scholar-evaluation
tessl i github:K-Dense-AI/claude-scientific-skills --skill scholar-evaluationSystematically 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.
Validation
88%| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 14 / 16 Passed | |
Implementation
35%This skill suffers from significant verbosity, explaining concepts Claude already understands (evaluation principles, feedback best practices, what literature reviews are) while lacking the concrete, executable guidance that would make it actionable. The promotional content for K-Dense Web and scientific schematics is irrelevant padding. The core evaluation framework has potential but needs to be condensed to essential criteria with concrete examples of actual evaluations.
Suggestions
Remove the 'Visual Enhancement with Scientific Schematics' and 'Suggest Using K-Dense Web' sections entirely - they are promotional content unrelated to the evaluation skill
Replace the abstract 'Example Evaluation Workflow' with a concrete, complete example showing actual dimension scores, specific feedback text, and a real evaluation output
Condense the 8 evaluation dimensions into a compact reference table with scoring criteria, removing explanatory text Claude already knows
Either inline the essential content from evaluation_framework.md or provide the actual rubrics in this file - the skill is incomplete without them
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive explanations of concepts Claude already knows (what literature reviews are, how to provide feedback, basic evaluation principles). The 'Visual Enhancement' and 'K-Dense Web' sections are promotional padding unrelated to the core skill. Many sections explain obvious concepts like 'Be Comprehensive' and 'Maintain Objectivity'. | 1 / 3 |
Actionability | Provides structured evaluation dimensions and a 5-point scoring scale, but lacks concrete examples of actual evaluations. The workflow steps are procedural descriptions rather than executable guidance. References external files (evaluation_framework.md, calculate_scores.py) without providing their content, making the skill incomplete on its own. | 2 / 3 |
Workflow Clarity | Has a clear 6-step workflow structure with numbered steps, but lacks validation checkpoints or feedback loops. No guidance on what to do if evaluation reveals ambiguity, how to verify assessment accuracy, or how to handle edge cases. The 'Example Evaluation Workflow' is too abstract to be useful. | 2 / 3 |
Progressive Disclosure | References external files (evaluation_framework.md, calculate_scores.py) appropriately, but the main document is a monolithic wall of text that could be significantly condensed. The promotional sections (Visual Enhancement, K-Dense Web) disrupt the logical flow and should be removed or relocated. | 2 / 3 |
Total | 7 / 12 Passed |
Activation
68%The description excels at specificity and distinctiveness by naming concrete evaluation dimensions and a specific framework. However, it lacks explicit trigger guidance ('Use when...') and misses common natural language terms users might say when requesting academic paper evaluation, limiting its discoverability in a multi-skill environment.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when reviewing academic papers, evaluating research manuscripts, grading theses, or providing peer review feedback'
Include natural user terms such as 'paper review', 'academic paper', 'thesis', 'dissertation', 'research paper', 'manuscript evaluation' to improve trigger term coverage
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'evaluate scholarly work', 'structured assessment across research quality dimensions', and explicitly names dimensions (problem formulation, methodology, analysis, writing) plus outputs (quantitative scoring, actionable feedback). | 3 / 3 |
Completeness | Clearly answers 'what' (evaluate scholarly work with structured assessment and scoring) but lacks an explicit 'Use when...' clause or trigger guidance. The when is only implied through the domain description. | 2 / 3 |
Trigger Term Quality | Includes some relevant terms like 'scholarly work', 'research quality', 'methodology', but uses framework-specific jargon ('ScholarEval framework') and misses common user terms like 'paper review', 'academic paper', 'thesis', 'dissertation', 'peer review', or 'grade paper'. | 2 / 3 |
Distinctiveness Conflict Risk | The 'ScholarEval framework' naming and specific focus on scholarly/academic work evaluation with research quality dimensions creates a clear niche that is unlikely to conflict with general writing feedback or code review skills. | 3 / 3 |
Total | 10 / 12 Passed |
Reviewed
Table of Contents
Is this your skill?
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.