anndata

Data structure for annotated matrices in single-cell analysis; use when reading/writing .h5ad (or zarr) and exchanging data with the scverse ecosystem.

Quality

85%

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

Quality

Content

78%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.

Highly actionable content with a complete runnable example and accurate API detail, weakened by duplication between summary and detail sections and poorly signaled navigation to the existing reference files. Restructuring the reference pointers and de-duplicating would lift it substantially.

Suggestions

Replace the 'Reference notes' blockquote with clearly signaled per-topic links, e.g. under each Implementation Details subsection: 'See [references/concatenation.md](references/concatenation.md) for the full guide', so the existing bundle files are actually discoverable.

De-duplicate 'Key Features' against 'Implementation Details' — collapse them into one section (or keep a 3-4 line summary) to reclaim tokens and remove redundancy.

Trim the Dependencies section to the required packages (anndata, numpy, pandas, scipy) and mention optional tools only where they are used in the examples, moving the rest to references/best_practices.md.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and library-specific, but 'Key Features' bullets substantially duplicate 'Implementation Details', and the Dependencies section pads with optional ecosystem tools (torch, muon). Efficient with minor trimmable content rather than the noticeable padding of anchor 3.	4 / 5
Actionability	The example is fully executable and copy-paste ready, covering creation, sparse conversion, write/read of .h5ad, boolean subsetting, ad.concat with join/label/keys, and backed mode with to_memory(). Concrete API parameters cover the common cases.	5 / 5
Workflow Clarity	The example is clearly sequenced in numbered sections (create → write/read → subset → concatenate → backed mode), and the operations are non-destructive so no validation cap applies. Missing explicit checkpoints or error-recovery guidance (e.g., what to do on failed reads or OOM) keeps it below 5.	4 / 5
Progressive Disclosure	Five real one-level-deep reference files exist (data_structure.md, io_operations.md, concatenation.md, manipulation.md, best_practices.md), but they are only weakly signaled in a hedged blockquote ('the original material mentions additional guides under references/'), and detailed implementation content that belongs in those files is inlined in SKILL.md. References are present but not clearly signaled, matching anchor 3.	3 / 5
	Total	16 / 20 Passed

Description

87%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.

A strong description: third-person, concise, with an explicit 'use when' trigger clause naming concrete formats and ecosystem. Main gap is missing high-probability synonyms like 'AnnData' and 'scRNA-seq' that users would naturally say.

Dimension	Reasoning	Score
Specificity	Names the domain ('annotated matrices in single-cell analysis') and several concrete actions with formats ('reading/writing .h5ad (or zarr)', 'exchanging data with the scverse ecosystem'), though coverage omits subsetting, concatenation, and backed mode. Fits the 'several specific actions; minor gaps' anchor rather than the comprehensive 5 or the 1-2-action 3.	4 / 5
Completeness	Explicitly answers both: what ('Data structure for annotated matrices in single-cell analysis') and when ('use when reading/writing .h5ad (or zarr) and exchanging data with the scverse ecosystem') with concrete trigger phrases. The when-clause is specific, so the 4 anchor ('when could be more explicit') does not fit.	5 / 5
Trigger Term Quality	Good natural keywords including file extensions ('.h5ad', 'zarr', 'single-cell analysis', 'scverse ecosystem'), but common user phrasings like 'AnnData', 'scanpy', and 'scRNA-seq' are absent. Above anchor 3 (relevant keywords present) but short of the comprehensive synonym coverage of 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche with distinct triggers — single-cell annotated matrices, .h5ad/zarr formats, scverse ecosystem — making conflict with other skills minimal. No generic phrasing that would overlap unrelated skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/anndata/SKILL.md
Commit: 686e09d

Reviewed: 12 hours 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.