neurokit2
Comprehensive biosignal processing toolkit for analyzing physiological data including ECG, EEG, EDA, RSP, PPG, EMG, and EOG signals. Use this skill when processing cardiovascular signals, brain activity, electrodermal responses, respiratory patterns, muscle activity, or eye movements. Applicable for heart rate variability analysis, event-related potentials, complexity measures, autonomic nervous system assessment, psychophysiology research, and multi-modal physiological signal integration.
90
86%
Does it follow best practices?
Impact
99%
1.80xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly defines a specialized domain (biosignal processing), lists concrete signal types and analysis methods, and provides explicit trigger guidance via 'Use this skill when...' and 'Applicable for...' clauses. The description uses appropriate third-person voice and includes both acronyms and descriptive terms that users in this domain would naturally use. It is a strong example of a well-crafted skill description.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and signal types: ECG, EEG, EDA, RSP, PPG, EMG, EOG processing, heart rate variability analysis, event-related potentials, complexity measures, autonomic nervous system assessment, and multi-modal signal integration. | 3 / 3 |
Completeness | Clearly answers both 'what' (comprehensive biosignal processing toolkit for analyzing physiological data) and 'when' (explicit 'Use this skill when...' clause covering multiple trigger scenarios, plus 'Applicable for...' providing additional use-case triggers). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms a user would say: includes both abbreviations (ECG, EEG, EDA, PPG, EMG, EOG) and descriptive terms (cardiovascular signals, brain activity, electrodermal responses, respiratory patterns, heart rate variability, psychophysiology). These are the exact terms researchers and engineers would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche in biosignal/physiological data processing with very specific domain terminology (ECG, EEG, HRV, event-related potentials, psychophysiology). Extremely unlikely to conflict with other skills given the specialized vocabulary. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill that serves as an effective overview and entry point for NeuroKit2's extensive capabilities. Its main strengths are excellent progressive disclosure with clear references to detailed documentation and fully executable code examples. The main weaknesses are moderate verbosity (some sections could be tightened) and lack of validation/error-handling guidance for a domain where signal quality issues are common.
Suggestions
Add signal quality validation steps to workflows (e.g., checking nk.ecg_quality() output before proceeding with analysis, handling poor-quality segments).
Trim the 'When to Use This Skill' section since it largely duplicates the section headers, and condense the enumerated lists of available measures (entropy types, fractal dimensions) since these are already in the referenced files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is well-organized but quite verbose for what is essentially an API reference. Many sections repeat the same pattern (description + key functions) and the 'When to Use This Skill' section largely duplicates the Overview and section headers. The enumeration of all available measures (entropy types, fractal dimensions, etc.) adds bulk that Claude could look up in the referenced files. | 2 / 3 |
Actionability | All code examples are executable and copy-paste ready with proper imports, function calls, and parameter specifications. The examples cover the full range of signal types with concrete sampling rates and realistic usage patterns. | 3 / 3 |
Workflow Clarity | The 'Common Workflows' section provides clear step sequences (load → process → analyze → visualize), and the ECG pipeline mentions cleaning → R-peak detection → delineation → quality assessment. However, there are no validation checkpoints, error handling guidance, or feedback loops for when signal quality is poor or processing fails—important for physiological signal processing where noisy data is common. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear overview in the main file and well-signaled one-level-deep references to 12 specific reference files organized by signal type. Each section points to its detailed reference file, and the References section provides a complete index with descriptions. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
25e1c0f
- 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.