CtrlK
BlogDocsLog inGet started
Tessl Logo

cellxgene-skill

Submit compact CELLxGENE Discover API requests for public collection and dataset metadata. Use when a user wants concise single-cell collection summaries

67

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/life-science-research/skills/cellxgene-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 tight, actionable, well-structured wrapper around a single script with concrete examples and a clear input/output contract. Its only gaps are a duplicated example payload and the absence of an explicit error-recovery loop.

Suggestions

De-duplicate the example JSON: keep the full payload only in 'Common patterns' and reference it from the Execution block, or vice versa.

Add a short error-recovery note in the Output or Execution section (e.g. on ok=false, inspect error.code/error.message, adjust path/params, and re-run).

Optionally note the collections list pagination/size handling so the higher timeout_sec guidance ties to a concrete verification step.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (no explanation of what CELLxGENE or single-cell data is), but the same example JSON payload is duplicated between 'Common CELLxGENE patterns' and the 'Execution' block. Not 5 because of that duplicated payload that could be trimmed; not 3 because it is otherwise efficient with every line operational.

4 / 5

Actionability

Quotes the copy-paste ready command 'echo '{...}' | python scripts/rest_request.py' plus concrete JSON input examples, a specific base_url, a real collection_id, specific paths, and explicit field lists. Not 4 because the guidance is fully executable and covers the common cases rather than having minor gaps.

5 / 5

Workflow Clarity

The single action (build JSON input, pipe to script, interpret output) is unambiguous and the Output section documents the success/failure shape as a checkpoint; this is a read-only API call so the destructive/batch cap to 3 does not apply. Not 5 because there is no explicit validate→fix→retry recovery loop; not 3 because the sequence and error shape are clearly documented.

4 / 5

Progressive Disclosure

At 37 lines with well-organized sections (Operating rules, Execution behavior, Input, Output, Execution, References) and a single one-level-deep reference to the real file scripts/rest_request.py, this fits the simple-skill exception for a 5. Not 4 because structure and the single reference are clear with no organization gaps.

5 / 5

Total

18

/

20

Passed

Description

73%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.

The description clearly states what the skill does and when to use it, with a distinctive single-cell/CELLxGENE niche. Its main weakness is that the trigger clause covers only collection summaries while the capability clause also names dataset metadata.

Suggestions

Add dataset-related triggers to the 'Use when' clause (e.g. 'or when the user wants dataset metadata summaries') so the when matches the full what.

Include common synonyms such as 'scRNA-seq' or 'cellxgene' to broaden natural trigger coverage.

Name a second concrete action beyond 'submit API requests' (e.g. 'fetch and summarize') to lift specificity.

DimensionReasoningScore

Specificity

Quotes 'Submit compact CELLxGENE Discover API requests for public collection and dataset metadata' — names the domain and one concrete action (submit API requests for metadata), matching the anchor for 1-2 concrete actions without comprehensive coverage. Not 4 because it lists essentially one action rather than several specific actions; not 2 because the domain and action are concrete rather than generic.

3 / 5

Completeness

Has both a clear 'what' ('Submit compact CELLxGENE Discover API requests for public collection and dataset metadata') and an explicit 'when' ('Use when a user wants concise single-cell collection summaries'). Not 5 because the when is narrower than the what — it only mentions collection summaries, omitting dataset metadata as a trigger; not 3 because both what and when are explicitly present.

4 / 5

Trigger Term Quality

Quotes 'Use when a user wants concise single-cell collection summaries' — a natural phrase a user would say, giving good keyword coverage. Not 5 because it lacks common synonyms/variations (e.g. scRNA-seq, dataset metadata, cellxgene); not 3 because it does include a clear natural user phrase rather than only technical jargon.

4 / 5

Distinctiveness Conflict Risk

Quotes 'CELLxGENE Discover API' and 'single-cell collection summaries' — a clear niche with distinct triggers and minimal conflict risk with other skills. Not 4 because the niche is highly specific rather than merely 'mostly distinct'.

5 / 5

Total

16

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/plugins
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.