neuropixels-analysis
Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.
88
86%
Does it follow best practices?
Impact
91%
1.37xAverage 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 thoroughly covers specific capabilities, includes comprehensive trigger terms natural to the neuroscience domain, and clearly delineates both what the skill does and when to use it. The description is highly distinctive due to its specialized domain focus, and it uses proper third-person voice throughout. It closely matches the rubric's examples of good descriptions.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis. Very detailed and actionable. | 3 / 3 |
Completeness | Clearly answers both 'what' (load data, preprocess, motion correction, spike sorting, quality metrics, curation, visual analysis) and 'when' with an explicit 'Use when...' clause listing specific trigger scenarios and terms. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms a neuroscience user would say: Neuropixels, SpikeGLX, Open Ephys, Kilosort, spike sorting, neural recordings, extracellular electrophysiology, quality metrics, unit curation. These are the exact terms domain users would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche skill targeting Neuropixels electrophysiology specifically. The combination of domain-specific tools (SpikeGLX, OpenEphys, Kilosort4) and hardware (Neuropixels 1.0/2.0) makes it extremely unlikely to conflict with other skills. | 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 with strong actionability and excellent progressive disclosure through clearly signaled reference documents. The main weaknesses are moderate verbosity (sections like 'When to Use This Skill', hardware tables, and installation instructions that don't add value for Claude) and incomplete validation checkpoints in the multi-step workflow beyond the drift check.
Suggestions
Remove or significantly trim the 'When to Use This Skill', 'Supported Hardware & Formats', 'Installation', and 'Project Structure' sections - these are either redundant with frontmatter, basic knowledge, or better placed in a reference file.
Add explicit validation checkpoints after spike sorting (e.g., check unit count, verify no empty sorting) and after postprocessing (verify extensions computed successfully) to create proper feedback loops for error recovery.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary sections like 'When to Use This Skill' (which repeats the frontmatter description), the 'Supported Hardware & Formats' table (Claude knows Neuropixels specs), installation instructions (standard pip commands), and project structure (conventional layout). However, the core workflow sections are reasonably efficient with good code examples. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste ready code examples throughout - from loading data through preprocessing, spike sorting, postprocessing, curation, and export. CLI commands for bundled scripts are concrete and specific. Quality metric queries use actual pandas syntax with real threshold values. | 3 / 3 |
Workflow Clarity | The 8-step workflow is clearly sequenced and includes a drift validation checkpoint (step 2 with the >10μm threshold). However, there are no validation/verification steps after spike sorting, no error recovery guidance if sorting fails, and no checkpoint after postprocessing to verify analyzer extensions computed correctly. For a complex multi-step pipeline involving potentially destructive batch operations, the feedback loops are insufficient. | 2 / 3 |
Progressive Disclosure | Excellent structure with a concise quick-start overview, a standard workflow with inline code, and a well-organized reference table pointing to 10+ detailed guides (all one level deep). Bundled scripts are listed with usage examples. The split between SKILL.md overview and reference/ files is well-signaled and appropriate. | 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
b58ad7e
- 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.