neuropixels-analysis

Analyze Neuropixels extracellular recordings end-to-end with SpikeInterface. Covers loading SpikeGLX/Open Ephys/NWB data, preprocessing, drift/motion correction, Kilosort4 (and CPU) spike sorting, quality metrics, and unit curation (threshold-based, model-based UnitRefine, and AI-assisted visual review). Use when working with Neuropixels 1.0/2.0 recordings, spike sorting, or extracellular electrophysiology analysis.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

72%

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 with excellent progressive disclosure and copy-paste-ready code. The main gaps are mild verbosity/redundancy between the inline workflow and the bundled references, and only implicit validation feedback loops in the multi-step pipeline.

Suggestions

Tighten the inline 8-step workflow by summarizing steps that are fully covered in references/standard_workflow.md and the bundled scripts, keeping only the quick-start essentials and pointers, to reduce overlap and token cost (addresses conciseness).

Add explicit validation checkpoints and a feedback loop in the pipeline section — e.g. 'after preprocessing, verify bad-channel count; after sorting, check unit count vs. expected; if drift > 10 um, re-run correct_motion and re-sort' — to lift workflow_clarity to a 3.

Mark which steps the bundled neuropixels_pipeline.py performs automatically versus which require interactive inspection, so Claude knows where human-in-the-loop validation is expected.

Dimension	Reasoning	Score
Conciseness	The body is largely actionable code and domain-specific API detail Claude does not already know (exact function names, presets, the isi_violations_ratio column), but it runs ~400 lines and the 8-step inline workflow overlaps content already in references/standard_workflow.md and the bundled scripts, so it could be tightened; not level 3 because not 'every token earns its place', not level 1 because it is not padded with general concepts Claude knows.	2 / 3
Actionability	Fully executable, copy-paste-ready code throughout (e.g. si.read_spikeglx(...), si.correct_motion(preset=...), the pipeline command 'python scripts/neuropixels_pipeline.py ... /path/ output/ --sorter kilosort4 --curation allen') with specific runnable scripts, matching the level-3 anchor.	3 / 3
Workflow Clarity	A clear 8-step sequence (load -> preprocess -> drift -> sort -> postprocess -> metrics -> curation -> export) with some validation gates ('Always inspect drift before sorting', detect_bad_channels, trust_model warnings, review uncertain units) is present, but explicit error-recovery feedback loops (validate -> fix -> retry) and hard checkpoints are only implicit, so it sits at level 2 rather than 3.	2 / 3
Progressive Disclosure	SKILL.md is a concise overview with a well-signaled one-level-deep reference table (10 reference files, all verified present as real files in references/), documented scripts/ and assets/, and appropriately split detail; matches the level-3 anchor rather than the inline-bloated level 2.	3 / 3
	Total	10 / 12 Passed

Description

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.

A strong description: concrete third-person action list, natural trigger terms, explicit 'Use when' clause, and a clearly distinct niche. No meaningful weakness to address.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions in third person — 'loading SpikeGLX/Open Ephys/NWB data, preprocessing, drift/motion correction, Kilosort4 (and CPU) spike sorting, quality metrics, and unit curation' — matching the 'lists multiple specific concrete actions' anchor rather than the single-action level 2.	3 / 3
Completeness	Explicitly states both what ('Analyze...end-to-end', 'Covers loading...unit curation') and when ('Use when working with Neuropixels 1.0/2.0 recordings, spike sorting, or extracellular electrophysiology analysis'), matching the level-3 anchor; level 2 lacks the explicit 'Use when' trigger which is present here.	3 / 3
Trigger Term Quality	Uses natural domain terms a user would actually say — 'Neuropixels 1.0/2.0 recordings, spike sorting, extracellular electrophysiology analysis' — giving good coverage rather than the partial-keyword level 2.	3 / 3
Distinctiveness Conflict Risk	Highly niche (Neuropixels + SpikeInterface spike sorting with named sorters and UnitRefine models) with distinct triggers unlikely to fire for unrelated skills; level 2 implies residual overlap, which is not the case here.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/neuropixels-analysis/SKILL.md
Commit: 757b63b

Reviewed: about 12 hours ago

Table of Contents

Discovery Implementation Validation

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.