CtrlK
BlogDocsLog inGet started
Tessl Logo

neurokit

Comprehensive biosignal processing for ECG/PPG/EEG/EDA/RSP/EMG/EOG; use when you need to clean, segment, and extract physiological features for HRV, event-related responses, complexity metrics, or multimodal psychophysiology pipelines.

67

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

76%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is actionable and well-structured, with a complete runnable example and clear pointers to per-modality reference files. Its main gaps are the total absence of validation/verification checkpoints in the processing workflow and a couple of minor navigation inconsistencies.

Suggestions

Add validation/verification checkpoints to the pipeline pattern (e.g., inspect ecg_info['ECG_R_Peaks'] to confirm peak detection, or run a signal-quality check before computing HRV) and an error-recovery note for failed analyses.

Include references/ppg.md in the reference docs list on line 19, since PPG is listed under Key Features, and format the reference paths as markdown links for easier navigation.

Tighten the 'Analysis mode selection' and 'HRV domains and inputs' prose to the essential neurokit2-specific behavior to improve token efficiency.

DimensionReasoningScore

Conciseness

The body is efficient and free of generic editorial fluff, leaning on a runnable example plus neurokit2-specific patterns; minor prose in the "Analysis mode selection" and "HRV domains" sections could be trimmed without losing value, placing it just above the midpoint.

4 / 5

Actionability

Provides a fully executable, copy-paste-ready example that simulates signals, runs ecg_process/hrv, bio_process/bio_analyze, and event-related epoching, plus concrete smaller snippets for filtering and complexity that cover the common cases.

5 / 5

Workflow Clarity

A clear numbered sequence and pipeline pattern (process -> analyze -> hrv) are present, but there are no validation or verification checkpoints (e.g., confirm R-peak detection, check signal quality), and biosignal batch processing warrants such feedback, capping it at 3.

3 / 5

Progressive Disclosure

Good sectioning with eleven real one-level-deep reference files clearly signaled and content appropriately split between overview and references; minor gaps keep it from a 5: the reference list is plain paths rather than links and references/ecg_ppg exists but ppg.md is absent from the body's reference list despite PPG being a listed feature.

4 / 5

Total

16

/

20

Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is well-constructed: it states a precise niche, enumerates concrete actions and feature outputs, and includes an explicit "use when" trigger clause. The only minor weakness is slight buzzword padding ("Comprehensive") and missing a few lay synonyms.

DimensionReasoningScore

Specificity

Lists several concrete actions ("clean, segment, and extract physiological features") across named feature outputs (HRV, event-related responses, complexity metrics), but the leading word "Comprehensive" is mild fluff and the three verbs are somewhat generic, so it sits just below the fully comprehensive anchor.

4 / 5

Completeness

Explicitly answers both what ("Comprehensive biosignal processing for ECG/PPG/EEG/EDA/RSP/EMG/EOG") and when ("use when you need to clean, segment, and extract physiological features for HRV, event-related responses, complexity metrics, or multimodal psychophysiology pipelines") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong keyword coverage with all seven modality acronyms (ECG/PPG/EEG/EDA/RSP/EMG/EOG) plus HRV and "biosignal processing", which are exactly what users say; a few natural forms are missing (e.g., spelled-out "heart rate variability", "stress", "arousal"), keeping it just short of comprehensive.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (physiological biosignal processing for named modalities) with distinct triggers that would not fire for general data or document skills, giving minimal conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
aipoch/medical-research-skills
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.