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

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%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 content is highly actionable with a complete, executable example and concrete API details, and it stays lean without over-explaining. Its main weaknesses are redundancy between the When to Use, Key Features, and Implementation Details sections, and orphaned bundle files (scripts/query.py, references/evaluation-checklist.md) that are never linked from SKILL.md.

Suggestions

Reference the bundle files from the body so they are discoverable: e.g., a '## Full query script' section pointing to scripts/query.py (including its natural-language-to-ontology-ID mapping) and a '## Validation checklist' section pointing to references/evaluation-checklist.md.

Trim the 'Key Features' section, whose bullets duplicate 'When to Use' and 'Implementation Details' content (e.g., 'No API key required', 'Faceted search for studies'), to reduce token cost.

Add brief guidance on handling empty search results and HTTP errors beyond the code's implicit checks, to give the workflow an explicit validation/recovery checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is efficient overall: a complete runnable example plus concrete endpoint details, with no explanations of concepts Claude already knows. Not 5 because the 'Key Features' bullets substantially duplicate 'When to Use' and 'Implementation Details' (e.g., 'No API key required (public endpoints)', 'Faceted search for studies'), which could be trimmed.	4 / 5
Actionability	The Example Usage section is fully executable, copy-paste-ready Python covering search, facet inspection, and study-detail retrieval, and Implementation Details gives exact endpoint paths, facet syntax, and the size parameter. Not 4 because the common cases are all covered with concrete, runnable code.	5 / 5
Workflow Clarity	The demo is a clear numbered sequence (search -> inspect facets -> fetch details) with checkpoints via raise_for_status() and defensive dict.get, and operations are read-only so no destructive-validation cap applies. Not 5 because explicit guidance for empty results or error-recovery feedback loops is only implicit in the code.	4 / 5
Progressive Disclosure	The body itself is well-sectioned and appropriately sized for an overview, but the bundle contains scripts/query.py (with natural-language-to-ontology mapping not described in SKILL.md) and references/evaluation-checklist.md, neither of which is referenced or signaled anywhere in the body. Not 4 because completely orphaned bundle files are more than a minor organization gap; not 2 because the inline content is still well structured and self-sufficient for the core task.	3 / 5
	Total	16 / 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 description: it states concrete, parameterized capabilities against a uniquely named resource and includes an explicit, specific 'when' trigger clause. Minor improvements would add common synonyms (e.g., scRNA-seq) and mention study-details-by-accession retrieval.

Dimension	Reasoning	Score
Specificity	Names the domain ('Broad Institute Single Cell Portal REST API') and two concrete, parameterized actions ('query public single-cell study metadata', 'search and filter datasets by organism, tissue, disease, or cell type'). Not 3 because the actions are parameterized with concrete filter dimensions; not 5 because coverage has minor gaps (study details by accession and facet dictionary retrieval are not mentioned).	4 / 5
Completeness	Explicitly answers both 'what' ('Programmatically query public single-cell study metadata from the Broad Institute Single Cell Portal REST API') and 'when' ('when you need to search and filter datasets by organism, tissue, disease, or cell type without an API key') with concrete trigger phrases. Not 4 because the when-clause is explicit and specific rather than vague or weakly implied.	5 / 5
Trigger Term Quality	Contains natural terms users would say for this domain ('single-cell', 'study metadata', 'organism', 'tissue', 'disease', 'cell type'). Not 5 because common synonyms such as 'scRNA-seq', 'single cell RNA', or 'Broad' are missing.	4 / 5
Distinctiveness Conflict Risk	Identifies a unique, niche resource (the Broad Institute Single Cell Portal REST API) with distinct domain triggers, giving it a clear niche with minimal conflict risk against other skills. Not 4 because no overlap with generic data-query skills is plausible given the named portal and single-cell-specific filter terms.	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: 686e09d

Reviewed: 13 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.