Systematically evaluate scholarly work using the ScholarEval framework, providing structured assessment across research quality dimensions including problem formulation, methodology, analysis, and writing with quantitative scoring and actionable feedback.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill scholar-evaluation77
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 92%
↑ 1.67xAgent success when using this skill
Validation for skill structure
Programmatic score calculation with 8-dimension framework
All 8 dimensions present
41%
100%
5-point scale used
100%
100%
Correct score JSON keys
0%
100%
calculate_scores.py invoked
66%
100%
Output report produced
50%
100%
Quality threshold interpretation
0%
100%
Dimension weights reflected
0%
100%
Scores within valid range
100%
100%
Evaluation covers paper content
100%
100%
Workflow steps documented
90%
100%
Without context: $0.7062 · 3m 11s · 30 turns · 146 in / 11,903 out tokens
With context: $0.8114 · 2m 27s · 26 turns · 11,772 in / 7,993 out tokens
Qualitative per-dimension assessment and overall synthesis
Per-dimension strengths count
0%
58%
Per-dimension weaknesses count
0%
83%
Overall major strengths 3-5
0%
100%
Overall critical weaknesses 3-5
40%
20%
Prioritized recommendations present
100%
100%
Specific section references
100%
100%
Actionable suggestions
100%
100%
Balanced tone
25%
100%
Evidence-based grounding
60%
80%
Overall quality assessment present
37%
100%
Without context: $0.2278 · 1m 37s · 11 turns · 16 in / 4,622 out tokens
With context: $0.8728 · 3m 21s · 24 turns · 11,562 in / 10,283 out tokens
Contextual evaluation adjustments and structured feedback format
Work type identified
87%
100%
Student/educational focus
90%
100%
Stage-appropriate standards
90%
100%
Output named SCHOLAR_EVALUATION.md
0%
100%
Discipline-specific norms applied
80%
100%
Venue-adjusted standards
50%
100%
8 dimensions covered
40%
100%
Publication readiness section
60%
40%
Priority recommendations ranked
100%
100%
Does not use peer review tone
100%
100%
Without context: $0.2325 · 1m 42s · 10 turns · 14 in / 4,543 out tokens
With context: $0.8907 · 3m 44s · 24 turns · 6,973 in / 11,291 out tokens
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.