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.
69
37%
Does it follow best practices?
Impact
90%
1.25xAverage score across 6 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/zarr-python/SKILL.mdQuality
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 provides a reasonable feature list for what appears to be a Zarr-related skill but reads more like a marketing tagline than a functional skill description. It critically lacks a 'Use when...' clause and omits the likely library name (Zarr), which would be the most important trigger term. The description would benefit from explicit trigger guidance and more concrete action verbs.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Zarr arrays, chunked array storage, or reading/writing large N-D arrays to cloud storage (S3/GCS).'
Include the library name 'Zarr' prominently as a trigger term, since users will almost certainly mention it by name when they need this skill.
Replace feature-list style phrasing with concrete action verbs, e.g., 'Creates, reads, and writes Zarr stores; configures chunking and compression; integrates with S3/GCS backends.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (chunked N-D arrays, cloud storage) and some actions (compressed arrays, parallel I/O, S3/GCS integration), but these read more like feature bullet points than concrete actions a user would perform. It doesn't list specific tasks like 'create Zarr stores', 'read/write chunked arrays', or 'convert NetCDF to Zarr'. | 2 / 3 |
Completeness | The description addresses 'what' at a high level (chunked N-D arrays for cloud storage with various integrations) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also somewhat vague, warranting a score of 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'S3', 'GCS', 'NumPy', 'Dask', 'Xarray', 'compressed arrays', and 'parallel I/O' that users might mention. However, it's missing the key term 'Zarr' (which is almost certainly the library this skill is about), and lacks common user phrases like 'chunked storage', 'array store', or 'zarr format'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of chunked N-D arrays, cloud storage, and specific library compatibility (NumPy/Dask/Xarray) narrows the domain somewhat, but without naming the specific library (likely Zarr), it could overlap with other array storage or scientific computing skills. The mention of S3/GCS integration could also conflict with general cloud storage skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a comprehensive library documentation page rather than a focused, concise skill reference. While the code examples are excellent and fully actionable, the document is far too verbose for a SKILL.md—it explains concepts Claude already knows, includes extensive 'Benefits' lists, and packs everything into a single monolithic file. The lack of validation steps in multi-step workflows and absence of progressive disclosure through external files significantly reduce its effectiveness as a skill.
Suggestions
Reduce content by 60-70%: remove explanatory prose Claude already knows (what chunking is, what Dask benefits are, what groups are similar to), keep only the code examples and critical gotchas/non-obvious behavior.
Split into multiple files: keep SKILL.md as a quick-start overview (~50-80 lines) with references to separate files like CHUNKING.md, CLOUD_STORAGE.md, COMPRESSION.md, and PATTERNS.md.
Add explicit validation checkpoints to multi-step workflows, especially the cloud-native pattern (verify write, check metadata consolidation) and format conversion (validate output integrity).
Remove the 'Benefits' bullet lists and descriptive sentences like 'Zarr is a Python library for storing large N-dimensional arrays'—Claude knows what Zarr is from the skill description.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~500+ lines, explaining many concepts Claude already knows (what chunking is, what NumPy arrays are, how HDF5 works, what Dask benefits are). Sections like 'Benefits' bullet lists, explanations of compression tradeoffs, and basic concepts like 'Groups organize multiple arrays hierarchically, similar to directories or HDF5 groups' are unnecessary padding. Much of this reads like library documentation rather than a concise skill reference. | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste ready code examples throughout every section. Code snippets include complete imports, realistic parameters, and cover the full range of operations from creation to cloud deployment. Examples are concrete and specific rather than pseudocode. | 3 / 3 |
Workflow Clarity | While individual operations are clear, multi-step workflows (like the cloud-native pattern or format conversion) lack explicit validation checkpoints. There are no feedback loops for error recovery—e.g., the cloud workflow doesn't verify the write succeeded, and the format conversion pattern doesn't validate the output. The troubleshooting section helps but is reactive rather than integrated into workflows. | 2 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of text with no references to external files. All content—quick start, advanced chunking strategies, compression details, cloud storage, parallel computing, common patterns, troubleshooting—is inlined into a single massive document. With no bundle files, content like the full API patterns, compression benchmarks, and storage backend details should be split into separate referenced files. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
81%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 | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
cbcae7b
- 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.