uniprot-database

Access protein metadata, function, taxonomy, and sequences across UniProtKB, UniParc, and UniRef. Use when searching for proteins, mapping identifiers, or retrieving functional annotations and publications. Don't use for sequence alignment, protein folding, or sequence similarity search (use specialized skills for those tasks).

Quality

92%

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

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 commands, clear workflows with validation checkpoints, and clean progressive disclosure to verified reference files. The main weakness is repetitive restatement of the bulk/stream guidance across multiple sections.

Suggestions

Consolidate the stream-vs-search and `--limit` guidance into a single 'Bulk retrieval' section and remove the duplicate restatements in Available Tools and Common Mistakes to improve token efficiency.

Reduce repetition of the 'prefer stream/sparql for bulk data' rule, which appears in Bulk Retrieval Priorities, the IMPORTANT callout, and Common Mistakes.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence, but the stream/`--limit` limitation and 'prefer stream/sparql for bulk' guidance are restated across Available Tools, Bulk Retrieval Priorities, and Common Mistakes, which could be tightened into a single source.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands (e.g., `uv run scripts/uniprot_tools.py count "taxonomy_id:9606"`) and concrete SPARQL query patterns for each mode.	3 / 3
Workflow Clarity	Workflows are clearly sequenced with checkbox checklists (Protein Research Workflow), numbered pivot strategies for search misses, and explicit validation checkpoints ('ALWAYS perform a `count` before running a `search`', 'use `--limit 5` to verify').	3 / 3
Progressive Disclosure	SKILL.md serves as a clear overview with well-signaled one-level-deep references to real bundle files (references/sparql_examples.md, references/search_query_fields.md, references/id_mapping_documentation.md), keeping detailed reference material appropriately split out.	3 / 3
	Total	11 / 12 Passed

Description

100%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 specific, concise, and complete with clear positive and negative triggers, written in third person. It is well-distinguished from adjacent skills via explicit exclusions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions such as 'Access protein metadata, function, taxonomy, and sequences' and 'mapping identifiers' and 'retrieving functional annotations and publications' rather than vague abstractions.	3 / 3
Completeness	Explicitly answers both 'what' (access protein metadata/function/taxonomy/sequences across three databases) and 'when' ('Use when searching for proteins, mapping identifiers, or retrieving functional annotations'), with explicit negative triggers.	3 / 3
Trigger Term Quality	Includes natural user phrases like 'searching for proteins', 'mapping identifiers', and 'functional annotations' that a user would naturally say, plus database names (UniProtKB, UniParc, UniRef) as recognizable hooks.	3 / 3
Distinctiveness Conflict Risk	Has a clear UniProt-specific niche and an explicit 'Don't use for sequence alignment, protein folding, or sequence similarity search' clause that steers toward specialized skills, minimizing wrong-skill triggering.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

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

Reviewed: 7 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.