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 ./backend/cli/skills/data-engineering/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 body is a thorough, mostly executable reference with good section organization, but it is over-long with redundancy, lacks validation checkpoints in its workflows, and fails to surface the existing bundled reference file. Tightening and linking the reference would lift the weaker dimensions.

Suggestions

Link the bundled references/api_reference.md from the body (e.g. an "API reference" section: "See [api_reference.md](references/api_reference.md)"), and move bulk API detail there to reduce inline length.

De-duplicate chunking guidance between "Chunking Strategies" and the "Performance Optimization" checklist into a single authoritative section.

Add explicit validation/verification checkpoints to the cloud-write and parallel-write workflows (e.g. verify consolidated metadata, confirm shard write success) to support feedback loops.

Fix zarr.open() calls that pass shape/chunks/dtype by switching them to zarr.open_array() or zarr.create_array() so examples are fully executable.

Dimension	Reasoning	Score
Conciseness	Mostly efficient code-centric content, but the ~770-line body repeats material across "Chunking Strategies" and the "Performance Optimization" checklist, and includes some explanatory prose Claude already knows ("Chunking is critical for performance"), so it could be tightened.	3 / 5
Actionability	Abundant concrete, copy-paste-ready code covering common cases, but a few examples call zarr.open() with shape/chunks parameters it does not accept (e.g. the time-series and matrix patterns), which are minor executability gaps.	4 / 5
Workflow Clarity	Sequences exist (Quick Start, Cloud-Native Workflow pattern, Common Issues diagnosis) but there are no explicit validation checkpoints or feedback loops for risky parallel/cloud writes, so checkpoints remain implicit.	3 / 5
Progressive Disclosure	Sections are well-organized with clear headers, but the body inlines ~770 lines of API detail and the bundled references/api_reference.md is never linked or signaled from the body, leaving content that belongs in separate files inline.	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 is specific and fairly rich in trigger terms, but lacks an explicit "Use when..." clause, which caps completeness. It is distinguishable but could add natural synonyms and a concrete trigger phrase to reach the top anchors.

Suggestions

Add an explicit trigger clause, e.g. "Use when working with Zarr arrays, chunked N-D array storage, or cloud-based scientific data pipelines."

Include natural synonyms and the .zarr extension (e.g. "Zarr stores", ".zarr files") to broaden trigger-term coverage.

Lead with the primary action verb in third person to sharpen the opening (e.g. "Stores and processes chunked N-D arrays...").

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities — "Chunked N-D arrays", "Compressed arrays", "parallel I/O", "S3/GCS integration", "NumPy/Dask/Xarray compatible" — with only minor coverage gaps, matching the anchor for several specific actions.	4 / 5
Completeness	The "what" is clear and detailed, but there is no explicit "Use when..." trigger clause; the trailing "for large-scale scientific computing pipelines" only weakly implies when, so completeness is capped at 3 per the missing-trigger guideline.	3 / 5
Trigger Term Quality	Contains natural terms users would say ("cloud storage", "S3/GCS", "parallel I/O", "NumPy/Dask/Xarray", "scientific computing") but omits common synonyms and the .zarr extension, so it falls just short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	The chunked-cloud-storage + S3/GCS + NumPy/Dask/Xarray framing carves a mostly distinct niche with only minor overlap risk against general array or cloud-I/O libraries.	4 / 5
	Total	15 / 20 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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (779 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/data-engineering/zarr-python/SKILL.md
Commit: 5f2a37b

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.