methods appropriate?
- Are baselines and controls fair?
- Are uncertainty, sensitivity, or robustness checks included when needed?
- Are alternative explanations considered?
6. Results and Interpretation
- Are results clearly presented?
- Do claims stay within the evidence?
- Are figures, tables, and metrics understandable?
- Are negative or null results handled honestly?
7. Limitations and Threats to Validity
- Are limitations specific rather than generic?
- Are internal, external, construct, and conclusion-validity risks addressed?
- Does the paper distinguish speculation from demonstrated results?
8. Writing and Structure
- Is the argument easy to follow?
- Are sections organized around the research question?
- Are definitions and notation clear?
- Is the tone precise and scholarly?
9. Citations
- Do cited papers support the claims attached to them?
- Are primary sources used where possible?
- Are reviews labeled as reviews?
- Are preprints labeled as preprints?
- Are citation metadata and links correct?
Review Process
- Read the abstract, introduction, figures, and conclusion for claimed contribution.
- Read methods and results for evidence quality.
- Check the strongest claims against cited sources.
- Score each applicable dimension.
- Separate critical blockers from revision suggestions.
- End with concrete next edits.
Output Template
# Scholar Evaluation: <Artifact>
## Overall Assessment
- Overall score: <1-5 or N/A>
- Confidence: <high | medium | low>
- Summary: <3-5 sentences>
## Dimension Scores
| Dimension | Score | Evidence | Revision priority |
| --- | ---: | --- | --- |
| Problem and question | | | |
| Literature and context | | | |
| Methodology | | | |
| Data and evidence | | | |
| Analysis | | | |
| Results and interpretation | | | |
| Limitations | | | |
| Writing and structure | | | |
| Citations | | | |
## Critical Issues
## Recommended Revisions
## Evidence Checks Needed
Pitfalls
- Do not use the score as a substitute for concrete feedback.
- Do not penalize a paper for omitting a dimension outside its scope.
- Do not treat citation count, venue, or author reputation as proof of quality.
- Do not accept unsupported claims just because they appear in the abstract.
Related skills
More from affaan-m/everything-claude-code and the wider catalog.

search-first
Search for existing tools and libraries before writing custom code.

security-bounty-hunter
Hunt exploitable, bounty-worthy security vulnerabilities in code repositories with minimal noise.

security-review
Security checklist and patterns for authentication, input validation, secrets, and sensitive features.

security-scan
Audit Claude Code configuration for security vulnerabilities, misconfigurations, and injection risks using AgentShield.

seo
Audit and optimize technical SEO, on-page elements, structured data, and content strategy for better search visibility.

skill-comply
Measure whether coding agents actually follow skills, rules, and agent definitions across varying prompt conditions.