CtrlK
BlogDocsLog inGet started
Tessl Logo

cellxgene-census

Query the CELLxGENE Census (61M+ cells) programmatically. Use when you need expression data across tissues, diseases, or cell types from the largest curated single-cell atlas. Best for population-scale queries, reference atlas comparisons. For analyzing your own data use scanpy or scvi-tools.

62

Quality

75%

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 ./backend/cli/skills/databases/cellxgene-census/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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, actionable guide to querying the CELLxGENE Census with well-signaled reference files, but it is held back by noticeable redundancy: best-practice guidance and use-case code repeat material already covered in the numbered workflow patterns and in common_patterns.md.

Suggestions

Collapse the 'Common Use Cases' section or convert it to cross-references, since its four code examples largely duplicate the 'Core Workflow Patterns' above.

Trim the 'Key Concepts and Best Practices' section to only items not already covered inline (e.g., remove the repeated 'Always Filter for Primary Data', 'Specify Census Version', 'Select Only Needed Columns', and 'Use tissue_general' subsections), pointing to common_patterns.md instead.

Either define or clearly mark as illustrative the placeholder symbols in the ML examples (model, criterion, optimizer, num_epochs, process_batch) so the code is unambiguously executable.

DimensionReasoningScore

Conciseness

The content is largely API-specific (get_anndata, obs_value_filter, is_primary_data, tissue_general) rather than explaining basics Claude knows, but the 'Key Concepts and Best Practices' and 'Common Use Cases' sections duplicate code and guidance already shown in the numbered 'Core Workflow Patterns' and present in common_patterns.md, so it could be tightened considerably.

3 / 5

Actionability

It provides concrete, mostly copy-paste-ready code for the core query APIs (get_anndata, get_obs, get_var, axis_query, experiment_dataloader) with specific filter syntax; minor gaps remain where ML examples reference undefined placeholders like model, num_epochs, and process_batch().

4 / 5

Workflow Clarity

The process is clearly sequenced (open census -> explore metadata -> query at small/large scale -> integrate/ML) with an explicit 'Estimate Query Size Before Loading' checkpoint that guards memory, and a troubleshooting section; this is a read/query skill so the destructive-cap does not apply, though post-query validation is only implicit.

4 / 5

Progressive Disclosure

Two real one-level-deep reference files (census_schema.md, common_patterns.md) are signaled in a 'Reference Documentation' section with 'When to read' navigation guidance, but the body inlines substantial patterns and best practices that overlap with common_patterns.md, leaving a minor organization gap.

4 / 5

Total

15

/

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: it clearly states what the skill does, when to use it, and how it differs from scanpy/scvi-tools. Its only weakness is specificity, as it relies on one core action (querying) plus use-case variations rather than enumerating multiple distinct capabilities.

DimensionReasoningScore

Specificity

The description names the domain ('CELLxGENE Census') and a core concrete action ('Query ... programmatically') plus scope ('expression data across tissues, diseases, or cell types'), but the remaining phrases ('population-scale queries', 'reference atlas comparisons') are use-cases rather than distinct concrete actions, so coverage is not comprehensive.

3 / 5

Completeness

It explicitly answers both 'what' ('Query the CELLxGENE Census (61M+ cells) programmatically') and 'when' with a concrete 'Use when you need expression data across tissues, diseases, or cell types ...' trigger clause, matching the top anchor.

5 / 5

Trigger Term Quality

It includes natural domain terms a user would actually say — 'expression data', 'tissues', 'diseases', 'cell types', 'single-cell atlas' — plus related synonyms, giving good keyword coverage with only minor omissions (e.g., 'scRNA-seq').

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (the curated CELLxGENE single-cell atlas) and explicitly disambiguates from adjacent tools ('For analyzing your own data use scanpy or scvi-tools'), minimizing conflict risk.

5 / 5

Total

17

/

20

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.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (511 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
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.