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

71

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%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 an exemplary lean skill file: concrete operating rules, exact input/output contracts, copy-paste-ready execution examples, and an explicit statement that no further references are needed. It adds only information Claude could not infer (base URL, script contract, preferred paths) with zero filler.

DimensionReasoningScore

Conciseness

Every section instructs rather than explains — no padding, no primer on REST APIs or CELLxGENE itself, no re-stating what Claude already knows. Matches 'Lean and efficient; assumes Claude's competence; every token earns its place'.

5 / 5

Actionability

The body gives a copy-paste-ready executable command with the full JSON payload, two additional common request patterns covering both collection-detail and broad list lookups, exact required/optional field lists, and the success/failure output shape — 'Fully executable; copy-paste ready code or commands; specific examples cover the common cases'.

5 / 5

Workflow Clarity

This is a simple single-task skill (pipe one JSON object into scripts/rest_request.py) and that single action is unambiguous, with a preferred-path ordering (collection detail first, collections list on explicit request). No destructive or batch operations exist that would require validation checkpoints, so the simple-skill exception applies.

5 / 5

Progressive Disclosure

The skill is under 50 lines with clear section headers and no need for external references; the 'References' section explicitly states no additional runtime references are required, and the bundle (scripts/rest_request.py, which is referenced correctly and exists) matches that structure — 'For skills under 50 lines with no need for external references, progressive disclosure can score 5 with just well-organized sections'.

5 / 5

Total

20

/

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 is concise, in third person, and clearly names its niche (CELLxGENE Discover API metadata requests) with an explicit use-when clause. Its main gaps are limited action coverage and a narrow trigger clause that omits dataset-related and scRNA-seq phrasing users might naturally use.

Suggestions

Broaden the 'when' clause to cover dataset as well as collection requests, e.g. 'Use when a user wants concise single-cell collection or dataset summaries' or mentions of CELLxGENE Discover, scRNA-seq data, or dataset metadata.

Add one more concrete capability to the 'what' (e.g., fetching dataset details or filtering collections by id) to move specificity beyond a single action.

Include common synonyms such as 'single cell RNA' or 'scRNA-seq' alongside 'single-cell' to strengthen trigger-term coverage.

DimensionReasoningScore

Specificity

"Submit compact CELLxGENE Discover API requests for public collection and dataset metadata" names the domain and one concrete action with a clear target, but stops short of listing several actions (e.g., dataset detail lookups or filtering), matching the anchor 'Names domain and 1-2 concrete actions, but not comprehensive'.

3 / 5

Completeness

Both parts are present: a clear third-person "what" (submit compact API requests for collection and dataset metadata) and an explicit "Use when a user wants concise single-cell collection summaries" clause. The "when" is somewhat narrow — it only covers collection summaries and misses dataset-related triggers — so it matches anchor 4 rather than the fully concrete trigger coverage of anchor 5.

4 / 5

Trigger Term Quality

Includes natural terms users of this domain would say — "CELLxGENE", "single-cell", "collection", "dataset" — but omits common variations such as "scRNA-seq" or "single cell RNA", fitting 'Good keyword coverage; a few natural terms missing'.

4 / 5

Distinctiveness Conflict Risk

The CELLxGENE Discover API is a clear niche with distinct trigger terms ("CELLxGENE", "single-cell collection summaries"), so it is unlikely to fire for the wrong skill — matching 'Clear niche with distinct triggers; minimal conflict risk'.

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.

Validation — 16 / 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.