scholar-evaluation
scholar-evaluation is a Peer review & grants skill for AI agents, published by K-Dense-AI in the claude-scientific-writer repository on GitHub. Skillspace rates scholar-evaluation B (87/100) and it passed the safety scan; a judge model has also reviewed it.
Systematically evaluate scholarly and research work using the ScholarEval framework. Use when evaluating research papers, proposals, or literature reviews for quality and rigor, scoring methodology and analysis, assessing publication readiness for target venues, or providing structured quantitative feedback to complement qualitative peer review.
- Grade
- B
- Quality
- 87 / 100
- Safety
- Passed
- GitHub stars
- 2,117
Placed #5 of 6 in the judged category final for Peer review & grants.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 100 / 100
- Maturity
- Packaged: licensed, with a version or references
- Security scan
- No issues found
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 3 collections
- Scope
- Portable: works in any project. General academic paper/proposal evaluation framework, usable anywhere.
Judge review
Placed #5 of 6 in the judged category final for Peer review & grants.
- Trigger
80 80 - Instructions
70 70 - Specificity
69 69 - Safety
61 61 - Disclosure
52 52 - Maintenance
40 40
A reasonable eight-dimension evaluation rubric with an external framework reference, diluted by a large unrelated pitch for generating schematics through a different skill.
Same eight well-defined evaluation dimensions and the same off-topic default to auto-generate schematics, but its own invocation path for that script does not point anywhere inside this skill.
Not checked yet
- No blind task eval yet
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.