singlecell-portal

Programmatically query public single-cell study metadata from the Broad Institute Single Cell Portal REST API when you need to search and filter datasets by organism, tissue, disease, or cell type without an API key.

Quality

79%

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 ./scientific-skills/Data Analysis/singlecell-portal/SKILL.md

Quality

Content

71%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 actionable with a complete executable example and a clear sequence, but it is held back by redundant restatement of endpoints/SSL handling across sections and by orphaned bundle files that are never linked from the overview.

Suggestions

De-duplicate endpoint and SSL/Windows handling: state them once in 'Implementation Details' and reference that from 'Key Features' and the code docstring rather than repeating each list.

Link the bundle files from the body — point readers to scripts/query.py for the full-featured script and references/evaluation-checklist.md for testing guidance, instead of inlining a parallel example.

Add a brief validation/error-recovery checkpoint (e.g., 'if search returns no studies, fall back to inspecting facet values before retrying') to make the query workflow more robust.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and avoids teaching concepts Claude already knows, but the same material is restated across sections — endpoint lists appear in both 'Key Features' and 'Implementation Details', and SSL/Windows handling is repeated in the code docstring, a Key Features bullet, and Implementation Details.	3 / 5
Actionability	Provides a fully executable, copy-paste-ready Python example covering the common cases (search with facets, inspect facet keys, fetch study details by accession), with defensive dict.get access matching real response shapes.	5 / 5
Workflow Clarity	The numbered example (search -> inspect facets -> fetch details) gives a clear sequence, but there are no explicit validation checkpoints or error-recovery feedback loops; read-only scope makes this a minor gap rather than a cap.	4 / 5
Progressive Disclosure	Sections are well organized, but the provided bundle files (scripts/query.py and references/evaluation-checklist.md) are never referenced from the body, and the inline code example duplicates the bundled script rather than pointing to it — references present but not signaled.	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, specific description that answers both 'what' and 'when' with concrete facet-based triggers and a clearly bounded niche. Minor gaps in action breadth and synonym coverage keep specificity and trigger-term quality just below the top anchor.

Dimension	Reasoning	Score
Specificity	Names the domain ('query public single-cell study metadata') and concrete actions ('search and filter datasets by organism, tissue, disease, or cell type'), covering several specific facets but not the full action set (e.g., facet retrieval, study-by-accession) found in the body.	4 / 5
Completeness	Explicitly states what it does ('Programmatically query public single-cell study metadata from the Broad Institute Single Cell Portal REST API') and when to use it ('when you need to search and filter datasets by organism, tissue, disease, or cell type without an API key') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural terms users would say ('single-cell study metadata', 'search and filter datasets', organism/tissue/disease/cell type), but omits common synonyms like 'scRNA-seq' or 'transcriptomics' that a user might naturally invoke.	4 / 5
Distinctiveness Conflict Risk	Targets a clearly named, niche source ('Broad Institute Single Cell Portal REST API') with distinct triggers, so it is unlikely to fire for unrelated skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/singlecell-portal/SKILL.md
Commit: f5ef65b

Reviewed: ~9 hours 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.