zarr-python

Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.

Install with Tessl CLI

npx tessl i github:K-Dense-AI/claude-scientific-skills --skill zarr-python

What are skills?

1.25x

Quality

48%

Does it follow best practices?

Impact

90%

1.25x

Average score across 6 eval scenarios

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/zarr-python/SKILL.md

SKILL.md

Review

Evals

Quality

Discovery

32%

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 identifies a specific technical domain (chunked N-D arrays for cloud storage) and lists relevant integrations, but reads more like a feature list than actionable guidance. It critically lacks any 'Use when...' clause to help Claude know when to select this skill, and uses noun phrases instead of action verbs to describe capabilities.

Suggestions

Add an explicit 'Use when...' clause with trigger scenarios like 'Use when working with Zarr files, storing large arrays in S3/GCS, or when the user mentions chunked arrays, cloud-based array storage, or Zarr format'

Convert noun phrases to action verbs: 'Store and retrieve chunked N-D arrays in cloud storage, compress array data, perform parallel I/O operations'

Include the library name (Zarr) prominently as a key trigger term users would naturally mention

Dimension	Reasoning	Score
Specificity	Names the domain (chunked N-D arrays, cloud storage) and lists some capabilities (compressed arrays, parallel I/O, S3/GCS integration), but uses noun phrases rather than concrete action verbs describing what the skill does.	2 / 3
Completeness	Describes what the skill relates to but completely lacks a 'Use when...' clause or any explicit trigger guidance. There is no indication of when Claude should select this skill over others.	1 / 3
Trigger Term Quality	Includes relevant technical terms like 'S3', 'GCS', 'NumPy', 'Dask', 'Xarray', 'chunked arrays' that users might mention, but missing the library name (likely Zarr) and common variations users might say like 'array storage', 'cloud arrays', or 'distributed arrays'.	2 / 3
Distinctiveness Conflict Risk	The combination of chunked arrays, cloud storage, and specific library compatibility (NumPy/Dask/Xarray) provides some distinctiveness, but could overlap with general cloud storage skills or NumPy/array processing skills without clearer boundaries.	2 / 3
	Total	7 / 12 Passed

Implementation

64%

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

This is a comprehensive, highly actionable Zarr skill with excellent executable code examples covering the full API surface. The main weaknesses are verbosity (could be 30% shorter by removing explanations of concepts Claude knows) and the monolithic structure that would benefit from splitting advanced topics into separate files. Workflow clarity could be improved with explicit validation steps for multi-step operations.

Suggestions

Remove explanatory text Claude already knows (e.g., 'Chunking is critical for performance', 'Zarr applies compression per chunk to reduce storage') and let the code examples speak for themselves

Split advanced topics (Integration with NumPy/Dask/Xarray, Common Patterns, Performance Optimization) into separate reference files with brief summaries and links in the main SKILL.md

Add explicit validation steps to multi-step workflows, e.g., 'Verify write succeeded: assert z.nbytes_stored > 0' after cloud writes

Consolidate the 'Common Issues and Solutions' section into a troubleshooting reference file to reduce main document length

Dimension	Reasoning	Score
Conciseness	The skill is comprehensive but includes some unnecessary explanations Claude would know (e.g., explaining what chunking is, what compression does). Some sections like 'Benefits' lists could be trimmed. The content is mostly efficient but could be tightened by ~30%.	2 / 3
Actionability	Excellent executable code examples throughout - all snippets are copy-paste ready with proper imports, realistic parameters, and complete syntax. Covers creation, reading, writing, cloud storage, and integration patterns with fully working code.	3 / 3
Workflow Clarity	While individual operations are clear, multi-step workflows lack explicit validation checkpoints. For example, the cloud-native workflow pattern doesn't include verification that data was written correctly. The 'Common Issues and Solutions' section helps but workflows could benefit from explicit 'verify before proceeding' steps.	2 / 3
Progressive Disclosure	The document is well-structured with clear sections, but it's monolithic at ~600 lines. Content like 'Common Patterns', 'Integration with NumPy/Dask/Xarray', and 'Common Issues' could be split into separate reference files. The 'Additional Resources' section at the end is good but inline references to separate docs would improve navigation.	2 / 3
	Total	9 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (778 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning

	Total	9 / 11 Passed

Reviewed: 1 day 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.