CtrlK
BlogDocsLog inGet started
Tessl Logo

anndata

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

66

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Data Analysis/anndata/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 an excellent runnable example, but workflow validation for batch operations is implicit and the reference-file navigation is weakly signaled.

Suggestions

Replace the buried parenthetical reference note with a dedicated '## Further reading' section that maps each topic to its file (e.g., 'Data model: references/data_structure.md', 'I/O: references/io_operations.md').

Add an explicit validation/verification checkpoint after the concatenation step (e.g., assert expected batch counts or check combined.shape) to establish a feedback loop for the batch operation.

Trim redundancy between the Example Usage code comments and the Implementation Details section so each topic appears in one place.

DimensionReasoningScore

Conciseness

Mostly lean and assumes competence, but the Implementation Details section repeats concepts (concat, backed mode) already shown in the runnable example and could be tightened.

4 / 5

Actionability

Provides a complete, copy-paste-ready Python example covering object creation, .h5ad write/read, subsetting, batch concatenation, and backed mode, plus concrete parameter guidance.

5 / 5

Workflow Clarity

The example is numbered (steps 1-5) but has only implicit checkpoints (print statements) and no explicit validate/verify feedback loop for the batch concatenation operation, capping the score per the batch-operation guidance.

3 / 5

Progressive Disclosure

Five real reference files exist and are one level deep, but navigation is a buried parenthetical aside ('the original material mentions additional guides under references/...') rather than a clearly signaled per-topic map, and some detail could live in the reference files.

3 / 5

Total

15

/

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, third-person description that clearly states both capability and trigger conditions with concrete file-format keywords. Minor additional synonyms would round out trigger coverage.

DimensionReasoningScore

Specificity

Names the domain ('annotated matrices in single-cell analysis') and several concrete actions ('reading/writing .h5ad (or zarr)', 'exchanging data with the scverse ecosystem'), with minor coverage gaps (subsetting, concatenation, backed mode are absent from the description).

4 / 5

Completeness

Explicitly answers both 'what' (data structure for annotated matrices in single-cell analysis) and 'when' via a concrete 'use when reading/writing .h5ad (or zarr) and exchanging data with the scverse ecosystem' trigger clause.

5 / 5

Trigger Term Quality

Includes natural, user-sayable terms plus file extensions ('.h5ad', 'zarr', 'single-cell analysis', 'scverse ecosystem'); a few common synonyms are missing (the word 'AnnData' itself, 'scanpy', 'scRNA-seq').

4 / 5

Distinctiveness Conflict Risk

The single-cell/scverse/.h5ad/zarr niche is highly specific with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
aipoch/medical-research-skills
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.