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.

Quality

61%

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

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/zarr-python/SKILL.md

Quality

Content

57%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 content is highly actionable with broad executable examples and good section structure, but it is over-long with some redundant explanation of familiar concepts, lacks explicit validation feedback loops, and fails to point to the bundled api_reference.md.

Suggestions

Trim or relocate familiar explanations (e.g., what Dask/Xarray/Groups are) and de-duplicate the chunking guidance spread across 'Chunking Strategies', 'Performance Optimization', and 'Common Issues' to improve conciseness.

Add explicit validation/verification steps for cloud writes and parallel/concurrent write workflows (e.g., confirm consolidated metadata, verify round-trip reads) to strengthen feedback loops.

Move detailed API content into references/api_reference.md and add clearly signaled one-level-deep links from the body (e.g., 'See [api_reference.md](references/api_reference.md) for the full API') to use the bundle and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is roughly 770 lines and re-explains concepts Claude already knows ('Groups organize multiple arrays hierarchically, similar to directories', 'Dask provides lazy, parallel computation', 'Xarray provides labeled, multidimensional arrays') with some redundant coverage of chunking across multiple sections, though it is largely code-driven rather than padded filler.	3 / 5
Actionability	Provides extensive concrete, mostly copy-paste-ready code across array creation, codecs, storage backends, and Dask/Xarray integration, but several snippets reference an undefined `data` variable or assume surrounding context, leaving minor gaps that keep it below fully-executable 5.	4 / 5
Workflow Clarity	A performance checklist and 'Common Issues' diagnosis-to-solution sections provide sequencing, but there are no explicit validation checkpoints or validate-fix-retry feedback loops, which the rubric flags as capping workflow clarity at 3 for batch/destructive-style operations like cloud and parallel writes.	3 / 5
Progressive Disclosure	The body has well-organized section headers, but it inlines API-reference-style content even though a bundled references/api_reference.md exists, and it never signals or links to that file, so content that belongs in a separate file is not navigated to.	3 / 5
	Total	13 / 20 Passed

Description

66%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 conveys a clear, specific feature set with good keyword coverage and low conflict risk, but it omits an explicit 'Use when...' trigger clause, leaving the 'when to use' guidance only weakly implied.

Suggestions

Add an explicit 'Use when ...' trigger clause (e.g., 'Use when working with large N-dimensional arrays, chunked storage, or S3/GCS-backed scientific datasets.') to raise completeness.

Include natural synonyms and file extensions users might say (e.g., 'ndarray', 'zarr', '.zarr', 'HDF5 alternative') to broaden trigger-term coverage.

Reframe feature phrases as concrete action verbs (e.g., 'Store, read, and compress N-D arrays') to strengthen specificity.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities ('Chunked N-D arrays', 'Compressed arrays', 'parallel I/O', 'S3/GCS integration', 'NumPy/Dask/Xarray compatible') but phrases them as features rather than explicit action verbs, so it falls below the comprehensive action-list anchor of 5.	4 / 5
Completeness	Clearly states 'what' the skill does, but the 'when' is only weakly implied via 'for large-scale scientific computing pipelines' with no explicit 'Use when...' trigger clause, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Includes good natural keywords and library names ('N-D arrays', 'S3/GCS', 'NumPy/Dask/Xarray', 'scientific computing pipelines') but is missing common synonyms and file extensions a user might say, so it does not reach the comprehensive coverage of 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (chunked N-D array cloud storage) with specific integrations, leaving only minor overlap risk with general array/NumPy skills; lacks the explicit trigger phrases needed for a 5.	4 / 5
	Total	15 / 20 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
skill_md_line_count	SKILL.md is long (777 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning

	Total	14 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/zarr-python/SKILL.md
Commit: ddcaa2a

Reviewed: 6 days 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.