human-protein-atlas-database

Use when you want to retrieve semi-quantitative protein expression and spatial localisation data from the Human Protein Atlas (HPA).

Quality

87%

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

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable examples for all five subcommands, clear command selection, and well-structured one-level-deep references. The main shortfall is minor verbosity in the introductory framing and some redundancy between the When-to-Use and Command Selection Guide sections.

Suggestions

Trim the introductory RNA-seq-vs-HPA contrast to one line, or move it into the 'Do NOT use when' section where it already recurs, to reduce token overhead.

Merge the overlapping 'When to Use' and 'Command Selection Guide' lists so each mapping (intent -> subcommand) appears once.

Reference references/citation.bib explicitly somewhere in the body so all bundle files are discoverable, not just search-api.md.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but the introductory RNA-seq-vs-HPA explanation and the partial overlap between 'When to Use' and 'Command Selection Guide' could be tightened, fitting the score-2 anchor.	2 / 3
Actionability	Every subcommand has a copy-paste-ready executable example with explicit arguments, defaults, and output paths, matching the score-3 fully-executable anchor.	3 / 3
Workflow Clarity	A Command Selection Guide, a sequenced Quick Start (resolve ID then query), and a Common Errors recovery section give a clear sequence with error feedback; operations are read-only so no destructive-operation validation cap applies.	3 / 3
Progressive Disclosure	SKILL.md is a concise overview that signals one-level-deep references (references/search-api.md for query syntax, scripts/hpa_cli.py as the wrapper) and splits detail appropriately, matching the score-3 anchor against the real bundle structure.	3 / 3
	Total	11 / 12 Passed

Description

90%Weight 40%Scale 1-3

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, third-person, and includes an explicit 'Use when' trigger tied to a clearly distinctive HPA niche. Its only weakness is that it states one retrieve action over two data types rather than enumerating multiple concrete capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain and a concrete action ("retrieve semi-quantitative protein expression and spatial localisation data") but uses a single verb over two data types rather than listing multiple distinct actions, so it stops short of the comprehensive score-3 anchor.	2 / 3
Completeness	Explicitly answers both what (retrieve HPA protein expression and localisation data) and when ("Use when you want to retrieve..."), satisfying the score-3 anchor with an explicit trigger.	3 / 3
Trigger Term Quality	Natural terms a user would actually say are well covered ("protein expression", "spatial localisation", "Human Protein Atlas", "HPA"), matching the score-3 anchor for good keyword coverage.	3 / 3
Distinctiveness Conflict Risk	The Human Protein Atlas / HPA niche is narrow and distinctive, with triggers unlikely to fire for unrelated skills, matching the score-3 anchor.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: google-deepmind/science-skills
Path: skills/human_protein_atlas_database/SKILL.md
Commit: 0b42509

Reviewed: 8 days 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.