CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

A well-structured, highly actionable skill body: a complete runnable example, a clearly explained processing pattern, and detail correctly pushed to reference files. Weaknesses are minor — slight redundancy across feature lists and one orphaned bundle reference file.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence — no padding explaining what ECG or HRV is, and sections are tight with runnable code. Minor over-explanation exists: the "Key Features" bullet list overlaps with "When to Use" and "Implementation Details", and could be trimmed. Not a 3 because there is no genuinely unnecessary concept explanation.

4 / 5

Actionability

The "Example Usage" section is a complete, copy-paste-ready script covering simulation, ECG processing, HRV, multimodal bio_process/bio_analyze, and event-related epoching; install commands and concrete API calls with parameters (e.g., nk.signal_filter with lowcut/highcut) cover the common cases. This matches the fully-executable anchor.

5 / 5

Workflow Clarity

"Implementation Details" gives a clear typical pattern (process → analyze → hrv), explains event-related vs interval-related mode selection, and sequences the event workflow (events_find → epochs_create → epochs_average). Not a 5 because there are no explicit validation checkpoints (e.g., verifying peak-detection quality before computing HRV); not a 3 because the sequences are well defined and the operations are non-destructive analysis.

4 / 5

Progressive Disclosure

SKILL.md is a proper overview: quick start example inline, bulk detail split into one-level-deep reference files that are listed by path and signaled inline ("see references/signal_processing.md", "see references/complexity.md"). Scored against the actual bundle, one reference file (references/ppg.md) exists but is never listed or referenced in the body — a minor organization gap that keeps this below the clear, fully-signaled anchor.

4 / 5

Total

17

/

20

Passed

Description

82%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.

A strong description that explicitly states both capabilities and use triggers with rich domain-specific vocabulary. Its main deductions are the second-person trigger phrasing ("use when you need to") and some missing natural synonyms for the modality acronyms.

Suggestions

Rewrite the trigger clause in third person to match the anchor style, e.g., "Use when the user needs to clean, segment, or extract features from physiological signals" instead of "use when you need to".

Add spelled-out synonyms for the acronym-heavy vocabulary, such as "heart rate variability (HRV)" and "electrodermal activity / galvanic skin response", so users who type the long-form terms match the trigger naturally.

DimensionReasoningScore

Specificity

The description lists several specific actions ("clean, segment, and extract physiological features for HRV, event-related responses, complexity metrics, or multimodal psychophysiology pipelines"), which fits the anchor for several specific actions with minor coverage gaps (base 4). However, the trigger clause "use when you need to" is second-person voice, which the judging guidelines penalize by reducing the specificity score by 1. Not a 2 because the domain and actions are concrete, not minimal or generic.

3 / 5

Completeness

Both questions are explicitly answered: 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"). This matches the anchor that clearly and explicitly answers both what and when with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural keywords a specialist would actually say: "ECG", "PPG", "EEG", "EDA", "EMG", "EOG", "HRV", "biosignal", "psychophysiology". A few natural variations are missing (e.g., "heart rate variability" spelled out, "electrodermal activity", "galvanic skin response"), so it does not reach comprehensive synonym coverage; clearly above having only some relevant keywords.

4 / 5

Distinctiveness Conflict Risk

The modality-specific acronyms (ECG/PPG/EEG/EDA/RSP/EMG/EOG) and terms like HRV and psychophysiology carve out a clear niche with distinct triggers and minimal conflict risk with unrelated skills; it is not merely broad or overlapping like "works with document files".

5 / 5

Total

17

/

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.

Validation — 15 / 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

Path

scientific-skills/Data Analysis/neurokit2/SKILL.md

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.