anndata

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/anndata/SKILL.md

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.

A well-structured, highly actionable skill body with excellent progressive disclosure and executable examples throughout. The main gaps are redundant snippets that hurt token efficiency and missing validation checkpoints in the destructive/batch workflows.

Suggestions

Add explicit validation checkpoints to destructive and batch workflows (e.g., after QC filtering and `adata.raw = adata.copy()`, verify `adata.shape` or assert no data loss before proceeding) to lift workflow_clarity above the cap.

De-duplicate code that appears in both Quick Start and Core Capabilities (e.g., read/write/subset snippets) — keep the canonical copy in one place and reference it from the other to improve conciseness.

Trim the Overview paragraph's restatement of what AnnData is and the repeated deprecated-API notes, since the Installation section already covers API guidance.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient code with brief intros, but Quick Start snippets are repeated/expanded in Core Capabilities, the deprecated-API list and scanpy integration snippets recur, and the Overview paragraph restates what AnnData is — tightening these redundancies would move it toward the efficient anchor.	3 / 5
Actionability	It provides abundant copy-paste-ready, executable code covering the common cases (create, read, write, subset, concat, backed mode, QC workflow), matching the fully-executable anchor.	5 / 5
Workflow Clarity	Multi-step workflows (single-cell RNA-seq, batch integration, large datasets) are clearly sequenced, but destructive/batch operations like filtering and `adata.raw = adata.copy()` lack explicit validation checkpoints or feedback loops, so the destructive-ops cap of 3 applies.	3 / 5
Progressive Disclosure	A clear overview points to five real, well-signaled one-level-deep reference files, each with a bulleted topic list, with bulk content split out and only key snippets inline — matching the clear-overview anchor.	5 / 5
	Total	16 / 20 Passed

Description

82%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 that clearly states what the skill is and when to use it, with excellent distinctiveness guidance that steers users away from sibling scverse tools. The main weakness is specificity, since it characterizes the data structure rather than enumerating concrete actions.

Dimension	Reasoning	Score
Specificity	"Data structure for annotated matrices in single-cell analysis" names the domain and its core capability clearly, but describes what the object is rather than listing multiple concrete actions, fitting the 'names domain and 1-2 concrete actions' anchor rather than the multi-action anchor above.	3 / 5
Completeness	It explicitly answers both 'what' ("Data structure for annotated matrices in single-cell analysis") and 'when' ("Use when working with .h5ad files or integrating with the scverse ecosystem") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	It includes natural terms users would say — ".h5ad files", "scverse ecosystem", "single-cell analysis" — with a file extension, but omits common synonyms like 'AnnData', 'h5ad', 'zarr', or 'loom', so it is good but not comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	The explicit disambiguation ("for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census") carves a clear niche and minimizes conflict with sibling scverse skills.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/anndata/SKILL.md
Commit: b2a92ba

Reviewed: 3 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.